Skip to content
85

Awesome Jev

A verified, community-maintained catalog of 997 open-source projects built with Jev.

1.1k stars84 forks967 entriesLast push Nov 12, 2026 (4 days ago)License MIT

This page lists names, links and short descriptions. The original list on GitHub is the source and belongs to its authors.

5 projects added on 2026-11-12 >Official (6)

TypeSafe agent skills

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

In 2 lists

System One adapter (Python)

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

In 2 lists

TypeSafe JavaScript SDK

Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk.

TypeSafe Python SDK

Official sync and async Python client. pip install typesafe-sdk.

TypeSafe Daggerverse

Official collection of reusable Dagger modules for TypeSafe AI and System One workflows.

TypeSafe Overwatch

Official tooling for observing and evaluating System One workflows.

5 projects added on 2026-11-12 >SDKs & clients (61)

openai-scala-client

Scala client module for TypeSafe System One that submits Jev Noul, Choice, and Score questions and returns typed answers.

In 2 lists

advocaat

A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.

In 2 lists

ruby_decision_model

Ruby client for decision models such as Typesafe Jev

In 2 lists

spring-ai-typesafe

A Java SDK for the TypeSafe AI JEV API, & Spring AI TypeSafe integrations.

In 2 lists

pijev

Permutation Invariant Jev.

pi-typesafe

Pi extension with a batched Jev evaluation tool, terminal playground, and typed API for other extensions.

TypeSafe Swift SDK

SwiftPM client for the TypeSafe System One API with typed Noul, Choice, and Score questions.

jev (dannote)

TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.

In 2 lists

typesafe-ai-php

PHP 8.2+ client for Jev with typed Choice, Score, and Noul request builders, result classes, retries, and base-URL overrides.

In 2 lists

go-jev

Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions.

jev (stefafafan)

Go Unix CLI for typed Jev decisions through TypeSafe, Cloudflare, or Vercel, with structured response validation and JSON or text output.

swift-jev

Swift client for TypeSafe Jev typed judgments instead of generated text.

typesafe-ai

Typed TypeSafe AI clients for Rust, with async and blocking backends and observable retries.

In 2 lists

typesafe-sdk-go (Tangerg)

Go SDK for the TypeSafe AI API — typed questions in, probability distributions out.

Jev PowerShell

PowerShell module that submits typed Noul, Choice, and Score questions to Jev and returns pipeline-friendly structured answers.

In 2 lists

zod-jev

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

jev-dsl

Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels.

scala-jev-sdk

Scala SDK for Jev. No effect system bundled.

super-jev

A small, extensible decision-to-action harness for TypeSafe Jev.

In 3 lists

typesafe-dotnet-sdk

Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.

In 2 lists

typesafe-sdk-swift (alterhq)

Dependency-free Swift 6 client for Jev Choice, Score, and Noul questions, with strict concurrency, retries, and offline transport tests.

In 2 lists

typesafe-sdk (joshmn)

Ruby client for typesafe.ai.

jev-go (Gaurav-Gosain)

Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text.

typesafe-ai-rs

Independent async and blocking Rust SDK for the TypeSafe AI System One API.

typesafe-sdk-swift

Swift SDK for TypeSafe AI.

zio-typesafe-ai

Scala 3 / ZIO client for the System One API: typed end-to-end, several questions per round-trip via NamedTuple.

In 2 lists

jod

Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.

typesafe_sdk

An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.

jev-java

Idiomatic Java SDK for TypeSafe AI Jev System One decision engine.

typesafe-ai-go

Community Go client for the TypeSafe System One API with typed question builders, retries, examples, and jev-latest as the default model.

typesafe-sdk-rust

Rust SDK for the TypeSafe AI API.

typesafe-go (cole-gillespie)

Unofficial go SDK for typesafe AI, with typed answers, retries, and context support.

jevgo

Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation.

TypeSafeAI.Net

.NET SDK for the TypeSafe AI platform.

typesafe-sdk-java

Community Java client for the TypeSafe System One API (unofficial).

SystemOneSharp

.NET 10 client for hosted Jev and compatible local servers, with typed Choice, Score, and Noul answers plus Microsoft AI integrations.

jevclient

Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.

jev

Unofficial Go client for TypeSafe's System One API and its model, Jev.

typesafe-sdk (binnash)

PHP & Laravel SDK for TypeSafe AI's JEV Model series.

typesafeai-go

Go SDK for TypeSafe AI API https://docs.typesafe.ai/api.

jev-go (guillemus)

Unofficial Go SDK for TypeSafe AI's Jev API.

typesafe-client

Unofficial typed async Rust client for the TypeSafe System One API.

typesafe_sdk_ex

Typesafe AI SDK in Elixir using Req.

decido

Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright.

typesafe-go (zhirschtritt)

Idiomatic Go SDK for the TypeSafe AI API.

typesafe-sdk-php (Butochnikov)

Unofficial PHP client for TypeSafe System One with typed Choice, Score, and Noul requests and synchronous or concurrent transport.

jev-sdk-java

Type-safe Java 21 client for the TypeSafe AI Jev (System One) decision API

DecisionKit

Provider-independent .NET decision library whose Jev provider maps typed Choice, Score, and Noul questions to the System One API.

In 2 lists

pydecide

Python client for typed Choice, Score, and Noul decisions across Jev, OpenRouter, OpenAI Decisions, and local models, with confidence-based fallback and a System One-compatible server.

In 2 lists

s1-rs

Typed System One layer for Rust (Choice/Score/Noul).

typesafe-rs

Latency-first Rust SDK for TypeSafe System One.

typesafe_ai (hfiguera)

A supervised Mint client for the TypeSafe AI System One API.

kunobi-jev

Rust client for the TypeSafe System One API (Jev).

jev-cli (lhotwll217)

JSON-in, typed-decisions-out CLI for the TypeSafe System One API.

typesafe

An idiomatic Elixir client for the TypeSafe AI API.

typesafe.zig

An idiomatic Zig client for the TypeSafe AI API.

tinyjevclient

An integration with jev by typesafe.ai in Rust.

typesafe_ai (typesend)

Unofficial Elixir SDK for the TypeSafe AI API.

typesafe-sdk-go

Unofficial Go SDK for the TypeSafe AI System One API — 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.

typesafe-sdk-php

Unofficial PHP SDK for the TypeSafe AI System One API — 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.

typesafe-go

Unofficial Go SDK for TypeSafe AI's System One API (Jev).

5 projects added on 2026-11-12 >Jev-like models (87)

laya

Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request.

In 3 lists

SemIf-OpenJev

Open-model semantic-if engine for local Jev-style decisions.

In 2 lists

SemIf

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

kev

Trainable family of small Qwen-based Jev-like decision models with typed primitives, datasets, evaluation tools, and local inference.

In 2 lists

NeoHorse-Jev

Open 4B decision model with prefill-only Choice, Noul, and Score inference over text or one image, plus native, vLLM, and SGLang runtimes.

In 2 lists

jevos

Local 1B CPU decision model with Jev-compatible Noul responses; it returns P(yes) and explicitly rejects Choice and Score.

In 3 lists

Jeff

Local Qwen3.5 and Gemma 4 fine-tunes with a Jev-compatible API for typed Choice, Noul, and Score decisions in one forward pass.

In 2 lists

LocalJev

Local Jev-compatible System One API that converts typed questions into DiffusionGemma classification prompts and probabilities.

von

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

In 2 lists

Flide

Inference engine serving open Jev-style decision models through the /v1/systemone API.

In 2 lists

Simple Jev

Open-model Jev-style server that reads next-token logits to return typed choices, rubric scores, and truth judgments.

In 2 lists

deepopen

非自回归System 1决策引擎,专为结构化类型决策场景设计 DeepOpen Multilingual, non-autoregressive System 1 decision engine.

laya

Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime.

Jeeves

Reasoning Jev-style 9B classifier with a diffusion drafter and compatible API for typed Noul, Choice, and Score decisions.

Intern-Decision

Multimodal Qwen3.5 decision models that answer multiple typed Choice, Score, and Noul questions with probabilities in one forward pass.

openjev-sglang

Jev-compatible API server built on open models and SGLang, with prefill-only inference and typed decision endpoints.

agent-jev

AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.

Open-Jev

Open probability decisions with Qwen3.5-2B, Qwen3.5-9B and Qwen3.8-27B.

rizzo-flow

The open, local take on Jev: typed decisions from an LLM, without generating a single token

jeff

Self-hosted Jev-compatible System One server backed by GLiNER-family models, with batching and typed question support.

In 2 lists

Phocinae-Largha-150M-v1

Open bilingual mmBERT-based 144.3M decision model returning Choice, Noul, and 2–10 Score answers with probabilities through a separate local PyTorch runtime.

In 2 lists

VideoJev

Open 4B and 35B-A3B video decision models that share a video prefix across questions and directly score temporal-grounding intervals and multiple-choice answers without text generation.

In 2 lists

djev-spark

DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe No repository-level license file was found during review.

openjev

Open, Jev-compatible System One decision server on DiffusionGemma.

AnyJev

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating).

In 2 lists

imajev

Local multimodal decision models that answer Jev-compatible typed questions over records, text, and up to two images, with explicit abstention.

laya-ultrafast

Same as jev-ultrafast but using Laya.

LLM2Jev

Adapter that turns local language models into Jev-style Choice, Score, and Noul decision engines with typed probabilities.

CLM

Contrastive language model for one-pass typed decisions and option probabilities.

In 2 lists

OpenJev

OpenSource Jev.

open-jev-fast

Specialized CUDA inference backend for Open-Jev-27B with a drop-in Jev-compatible server, prefix-tree reuse, and checked benchmark artifacts.

jimothy

Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js.

JevEmbed

Framework and fine-tuned embedding models that turn cosine similarities into Jev-style Choice, Score, and Noul probabilities.

JevK5

Open-weight Jev alternative that returns typed decisions with probabilities in one forward pass.

In 2 lists

OpenDecision

Open semantic decision engine implementing Choice, Noul, and Score primitives with a TypeSafe comparison harness.

In 2 lists

open-jev-typed-decision-engine

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

TypeLLM

Type-safe language-model generation and structured decisions.

solar-mini4-jev

Solar Mini–based local model for Jev-style typed decisions.

laya-server

Self-hosted API and web interface for Laya decision models with a Jev-compatible API shape.

Open Medical Jev

Frozen open-model medical decision stack that scores each exam option, then uses confidence and conformal gates to auto-release or escalate answers.

In 2 lists

OpenJev-Vision

Open visual decision model that encodes an image once and answers multiple structured questions.

djev

Jev-style structured decisions on DiffusionGemma: the example server from vLLM PR 57250.

Valen

Training stack for a multimodal Jev-like System One model with vision.

jevify

Supersimple way to serve LLMs as a Jev-like endpoint.

jev-forge

Training and inference stack for calibrated Jev-style choice models with dynamic candidate sets.

In 2 lists

OpenSourceJev

Turning an LLM model into a Jev like System.

typed-decision-bert

Unofficial PoC: a BERT-style encoder decision engine behind a typed-decision (noul / choice / score) HTTP API. Not affiliated with TypeSafe.

open-jev

open-jev is a browser-focused TypeScript library for typed decisions: one piece of text (the state) plus any number of typed questions go in, and one forward pass returns a calibrated probability distribution per question. Nothing is generated, so an answer is always one of the options you provided.

OpenThai-SystemOne

Open Thai-English System One model with Choice inference, calibration, evaluation scripts, and a Jev comparison suite.

MoJev

Open model for typed, calibrated decisions in one forward pass.

OpenJev

Open probabilistic Choice, Noul, and Score API powered by constrained open-model log probabilities.

gutsy

Local Qwen3.5-0.8B decision model using llama.cpp label probabilities for Noul, Choice, and Score, with a Jev-compatible HTTP endpoint.

In 2 lists

sys1

Rust System One–compatible API for open decision models such as Laya.

Mica v0.1 4B

Open 4B English/Korean decision model with Jev-compatible Choice, Score, and Noul probabilities plus BF16 and GGUF weights.

arbiter

Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent integrations.

stuntd

Local Jev-compatible proxy that learns an application’s typed decisions and serves them with a Laya head.

In 2 lists

notjev

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint.

open-jev (JoshuaSP)

Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results.

JEV-CPU

Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI.

snap

Local Jev-compatible typed decisions from unstructured state in one forward pass.

ollaya

Local decision-model runner with a Jev-compatible System One API.

In 2 lists

Eikos

Open decision models for finance with a Jev-compatible typed API and evaluation runners.

tev1

Open-weight Jev-inspired decision model fine-tuned from Qwen3.5 4B.

laya-mps

Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses.

blink

High-performance System One model with an embeddable C runtime and WebAssembly support.

JevAny

Open Jev-style model and training stack for typed decisions and option probabilities.

Nemotron_Jev

Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the model, the original Decision Lab explorer, and a TypeSafe-shaped API.

open-jev

an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch.

snapjudge

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text generation. TypeSafe-compatible HTTP API, runs on MLX.

jevper

Jev-shaped classification wrapper over OpenAI-compatible clients that returns probabilities and confidence.

Bev

Local Jevfire-style candidate scoring with ternary models and a System One API; probabilities are candidate-relative.

Vev

Qwen3.5-based decision models accepting text and images through a Jev-compatible server, with typed answers from label-token probabilities; weights are non-commercial.

In 2 lists

jev-style

Local 0.8B Jev-style model and compatible server for Choice, Score, and Noul decisions, with agent skills and a Claude Code permission guard.

In 2 lists

JEMM

Open multimodal decision model that returns candidate probabilities for text and screenshots through a Jev-style Choice, Score, and Noul endpoint.

WaterSheep

Local Jev alternative serving Noul, Choice, Score, and multi-label probabilities through a System One-compatible endpoint.

In 2 lists

open-spark-jev

Open local System One implementation for NVIDIA DGX Spark, with a Qwen3-based model, Jev-compatible API, architecture notes, and evaluation tooling.

poorjev

Local Jev-like System One decision layer that returns typed choices and calibrated confidence without a hosted API.

In 2 lists

OpenJev (xingwudao)

OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI. No repository-level license file was found during review.

edgejev

Local Jev-like typed-decision runtime using ONNX and quantized models for offline CPU inference.

Malkuth

Open 2B and 4B multilingual decision models focused on Korean, serving Jev-compatible Choice, Score, and Noul probabilities through Kev.

OneJev

Open multimodal System One model in four sizes that answers typed questions over screenshots, images, video, or text in one forward pass.

jev-local

Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist No repository-level license file was found during review.

In 2 lists

TinyJev

Local 596M typed-decision model with its own weights, Choice, Score, and Noul support, and a Jev-compatible System One endpoint.

In 2 lists

kneejerk

C library on llama.cpp that embeds Jev-style decision models in applications and returns typed answers through the System One request format.

In 2 lists

Diffusion Jev

Independent DiffusionGemma and SGLang typed-decision server for text and images, with a drawing playground and public evaluation artifacts.

In 2 lists

TetraJev

Local decision stack that fuses four readings from two frozen open models, then uses agreement and calibration gates to answer or abstain.

In 2 lists

Verdict

Independent multilingual decision model with calibrated answers, abstention, and a Jev-compatible API.

In 2 lists

5 projects added on 2026-11-12 >Frameworks & integrations (89)

litellm

AI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing.

In 16 listsDetails

oh-my-pi

Coding agent with a TypeSafe judgment provider that uses Jev for typed checks, routing, and workflow decisions.

In 3 lists

json-render

Generative UI framework with an experimental evaluator that lets Jev choose among application-supplied composition criteria.

In 3 lists

eve

Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.

In 4 listsDetails

LangWatch

LLM evaluation platform whose Instant Evals sends production traces to Jev for batched Noul, Score, and Choice judgments.

In 5 listsDetails

ai

Laravel AI SDK with a TypeSafe provider for Jev Choice, Score, and Noul classification requests.

In 3 lists

learn-agent-architecture

Agent architecture examples that use Jev for fast typed control decisions.

In 2 lists

ai-cli

Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.

In 2 lists

hippo-memory

Agent memory library with an optional Jev reranker that judges which retrieved memories are relevant.

In 2 lists

ai-sdk-provider

The OpenRouter provider for the Vercel AI SDK contains support for hundreds of models through the OpenRouter chat and completion APIs.

aiavatarkit

Conversational-avatar framework with a Jev gate that judges whether a speaker has finished a turn.

In 3 lists

smithers

Agentic TypeScript workflow framework with a Jev session checker wired into its workflows.

In 2 lists

pg-jev

Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

In 2 lists

JEV Sees

Visual front end that converts images, video, and RGB-D observations into scene state for Jev to judge object attributes, relations, and risks.

skillbox

Self-hosted, versioned skills library for AI agents with optional Jev recommendations through TypeSafe or an AI gateway.

In 2 lists

ai-backends

API server runtime for common AI use cases — supports multiple models and providers. Run locally with Ollama or LM Studio, or in the cloud via OpenRouter, OpenAI, Anthropic, or Google.

NeuroLink

Unified AI SDK whose TypeSafe decide API supplies typed judgments for model routing, compaction, tools, and retrieval planning.

In 8 listsDetails

jev4pg

PostgreSQL semantic operators where Jev judges text predicates, retaining probabilities and source evidence while SQL handles exact joins and aggregation.

In 2 lists

pg_typesafe

Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification.

jev-shell-history

Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).

milvus-model

Milvus model library with a TypeSafe Jev reranker provider for semantic search.

In 2 lists

vLLM Jev

Serving runtime for open Jev-style text and vision checkpoints using vLLM on Linux or MLX/MPS on Apple Silicon behind /v1/systemone.

beam_weaver

BeamWeaver exposes Jev Choice, Score, and Noul evaluations as provider-neutral decision-model calls in Elixir workflows.

system-one

Provider-neutral System One runtime for TypeScript and the Pi coding agent.

neo4jev

Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships.

In 2 lists

tocket

Jev chooses the next step from bounded options and records that choice in Tocket’s shared project notebook.

jev-tree

Probability-tree and graph runtime for verifiable multi-step Jev decisions.

Jevbridge

ACP and MCP adapter that exposes Jev typed decisions and computer-use actions to Codex, Claude, OpenCode, and other agents.

In 3 lists

laya-php

PHP and Laravel client for Laya's Jev-compatible typed decisions, mapping answers to PHP types; hosted Jev compatibility has not been tested.

Astra

Astra uses native Jev judgments to inspect agent context and choose evidence-backed runtime actions.

Loki

Self-improving agent harness with an optional TypeSafe Jev companion for typed Choice, Score, and Noul judgments.

HA-Jev

Home Assistant integration for TypeSafe Jev. Ask a question about your house and get a probability, a choice or a score as an entity.

In 2 lists

ST-jeved

SillyTavern extension where Jev scores replies against configured narration rules before adding guidance.

laya-jev-GraphRAG

Agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.

duckdb-jev (colliber)

DuckDB extension: typed Jev answers as real SQL types

ruby_llm-typesafe

TypeSafe structured-output provider for RubyLLM 2.

invalidate

The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.

jev-reranker

Jev-powered relevance filtering and reranking for RAG in Python.

In 2 lists

hunch

Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev.

In 2 lists

Prompture

Structured-output library with a TypeSafe Jev driver for Noul, Choice, and Score decisions.

jev-edge

Typed-judgment admission control at the traffic edge: three-layer prompt-injection and abuse filter for nginx/OpenResty, powered by TypeSafe Jev. Fail-open, cached, hot-reloadable.

discern

Craft Type-Safe Uncertainty-aware semantic pattern matching, control flow, and smart procedures for Effect DecisionModel and Jev.

In 2 lists

Turn

Turn programs call Jev for Choice, Score, and Noul decisions and route execution from the typed answers.

JevLint

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

gut

Elixir control-flow library that uses Jev Choice through ReqLLM to select branches.

jevalyn

Rails-native Jev wrapper that turns typed, calibrated decisions into application control flow.

jevframe

Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.

jev-foundation-models

A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework.

In 2 lists

algal

Language and runtime for agent-graph evolution with Jev-backed decisions.

J++

Experimental language and Rust runtime where semantic questions and decision methods are composable program values, with Jev as a supported provider.

jev-feels

Semantic decisions as ordinary Ruby — feels?, decide, score, Rails validations and pattern matching powered by Jev

jevql

Adds jev(), jev_prob, jev_choice, and jev_score to vanilla PostgreSQL queries through a psql-shaped CLI and Go, TypeScript, and Python SDKs.

In 2 lists

a0-typesafe-ai

TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.

typesafe-jev-workflow

Async LangGraph workflow that gets a typed Jev Choice (invoice or general) and routes each inbound email to the matching handler.

In 2 lists

jevsearch

Site search that recalls candidates locally, then uses Jev to score and rerank them.

In 2 lists

typesafe-on-neon

Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing.

In 2 lists

mysql-ailike

Natural-language row filtering for MySQL, powered by TypeSafe Jev.

In 2 lists

llama-index-jev

LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.

In 2 lists

jevals

Framework-agnostic agent evals and guardrails that batch a trace's checks into one request to Jev, Kev, Laya, or a chat-model fallback.

duckdb-jev (prasanthj)

High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL.

In 2 lists

vgi-typesafe

A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions

Decis

Self-hosted Jev-compatible server for Laya and Kev engines with Docker images, official-SDK compatibility, and runnable decision games.

typesafe-ui

Shadcn-style reusable components and blocks for using TypeSafe AI.

laravel-typesafe-jev

Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.

In 2 lists

new-api-plugin-typesafe

TypeSafe AI System One task plugin for New API with a native /v1/systemone endpoint, routing, and token billing.

In 2 lists

typesafe-ai-rails

Community Rails integration on the typesafe-sdk gem: configuration, persisted usage and cost telemetry, and opt-in confidence policies.

jev-ui

React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev. No repository-level license file was found during review.

tripwire

Judge every LLM response before the user sees it. AI SDK middleware and OpenAI-compatible proxy.

jev-layer

Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.

Gut Check

Home Assistant integration where Jev assesses entity health, update risk, and cleanup suggestions, with confidence gates and user-confirmed changes.

In 2 lists

pydantic-jev-examples

Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each.

judging-with-typesafe

Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev).

typesafe-assist

Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model.

hunch

Python library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and DataFrame workflows.

In 2 lists

hunch-js

TypeScript library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and array workflows.

chat2jev

Workbench that converts Chat Completions requests into editable Jev State and Questions, compares text generation with typed judgments, and exposes reusable proxy routes.

Cribrix

RAG pipeline where Jev routes queries, filters retrieved passages, and verifies claims before releasing an answer; code separately checks numeric support.

In 2 lists

jev-connector

Connector for integrating TypeSafe Jev decisions into application workflows.

n8n-nodes-typesafe-ai

N8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities.

hiep-paseo-plugin

Local Paseo plugin that exposes Jev evaluations through MCP.

Jev4Mellea

Jev adapter to Mellea.

ground-zero

Evaluation framework for detecting AI hallucinations and instruction-following failures with Jev.

pytest-jev

Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.

In 2 lists

openclaw-typesafe-ai

Optional typed TypeSafe AI Jev decisions for OpenClaw, with SecretRef credentials and strict API validation.

jev-switch

Local multi-upstream router for the Jev protocol with a Rust backend and React interface.

In 2 lists

Tiltmeter

Drop-in proxy and Pydantic AI client that records Jev probabilities and alerts on model-version changes, distribution drift, threshold crowding, and estimated accuracy loss.

In 2 lists

Yueli DEX

Choice-only decision exchange that routes bounded business decisions to TypeSafe Jev or compatible providers and maps validated results to non-authorizing action intents.

JEV Book Tags

Calibre plugin where Jev Noul evaluates book genres, subjects, and evidence sufficiency, with probability thresholds and review before applying tags.

In 2 lists

vd-jev

VisiData plugin that sends each text-column row to Jev or another OpenRouter decision model and adds typed labels, scores, probabilities, and confidence as columns.

In 2 lists

5 projects added on 2026-11-12 >Agent tooling (239)

claude-code-templates

Claude Code configuration toolkit shipping Jev-based model routing, skill suggestion, and tool guardrail modules.

In 3 lists

openwork

Open-source Claude Cowork alternative whose eval testkit can use Jev as a typed verification judge for agent-produced work.

In 5 listsDetails

fast-jev-compaction

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

In 2 lists

memsearch

Agent memory search with optional Jev relevance judgments to rerank retrieved passages.

In 3 lists

agentconnect

Team agent workspace using Jev typed decisions for response routing and model selection.

In 2 lists

jevgrep

Semantic code-search CLI for coding agents; Jev selects relevant repository branches, files, and source units for a natural-language behavior query.

In 2 lists

distill

Coding-agent runtime using Jev decisions for model routing, context retention, and tool selection.

vexjoy-agent

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

foreman

Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.

In 3 lists

jev-review (devagrawal09)

A staged code-review workflow and local dashboard built with TypeSafe Jev.

In 2 lists

hermes-jev-skills

Hermes plugin and skill suite using Jev for model routing, skill selection, memory filtering, compaction, and GUI actions.

In 2 lists

mu

Coding-agent workspace where Jev or a local Laya judge gates bounded decisions such as context retention, approvals, routing, drift, and inter-agent sharing.

In 6 listsDetails

Keel

Local-first coding workspace where Jev or Laya selects an eligible agent/model route and the host validates every choice before execution.

jev-search

Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.

In 2 lists

decapod

Agent workflow infrastructure integrating decision engines such as Jev and Laya for typed decision evaluation.

Albatross

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI. No black box.

In 2 lists

jev-router (gargpratyush)

Route to the cheapest model in claude code for your task using jev-router.

In 2 lists

jev-gateway

An easy way to use jev with your coding agent for tool calling reasoning.

Astra-Ares

Adaptive reasoning effort for GPT-6 Astra during Codex tasks, powered by Jev to reduce token usage.

compact-adviser

Agent plugin that uses Jev to judge when a coding session should compact its context.

jev-review (NiazMorshed2007)

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

abide

Supervises coding-agent edits and uses Jev to flag violations of project rules.

In 2 lists

glowbom-oss

Coding agents can ask Jev to judge small workflow decisions, such as whether build results look healthy.

Anna-Agent

Anna uses Jev as a fast judgment layer for bounded enterprise-agent recommendations and abstentions.

jev-pruner

Claude Code and Codex hooks that ask Jev which parts of long shell output remain relevant before sending them into model context.

In 2 lists

jev-semgrep

grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる

In 2 lists

jev-mcp (jkudish)

Proof of concept MCP for Typesafe's new Jev AI model.

In 3 lists

building-with-jev-skill

A skill for writing and improving programs that call Jev, TypeSafe's System One model.

typesafe-mcp

Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.

In 2 lists

stanley-code

Bounded TypeSafe Jev workflows for coding agents.

In 2 lists

supercov

Code-quality and coverage reviewer that uses Jev to judge coding-agent changes.

In 9 listsDetails

deepseek-harness-jev

DeepSeek Harness plugin using Jev for skill and file selection, task supervision, output filtering, and approval assistance; features are disabled by default.

In 3 lists

pi-warden

Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.

Building with TypeSafe Jev

Installable agent skill that teaches Jev typed-decision design, validates live API shapes, and indexes reusable patterns from community projects.

In 3 lists

pi-jev (y0usaf)

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers.

In 2 lists

jevmem

Project-memory tooling for coding agents; Jev decides which turns to save, their kind, contradictions, recall relevance, and suspected memory poisoning.

In 2 lists

JevRouter

A lightweight Jev-powered router for models, tools, and subagents.

In 2 lists

skills

Four agent skills use Jev Score and Noul judgments to assess subjective criteria with calibrated probabilities.

jev-codex-router

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

jev-code

Bounded TypeSafe Jev workflows for coding agents.

Quicksilver

Claude Code skill and CLI that delegates bulk ranking, classification, filtering, and semantic-search judgments to Jev.

captaincore

Jev triages malware-scan findings and supplies typed Noul, Choice, and Score decisions for WordPress maintenance.

grok-bot-jev

Grok Bot integration where Jev applies usage gates and routes requests before the generative model runs.

In 2 lists

skillranker

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

In 2 lists

total-agent-memory

Jev checks retrieved memories for contradictions before an agent uses them in an answer.

save-token-jev-clean

Portable, Jev-guided context compaction for coding agents.

jmeter-ai

Jev classifies JMeter agent intent and selects a focused tool pack, with a full-tool fallback when routing is uncertain.

weflow-cli

When enabled, Jev classifies article topics and relevance for WeChat daily digests.

agent-router

CLI that uses Jev task classification to choose and launch Cursor, Claude Code, Codex, or OpenCode with an appropriate model and effort level.

oxlint-plugin-jev

> This package is experimental. Use at your own risk.

jegrep

Semantic grep CLI where Jev judges which files and exact line ranges match a natural-language code query.

jev-lint

Text linter that uses Jev Score judgments to evaluate strings embedded in source code against configurable writing rules.

Canny

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

In 2 lists

jev-recruiter

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

jev-rules

Claude Code plugin where Jev decides which project rules apply to each prompt and edited file.

jev-sift

Agent plugin and MCP tool where Jev classifies batches of text so agents can read only the relevant items. No repository-level license file was found during review.

duet-agent

Full-stack agent harness with memories, long-running tasks, multi-agent relay, and a Jev-backed model-routing table.

In 2 lists

hono-jev-router

Route HTTP requests by meaning. A semantic router for Hono powered by Jev.

In 2 lists

JevRev

An LLM + Jev workflow. Boost your vertebrate brain with a spine inside.

skilled-agent-harness_spec-driven-loops

The cli-jev transport routes typed-judgment requests from the skill harness to the Jev CLI and MCP interfaces.

jev-dsh-decision

Decision plugin for DeepSeek Harness and iPolloWork that lets OpenCode, Codex, and other agents use Jev to select tools, skills, and task owners and evaluate outputs.

ask-jev-skill

Skill for Hermes, and other agents, to ask typesafe's jev.

Jev-Mem

Jev-Mem: System-One Controlled Agentic Memory.

obsidian-llm-hub

Obsidian plugin for AI chat, workflow automation, and semantic search — supports Gemini, OpenAI, OpenRouter, Grok, Ollama, and CLI backends.

jev-skill-suggester

用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.

In 2 lists

pi-jev-skill-picker

Rank Pi Agent Skills for the current task with TypeSafe Jev.

In 2 lists

jevgrep

Semantic code search CLI and MCP server: Jev scores authorized repository excerpts and returns exact file paths and line numbers to coding agents.

ai-news-aggregator

Multi-agent AI news pipeline powered by GLM-5.3-Flash and Jev.

winnow

A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.

jev-judge-mcp

MCP tools that expose Jev for verification, screening, classification, reranking, review, gating, and scoring.

jev-permission-gate

Claude Code mod that asks Jev Noul questions about tool-call intent and risk, then allows, denies, or defers to the built-in classifier under explicit thresholds.

snifftest

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

In 2 lists

jev-use

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

In 5 listsDetails

agent-chaperone

MCP proxy that uses Jev to screen agent tool calls and tool results.

In 2 lists

jev-agent-design-with-topk-logits-choices

Jev-native agent design with top-k proposals, fallback decisions, memory, and replanning.

pi-advisor

Customizable Advisor and Executor workflow for Pi with Jev decision support.

jev-mcp (burnigtm)

MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.

In 2 lists

ErisLint

Rust linter powered by configurable Jev rules, with a VS Code extension.

Multi-Agent

Multi-agent orchestration engine with warm sessions, a durable mailbox, and per-task token accounting.

yoshi

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into Compozy.

In 2 lists

pi-jev (TheoOliveira)

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev.

In 2 lists

cnki-skills

The optional cnki-jev package uses Jev for first-pass literature screening and escalates complex cases for model or human review.

pi-jev-auto-mode

Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

jev-axi

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.

In 2 lists

oh-my-harness

Tame your AI coding agents with natural language. Generate enforced guardrails (CLAUDE.md, hooks, settings) from a single command.

zero-api-key-web-search

Jev-powered search infrastructure for AI agents: zero API keys, MCP-ready, LLM-context aware, with local neural evidence verification.

dsh-jev

Jev-powered decision layer for DeepSeek Harness.

a3m-router

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel ensemble merge. npm: adaptive-memory-multi-model-router.

jgrep

grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.

In 2 lists

jev-cli

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.

JevLoop

The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed.

In 2 lists

deepreseach-learing

Jev runs in shadow mode to append structured quality evaluations to generated deep-research reports.

jev-test-filter

Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, cargo test and go test already understand.

jevvy

Jev-powered plugins for coding agents.

pi-review

Jev screens likely defects, arbitrates ambiguous findings, classifies scope, and supports cross-round review memory.

is-malicious

Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.

In 2 lists

pi-jev-router (philippdubach)

Pi model router that uses Jev task classification and a measured Pareto frontier over quality, cost, and latency to select an OpenRouter model.

patdown

Block, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, and more. Built with Effect.

MetaCog

MetaCoginition powered by Reflex 4B.

Tiermem

The Jev integration routes agent memory queries between compact Markdown notes and searchable raw history.

azdaja

Azdaja exposes optional Jev semantic judgments inside a bounded local evaluation surface.

jevyoumean

Semantic "Did you mean?" for any CLI — wraps commands and uses TypeSafe's Jev to match subcommand typos by intent, not edit distance.

In 2 lists

jgrep

Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.

In 2 lists

jev-code

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.

jevcore

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

claude-jev

Claude Code plugin that uses Jev for rule checks, verbatim compaction, and prompt routing.

lintus

Natural-language linter that uses Jev to evaluate code against plain-language rules.

jev-seo

Agent-first SEO and GEO CLI suite and MCP server using DuckDuckGo evidence and Jev scoring.

In 2 lists

jev-mcp (blakestone-x)

MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer.

In 2 lists

jev-cli (Nasrallah-AL)

Command-line tool for TypeSafe's Jev AI model.

slop-grader

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

In 4 listsDetails

cmd-mod-jev-nudge

Command Code mod: nudges the agent to keep going when it stops with work left, judged by Jev.

eutrya

Jev-native AI security harness for autonomous research, multi-agent swarms, persistent hunt boards, and long-running agent workflows. CLI-first, open source, and built for authorized security research.

pi-jev

Jev-assisted file retrieval and request caching for faster Pi workflows.

zevals

Jev judges yes-or-no assertions about an agent transcript, and the test passes when its probability reaches the configured threshold.

pi-jev-router

Task-boundary model routing for Pi Coding Agent, powered by TypeSafe Jev. Conservative policies, exact caching, and observable failover.

jev (BorisLeMeec)

A claude code plugin for jev.

jevwire

Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).

JevLint

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

jev-guard

Prompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev.

In 2 lists

jcr

Jev Capability Resolver: agents query a nested capability tree and receive only the deterministic commands and context relevant to the task.

evoke

Software, by reflex. A sentence becomes a call of a small program, chosen by Jev, TypeSafe AI's classifier, and run only when it is sure enough. Reflexes are recipes anyone can write, share and improve. A CLI you talk to, a package manager for reflexes from git, and a TypeScript SDK.

liteagents

Provider-independent agent SDK that uses typed routing to select a model for each turn.

jev-belay

Claude Code Stop hook that asks four Jev questions when files changed without a passing check, blocking unverified completion claims while failing open on errors.

In 2 lists

hermes-jev-approvals

PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

In 2 lists

typesafe-skill-router

TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.

jev-agent-skill-router

Typed, confidence-aware agent skill routing with TypeSafe Jev.

In 2 lists

pi-quiet-ask

TypeSafe Jev as the pi coding agent's quiet decision layer.

In 2 lists

hermes-jev

Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

jev-router

LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.

omp-jev-compaction

Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter.

pi-jev-router

Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway.

In 2 lists

clean-code-review

Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

In 2 lists

opencompany

AI workspace whose approval review uses Jev to gate workspace actions with typed decisions.

In 2 lists

jev-architect

Agent skill for finding, designing, and validating useful Jev decision loops before committing them to an application.

In 2 lists

pi-jev-context

Model performance first. Token savings second. A Pi extension with freshness-aware read dedupe, Jev log filtering, and searchable verbatim recall. Keeps existing message history intact.

jev-mcp (arunav25)

Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.

pi-fast-jev-compaction

Pi extension: verbatim context compaction with TypeSafe Jev decisions.

In 2 lists

riff

A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.

jev-commit

Pre-commit hook where Jev checks the message against the staged diff and flags debug leftovers, unmentioned work, and added credentials.

In 2 lists

bicameral

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

jev-superpowers

Cross-agent software-development skills that add Jev decisions to planning, execution, debugging, and completion gates.

In 2 lists

slidepilot

Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev.

diffjury

DiffJury — TypeSafe Jev PR risk router + code review coach.

In 2 lists

tenet

Commit-time review gate where Jev judges plain-language rules against agent-written code.

jev-spec

Specification-driven semantic verification engine that uses Jev to check AI-generated code and specs against explicit requirements.

jev-tool-router

MCP router for Codex that uses Jev to select an external tool on demand instead of exposing the agent to every tool schema.

jev-pref

Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.

In 2 lists

jev-oas-sentinel

Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.

Augustus

Agent skill for designing Jev-assisted systems with decision theory, composition patterns, question diagnostics, and validation gates.

In 2 lists

typesafe-cli (geilt)

CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.

jev-judgment

Agent Skill: send closed coding-agent judgments to TypeSafe Jev.

In 2 lists

jevex

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

fast-dev-compaction

Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.

In 2 lists

pi-heed

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

In 2 lists

jev-router (prismhq)

Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM.

In 2 lists

jev-mcp (rashedInt32)

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

open-jev-approvals

Approval gate for Claude Code and Codex: intercepts tool calls, gets a Jev risk judgment, then applies a versioned local allow/deny policy.

dsh-jev

DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.

prompt2jev

Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script

jev-mcp-dispatcher

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence. No…

hermes-jev-plugin

TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate

langchain-skill-router

LangChain and deepagents skill router where Jev ranks installed SKILL.md files and decides whether and which skills to load for each turn.

In 2 lists

jcm-router

Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.

In 2 lists

typesafe-mod

Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.

jev-shield

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

mastra-jev-moderation

Mastra input processor that uses Jev for a typed block decision and moderation category.

In 2 lists

tiershift

Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

skill-router

Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.

todo-jev

⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One).

jev-workbench

Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.

typesafe-migration-guard

Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model).

pi-fast-jev-compaction (QuentinDanblon)

Pi context pruning that uses Jev to drop or truncate stale tool calls while preserving retained content verbatim.

jev-system-architect

System-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.

jev-skill-gate

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

ailerix

Type-safe model router. Jev (System One) banks each request to a typed catalog route.

typesafe-ai-firewall

Shadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md. No repository-level license file was found during review.

jev-mcp (freepik-company)

MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe

decision-first

Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt

jear

Jev-routed client for NEAR AI Cloud inference and IronClaw agents.

agent-reflex

Coding-agent plugins where Jev or a compatible System One model judges shell risks, task complexity, context retention, and tool exposure, with capabilities varying by host agent.

jev-git

Sub-second pre-commit and pre-push semantic gate that screens staged diffs with Jev.

In 2 lists

jev-scout

Grounded GitHub and crates.io discovery CLI and MCP server that uses Jev to score architectural fit, licensing, and maintenance.

In 2 lists

jev-skillful

Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.

jev-triage

Uses typeful jev, zero sync to pull and sync large repositories for issue triage.

In 2 lists

jev-predict-skill

Predict another skill's next closed decision with TypeSafe Jev — without running that skill.

stepwarden

Claude Code plugin that has Jev compare each pending tool call with the session plan before allowing, escalating, or blocking it.

Antigravity-mcp-semantic-search-with-TypeSafeAi

Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.

pi-jev

Pi extension suite for Jev-powered context compaction and model routing.

hunch

Semantic code review with Jev, plain-English rules, and installable agent skills.

In 2 lists

limpet

A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.

In 2 lists

ask-jev

Utilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.

jev-flash-router

MCP server that uses Jev to route coding-agent decisions such as file selection, task paths, and test-impact checks.

omp-typesafe

TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent.

pi-jev-helm

Pi extension that classifies tasks with Jev and routes each run to an explicitly configured model.

jev-mcp (BYK)

An eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text.

askjev (pZacca)

Unofficial MCP server for Jev (Typesafe AI)

jev-toolkit

MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.

jev-skill-router

Claude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer (shadow-first). A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router.

In 2 lists

dsh-jev-verify

Jev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.

jevonian

Local model-routing proxy where Jev selects the model route and reasoning depth, and also judges which tool history can be compacted.

In 2 lists

jev-routed-agent

LangChain and Flask agent where Jev chooses among knowledge, calculator, weather, and chat routes, with a local-rule fallback.

codex-jev-router

Portable Jev router for cost-aware Codex subagent model and reasoning selection.

In 2 lists

XavierJev

Local logprob decision layer and Claude Code permission gate that scores command risks, routes model tiers, and judges retries or stuck runs.

Jev Deep Research

Research-agent integration where Jev locates relevant source regions with Choice and Noul, then code returns verbatim passages for verification.

omp-statify

Oh-my-pi extension that asks Jev batched Noul relevance questions about tool-output and earlier assistant-text chunks before main-model context, with opt-in filtering and recoverable originals. No repository-level license file was found during review.

Jev Decision Gate

CLI, MCP server, and skill using Jev Choice to classify Issue kind, module, and information sufficiency, with calibrated accept/review policies and an offline rules baseline.

jev-judge

Test runner evaluating recorded LLM outputs with Jev assertions and CI reports, with an offline mock and documented response-parsing limitations.

In 2 lists

pi-agent-foreman

Send Pi agents back to work when they stop before the job is done.

switchboard

Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.

typesafe-demo-mcp

MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.

AskJev-MCP

MCP server for typed Jev Choice, Noul, and Score judgments with probabilities and confidence.

decide-mcp

Configurable decision MCP server with AI SDK, Jev, percentage scores, and bias-profile routing.

In 2 lists

pi-jev-router (gloridifice)

Jev model-routing integration for the Pi coding agent.

jevkeep

Codex plugin that uses Jev to preserve useful conversation excerpts alongside compacted summaries.

pi-jev-code

Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.

pi-typesafe-jev

A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.

In 2 lists

frost

A flexible and configurable CLI model router using TypeSafe Jev.

check-risk

A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge.

jev-compaction (picaye)

Hermes context compaction that has Jev score tool calls, drops stale content, and preserves everything retained verbatim.

jev-plugins

Cursor and Hermes plugin marketplace for JEV Labs routing tools.

jev-builder-loop

Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act).

typesafeai-review

Using Typesafe.AI to generate diff reviews.

agent-gate-loop

Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev.

omp-jevens-classifier

Jev-powered model-judged permission gate for OMP (TypeSafe System One).

jev-review (thiago-ss)

Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.

pi-typesafe

Pi coding-agent extension built on the TypeSafe AI System One API (Jev).

hermes-jev-router

Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.

zcode-jev

Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.

agent-handoff-gate

Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent.

jev-agent-kit

jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.

Jev-Checkpoint

A local MCP server that uses TypeSafe Jev to confidence-gate an AI agent’s next step, routing uncertain decisions to proceed, deeper review, or human input.

progressgate

Detect semantic stagnation in AI agent loops

jev-packs

Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints

JevGuard

Claude Code + Codex CLI plugin that verifies the agent follows project rules through a System One (Jev) model

jev-atlas

Map where Jev and System One models actually belong in your project, test the strongest ideas, then implement them. A skill for Claude Code and Codex.

jev-retrieval

Code and document search CLI combining BM25 recall with Jev verification and calibrated reranking.

In 2 lists

Immune

Python runtime screening for LLM applications where Jev judges suspected threats in prompts, tool calls, and responses before threshold-based actions.

local-decider

Experimental pre-action gate that applies deterministic rules before asking Jev or a local compatible model whether an unresolved tool action should proceed or require confirmation.

In 2 lists

5 projects added on 2026-11-12 >Browser & computer use (77)

cua

Computer-use platform with a Jev recipe where the model selects one bounded action candidate and the client validates it before execution.

In 4 listsDetails

Jev Ultrafast

Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed.

In 3 lists

agent-desktop

Desktop automation runtime with a Jev skill that chooses UI operations and targets from accessibility-tree candidates.

celesto

Agent-computer platform with a runnable pull-request review lab where Jev judges whether findings are introduced, supported, and actionable.

reticle

Runtime perception layer that gives web and desktop agents Jev-style machine-readable state.

surf-cli

Optional Jev commands find, filter, and verify browser elements, then select bounded actions subject to confidence and write-authority checks.

Jev-cu

把 Computer Use 的「下一步点哪里」交给 Jev(TypeSafe System One):Jev 从界面文字候选中选元素、动作、完成度与风险,Codex Computer Use 负责读取界面与执行,本地策略门槛拦截敏感操作。 Only send text, not screenshots..

In 2 lists

typesafe-computer-use

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

mobile-jev

Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.

In 2 lists

FluidUse

Apple-silicon computer-use toolkit that runs local typed-decision models to choose form-fill actions from macOS accessibility state.

jev-browser-use

5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.

In 2 lists

jev-browser

Browser use using Typesafe's Jev model.

In 3 lists

unclutter

WXT browser extension: Jev-powered page clutter removal with reusable template rules.

In 2 lists

arc-cua

Jev selects the next UI operation from the targets and actions exposed by the current desktop state.

jev-voice-browser

Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

webctl

Smart web search CLI for agents, backed by Jev. Saves a lot of tokens.

fast-browser-use

A fast browser-use skill powered by local LLMs via single-token reflexes. Fast, local-first, zero hallucinations.

Jevry

Desktop browser where Jev selects executable browser actions and a separate text model handles planning.

jev-browser

Indexed browser automation where Jev selects a control and Playwright executes it.

jev-use

Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model.

jev-desktop

TypeSafe Jev action selection inside Codex Computer Use.

In 2 lists

playwright-recast

Jev chooses camera moves, emphasis, and timing from a rendered Playwright recording and bounded direction candidates.

typesafe-adblock

🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.

In 2 lists

ghosthands

Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.

vibecheck

Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post.

computer-use-cache

Jev judges whether a cached computer-use workflow is semantically reusable for the current request.

jev-cua

macOS voice and text control where Jev selects UI actions in an observe–act–verify loop.

jev-browser-skill

Isolated Playwright Chromium driven by Jev. A coding agent (or you) runs a.

Jevbridge

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

ulka

Experimental browser agent powered by FX, Jev, and Vercel AI Gateway. Bring your own API key to read pages and automate browser tasks.

jev-browser (Ying-Kai-Liao)

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

hookmeter-jev

⚡ Millisecond-level Viral Hook Telemetry & Co-pilot for Social Media (Chrome Extension + JEV System 1).

jev-mac-voice

English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev.

jev-for-chrome

Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.

In 2 lists

Jev macOS Loop

Native macOS automation loop where Jev chooses the next GUI action from OCR, accessibility, and OmniParser observations.

x-scanner

Chrome extension where Jev scores and labels X posts with typed judgments and a live local cost counter.

lkclean

Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.

jev-ultrafast-mcp

Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.

system1-agents

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics.

jev-chat-for-twitch

Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension.

In 2 lists

jev-social

Social research agent for Instagram, TikTok, and LinkedIn: Jev repeatedly chooses the next concrete operation and target, while socai executes it in a local Chrome session.

In 12 listsDetails

live-jev

2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model.

sift

Chrome extension where Jev labels X posts by content type and judges which posts should be hidden.

In 2 lists

xtags

在 X 的时间线上,给每条帖子标出它想让你干什么。判断来自 Jev,一个只返回概率、不生成文本的模型。

jev-ego

TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.

jev-browser-bridge

CDP browser library using batched Jev Choice questions to select operations and DOM-derived targets.

In 2 lists

AskJev

AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude).

jev-agent-browser

Browser-agent integration where Jev selects typed actions for research and classification workflows.

In 2 lists

fastbrowse

Browser agent where Jev selects actions, an LLM reads and plans, and answers cite page evidence.

In 2 lists

jev-browser (vinilana)

Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.

jev-browse

Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark.

computer_use

MacOS computer use driven by Jev (TypeSafe System One) as the decision maker.

jev-skip

YouTube extension that asks Jev for the sponsor probability of each caption segment and paints the result on the seek bar without a crowd database.

In 2 lists

playjev

Experimental Playwright library for natural-language browser automation, using Jev to turn page state and instructions into typed actions.

Sedum

Playwright testing tool where Jev selects actions and page elements and judges verification claims, while code executes browser operations.

In 2 lists

jev-mobile

Fast structured Android control loops with TypeSafe Jev and Mobile MCP.

In 2 lists

jev-frontend-qa

Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.

otto

Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.

jevarena

Two Jev agents compete in click-only browser games through Browser Use.

turbo

Jev-powered semantic browser use.

jev-browser (tontoko)

One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

jev-shield (vmendes90)

Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev.

jev-ra

Browser automation MCP server where Jev chooses the next bounded browser action for a coding agent.

barrunto

A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse.

almond-fastloop

Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.

psearch

Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.

jev-browser-skill

Claude Code and Codex browser skill that asks Jev to choose the next browser action.

jev-browser-pilot

Bounded browser and desktop automation where Jev picks one next step while code owns perception, execution, and verification.

jev-orb

Push-to-talk voice orb for autonomous browser control using Jev and Metal Whisper.

JevTest

Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.

browser-use-olympics

Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).

jev-browser (KesavanKing)

Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.

jevlens

Chrome extension that uses Jev to annotate articles and posts on X and Threads.

jev-playwright-mcp

Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.

jev-browser (MahmoudAdelbghany)

Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.

sloppy-jevs-extension

Open-source Chrome extension that filters AI-generated prose and ads with Jev.

sift

Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler.

5 projects added on 2026-11-12 >Applications (137)

TradingAgents

Trading research agents with optional Jev screening of social posts for company relevance and sentiment.

In 7 listsDetails

QuantDinger

Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement.

In 3 lists

genoffice

Jev assigns a calibrated relevance score to each of the top 20 locally recalled files and reranks the search results.

xerj

Jev scores whether each retrieved document answers the query and reranks the search results by that relevance.

In 3 lists

PyGPT

Desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.

In 2 lists

Paca

Project management app using Jev for agent routing, task fields, assignee selection, and automation conditions.

In 3 lists

jev-chat-jarvis

Android conversation copilot where Jev interprets chat context and helps rank candidate replies before the user inserts one.

In 4 lists

jev-trader

One AI trade decision every Monad block. Jev on Kuru MON-USDC.

In 2 lists

jev-chat-windows

Windows WeChat reply assistant that uses local OCR and Jev to classify intent before presenting three manual-send replies.

horosa-skill

When explicitly enabled, Jev selects an astrology technique when keyword routing has no match and extracts settings stated by the user.

claude-code-trace

Jev scores agent progress, tool use, focus, exploration, recovery, and token efficiency from Claude Code session logs.

llm-debugger-vscode-extension

At each debugger pause, Jev chooses the next debugging action from the stack, locals, nearby source, output, and prior attempts.

AIStock

Stock-analysis application that uses Jev for structured market judgments.

tax-doc-classifier

Tax-document classifier where Jev selects an IRS form and page kind from extracted PDF text.

docjev

A very fast document classifier/splitter using Jev.

In 2 lists

jev-chat-jarvis-mac

Jev classifies incoming WeChat or QQ messages by intent and risk before the app presents reply guidance.

summarize

The optional Jev prefilter scores transcript segments before the selected material is sent to the summarizer.

siftrank

Jev compares items against a ranking prompt across repeated batches so SiftRank can produce a converged relevance order.

Goutoujunshi Jev Chat

Cross-platform chat assistant where Jev chooses a bounded reply strategy from reviewed conversation context before the user sends any draft.

notra

Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions.

In 2 lists

crush-monitor

Crush Favorability Monitor: Use Jev to analyze the emotions, intentions and reply performance of WeChat chats. Deploy locally, use your own API Key..

perch

Semantic code linting with Jev.

In 2 lists

OmniStudio

OmniStudio exposes Jev Noul, Choice, and Score decisions for triage, scoring, content guards, retrieval reranking, and intent routing.

Jev-X-Sentiment-Analysis

An on-demand crypto market intelligence and decision-support terminal powered by TypeSafe AI's System One model (Jev).

In 2 lists

jev-webmcp-extension

A small extension that demos the combination of Jev x WebMCP.

superterminal

Jev ranks command-palette entries against a plain-language query so the intended terminal action appears first.

formanator

CLI and MCP server for Forma benefit claims that can use Jev to classify receipt line items into reimbursement categories.

332_lab-jev-chat

Jev Chat Assistant for Windows - PC version of WeChat intent judgment and DeepSeek suggested reply.

jev-chat

A tool calling chat bot built with Jev and no LLM.

warrenduffer

Intraday trading bot where Jev ranks Nifty 50 candidates and deterministic code controls position sizing and risk.

jev-voice

Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

changelog.earth

When enabled, Jev performs bounded editorial and title checks on stories selected for an Earth changelog edition.

james_library

Scientific-agent architecture separating fast local judgment, probabilistic evaluation, evidence, and authorization.

jevmeter

Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit.

prism-liquidity-agent

Solana liquidity agent with optional Jev shadow judgments for deposit choice, toxic flow, and market-regime stress.

shapeshift

An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.

In 2 lists

QuantStudio

Jev evaluates market state from completed candles, live prices, positions, and strategy constraints, then suggests observe, open, or close actions for human approval.

JevIntent

WeChat plugin that uses Jev to analyze message intent, emotion, and reply posture locally.

Stratum

AI-powered Log Intelligence System - Semantic search, anomaly detection, and root cause analysis for logs using RAG techniques. Built with Rust, Axum, NATS, ClickHouse, and Qdrant.

live-jev (okinaaudio)

Ableton Live controller where Jev maps a short natural-language request to a bounded music-production action.

jev-poly-crypto-demo

Crypto decision dashboard that uses Jev to classify market state and risk.

Jev-Moderation-Bot

Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder.

In 2 lists

jev-suite

Four decision-quality applications where Jev answers structured questions and deterministic code keeps final authority.

In 2 lists

call-coach-ai

Call-coaching application where Jev evaluates conversation context to surface structured coaching decisions.

jev-guard

Exchange deposit and withdrawal risk-triage gateway where Jev triages and deterministic code adjudicates.

In 2 lists

jev-recall

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.

jev-seo

Live SEO audit for any website from one homepage URL, judged by Jev. PDF, XLSX and Markdown reports.

In 2 lists

jev-reviewer

Systematic-review extraction app where Jev answers structured review forms and points reviewers to quoted source lines.

sharp

Filter your X.com feed with Jev or any LLM.

jev-trade

Live Jev trader on Hyperliquid.

In 2 lists

jevmail

Read-only Gmail triage app where Jev assigns each message a tray, urgency score, and human-authorship judgment.

pi-codemode

The jev.ask runtime global lets sandboxed TypeScript programs request calibrated Jev Noul, Choice, and Score answers.

commit-miner

Classify Git commit diffs and messages with Jev. Bug fixes, security fixes/CWEs, and change types.

doc-router

Document OCR router where Jev judges page by page whether the existing text layer is usable or OCR is required.

SmartMoney-Cub

Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no advice.

In 3 lists

blink

Codebase search powered by Jev from @typesafe-ai.

refgarden

A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.

rikkahub-sillytavern-android

RikkaHub Plus Huadeng Edition - Android AI chat client & SillyTavern Android tavern compatibility. Connected to API instant chat: prefix cache to save token, semantic memory RAG, Jev intelligent decision-making, QuickJS plug-in, voice call, WeChat QQ Bot; character card, world book Lorebook,…

jevclip

Video editing pipeline where Jev judges transcript segments to select highlights and remove filler.

JEV Paper Radar

Scheduled research-paper radar that asks Jev whether each paper matches configured interests and exclusions, then publishes ranked web and feed output.

In 2 lists

Cheshi

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.

pi-dcp

The experimental Jev path scores completed context payloads so users can review and approve what remains available to the agent.

hermes-nerve

Nerve is a supervisory nervous system for Hermes agents, adding typed System One decisions, ranking, verification, token-aware oversight, and an opt-in tool gate powered by TypeSafe Jev or Open Source Laya.

jev-yaba-wechat

Don’t know how to answer the message on WeChat? macOS floating chat assistant: identifies message intent and communication risks, GPT generates a variety of words, Jev evaluates candidates, and fills in WeChat with one click. I will help you think about it and send it to you to order..

jev-gmail-ai-spam-filter-and-labeling

Self-hosted AI email classifier for Gmail powered by Jev. Create custom labels, organize your inbox, and filter spam with confidence and cost controls.

transcript-lens

YouTube transkriptlerini anlamına göre keşfedin. Türkçe arayüz, Jev analizi, altyazı dışa aktarma ve Vercel kurulum rehberi.

yanwai

Android WeChat module that uses Jev to show emotion probabilities, implied meaning, and communication suggestions.

hafiza-os

Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı Mem0/Jev.

jev-mail-classifier

Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven.

Jev-Trades

Trading bot with the all new TypeSafe AI's first system one model named as Jev.

wechat-jev-assistant

Windows WeChat assistant that reads and redacts conversations before Jev classifies them.

ad-radar

Browser extension that uses Jev to identify and fold ads and selected topics on social platforms.

jevthoven

AI Music (MIDI) generator powered by Jev.

Byeori

Scientific knowledge system using Jev to nominate reusable knowledge issues for human review.

Jev RAG

Local SQLite BM25 retrieval pipeline where Jev answers batched Noul evidence-relevance questions to rerank passages before a separate model generates an answer; selected text is sent to hosted providers.

In 2 lists

jevocks

Everyday Stocks Status with Jev.

In 2 lists

jevlogs

Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.

jsort

Sorts text along a plain-English criterion using pairwise Jev Noul judgments and a locally fitted Bradley–Terry scale, with uncertainty and reliability reporting.

In 2 lists

Jev LinkedIn Saved Classifier

Reads LinkedIn saved posts from Chrome and uses Jev Choice to assign user-defined categories, exporting a searchable board, CSV, and JSON.

jev-rerank

Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.

secondlayer

Self-hosted Stacks data service whose Slack gate and fault-triage paths use Jev decisions.

In 3 lists

semdecide

Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.

In 2 lists

jev-cli (tumf)

Small dependency-free CLI for TypeSafe Jev.

In 2 lists

ai-elo-ranker

High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking.

JevSpan

Zero-shot named entity recognition using Jev Choice to nominate, verify, and refine candidate text spans, retaining offsets, probabilities, and decision traces.

In 2 lists

jev-grug

Helping JEV speak <3.

typesafe-cli (y0usaf)

Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose.

jev-research-pipeline

Pilot research monitor where Jev uses typed Noul and Score judgments to keep, review, or drop new papers and repositories against open research questions, while another model writes daily notes.

In 2 lists

jevsql

SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.

smart-switch

Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model.

every

Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.

jev-resume-disqualifier

Recruiting-screening demo that combines deterministic date and eligibility checks with Jev judgments to route resumes for review or rejection.

In 2 lists

jselect

Selects source-linked evidence within a token budget using Jev relevance judgments plus local diversity-aware selection.

In 2 lists

jev-document-classification

JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.

typesafe-jev

Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.

In 2 lists

citation-verifier

Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.

In 2 lists

jev-tree

Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap.

jevibe-check

A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API.

jev.nvim

Neovim plugin that has Jev score each function against a plain-language question and ranks results in quickfix.

In 2 lists

btc-jev-signal

Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data.

jlink

Record-linkage toolkit for Python, CLI, Stata, and R: Jev judges record pairs against a plain-English matching rule and returns auditable probabilities.

In 2 lists

jevpdf

PDF reader that uses Jev Noul judgments to highlight lines matching a natural-language question.

In 2 lists

DeciFlow

Batch and streaming log-analysis application where Jev or Laya answers configurable typed questions about events, with validated numeric results and optional Python actions.

JevTicktRouter

A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.

Jackalope

Desktop GUI for agentic coding that routes tasks across local agents and accounts, with Jev picking the best agent per task, running basic code-review checks, and supplying context.

jev-cli

CLI for TypeSafe AI's Jev evaluation model — typed questions in, structured JSON answers out.

pagegrade

Browser extension that grades page sections for clarity, writing quality, and on-page SEO with Jev.

In 2 lists

commentcop

Put your code comments on trial. Powered by Jev.

qualm

Typed decisions from a System One model. An uncertain answer is a different type from a confident one — and the compiler makes you handle it.

jev-audio-beeper

Low-latency audio censorship POC using Jev typed decisions and ffmpeg.

jev-score

Local-first document evaluation workspaces powered by Jev

metis

Metis: automatic GitHub issue triage powered by TypeSafe AI Jev. A reusable GitHub Action.

tiab-review-plugin

Chrome extension for systematic-review screening where Jev returns per-criterion match probabilities and an inclusion judgment.

triagedy

Security-alert triage filter where Jev or a local model returns typed dispositions while policy routing remains in code.

Jev Subtitle Translator

SRT translation app whose Jev Noul checks flag subtitle pairs that need human review without rewriting them.

In 2 lists

jevegis

Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.

jev-resume-analyzer

CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI.

transcript-scorecard

ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepo.

emoji-jev

Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.

s1s

System One Search: navigate and trace code with TypeSafe judgments and repository evidence.

JevSysUno

TypeScript application exploring TypeSafe Jev as a System One decision layer.

jev (haibt163)

TypeScript application built around TypeSafe Jev decisions.

pkg-gate

Pre-install security gate for npm lifecycle scripts using TypeSafe System One.

typesafe-comment

Small Python package that uses typesafe.ai to evaluate code comments on certain heuristics.

mimicry

Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop.

newsscore

Async library and CLI that turns a week of news into one sentiment score per ticker, using Jev by default.

draftpulse

Experimental: live X draft viral scorer powered by TypeSafe Jev.

jev-trader (renatosousa)

Trading application that uses Jev for market decisions.

typesafe-triage-guard

Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate.

scam-shield

Scam text message filter powered by TypeSafe's Jev model.

trading-bot-jev

Binance testnet trading bot that uses Jev to judge news.

JevSlop

Scores public note.com articles across eight Jev dimensions and produces an inspectable AI-slop score.

In 2 lists

github-star-organizer-jev

Uses Jev to classify and organize GitHub stars.

jev-the-janitor

A janitor for markdown vaults powered by TypeSafe Jev: Jev votes on each note, your code files it, you review the low-confidence pile.

discoprint

Classify an artist's discography by theme, mood, and lyrical complexity with Jev (TypeSafe AI), and view it as a colorful terminal dashboard

1 Million Emojis

Shared emoji canvas where Jev chooses which emoji and square to paint next and judges whether to finish the visitor's stroke.

jev-seo

Website audit tool where Jev judges page intent, content quality, and citability using typed questions; source is public but UNLICENSED, with all rights reserved.

5 projects added on 2026-11-12 >Games & simulations (73)

typesafe-mario

A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.

In 2 lists

quackd

One offboard CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM) and a decision LLM for cheaper and faster steps (Jev, Laya, and Kev). Supports Microduck, Open Duck Mini, LeRobot,…

embodied-jev

EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs

In 2 lists

beebots

Paper-trading race where Jev chooses each bee's valid market move and conviction while deterministic code enforces risk limits and execution.

laya-vs-jev

Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording.

Jev Plays Pokémon Red

Pokémon Red harness where Jev chooses every menu, navigation, team, and battle action from legal options exposed by the emulator.

jev-drone

Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz.

In 2 lists

detroit-ai-player

Jev uses one typed Choice question to select each narrative action from the options available at a Detroit: Become Human decision node.

In 2 lists

jev-libero

LIBERO robot-control environment where Jev chooses fine-grained actions using task state and physics previews.

jev-robot-control

MuJoCo xArm7 study where Jev chooses movement directions and gripper actions from physical feedback.

RoboJEV

Two-stage JEV control of a Franka Panda in MuJoCo.

In 2 lists

Jev-as-Policy

The highly anticipated open-source repository for JEV as Policy enables one-click setup of the simulation environment. Evaluations of Astra + JEV on benchmarks such as RoboTwin will also be released soon.

Jev_Star

StarCraft agent experiment using Jev for fast tactical decisions.

In 2 lists

clash-jev

A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state.

PlayJev

🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.

In 2 lists

laya-vs-jev-arena

Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.

In 2 lists

robodiag-harness

AI diagnostic agent for ROS 2 robots — evidence-based, tool-calling, safety-gated.

typesafe-snake

Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.

jev-reflex-autonomy-lab

Drone-swarm simulation using Jev for reflex decisions and collision avoidance.

In 2 lists

tsai-sc

TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.

In 2 lists

mario-jev

Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.

JevTown

AI-town simulation where Jev selects character actions and responses.

Jev Driving Lab

Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out.

In 2 lists

heist-one

Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.

OneVOneJev

1v1 Jev quickscope arena — Three.js + TypeSafe System One.

Jev Driver

Browser driving game that captions dropped road images locally, then uses Jev Choice answers to drive the car while code owns physics and timing.

In 2 lists

jev-doom-agent

A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.

jev-plays-pokemon

Pokémon Red agent that turns structured game state into Jev decisions and validated moves.

In 2 lists

jev-askable-arm

Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.

jev-royal

Jev-powered game and decision experiment.

hundred

100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.

jev-plays-pokemon-red

Pokemon Red on PyBoy where Jev chooses legal actions only at branches and each battle turn logs a Brier-scored faint prediction.

In 2 lists

rubikjev

Challenge the Jev's intelligence in Rubik Cube puzzles.

robo-harness

SO-101 robot-arm workbench where Jev selects bounded joint actions under a spend budget.

In 2 lists

jev2048

Let Jev (TypeSafeAI) solve 2048.

tsai-civ2

TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.

jev-gomoku (XieChengYuan)

弈瞬:双 Jev 五子棋九宫格输入实验台,逐手查看模型决策,支持真实对局回放与实时对战。

last-exit

A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.

jev-pong

Pong benchmark where every ball step is a model decision, comparing Jev with LLMs through Vercel AI Gateway.

In 2 lists

river-run-typesafe

River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot.

river-oaks

NPCs of River Oaks Houston, Texas using Jev to power NPCs.

typesafe-minecraft-demo

A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard.

jev.mods

Minecraft mod where Jev tries to finish the game from scratch without a scripted route.

jev-snake

An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.

jev-play-ping-pong

Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.

jev-t-rex-runner

Chrome dino game played by Typesafe AI Jev model.

roverlab

A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.

jev-bfs

Wikipedia link races with direct Jev ranking and a live terminal display.

In 2 lists

typesafe-jev-drone-demo

Three.js drone simulator with a Python backend and live Jev navigation decisions.

In 2 lists

beatjev

Browser game: try to beat Jev at spotting a spam message.

jev-tetris

A visual TypeSafe demo where Jev chooses verified Tetris placements.

typesafe-3d-chess

3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.

f1

JEV Prix simulation with five AI drivers, procedural circuits, BYOK Jev, and saved replays.

jev-atari-lab

Replayable Atari experiments using Jev structured decisions and value questions.

jev-gomoku

MoonBit client for Jev plus a Jev-vs-Jev gomoku match, with timing logs.

naimono-lab

Family word game for playing with imaginary words, powered by Jev.

beat-jev

Penalty shootout powered by Render Workflows, TypeSafe Jev, and Render Postgres.

pdoom-protocol

USER + JEV: P(DOOM) PROTOCOL — co-op platform shooter where TypeSafe Jev plays alongside you.

ps2-ai-agent

Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One.

casse-brique-typesafe

A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code.

cyber-breach-jev

Cyber-Breach: The Jev Protocol - A tactical cyberpunk arena combat game powered by TypeSafe AI Jev System One decision model.

JevArena (rolki-png)

Two Jev agents duel at Snake through Vercel AI Gateway.

pong-jev

TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model.

jev-games

Visual Jev lab for multiple games and emulator platforms.

snake-jev

Snake controlled by parallel Jev assessments, with one API call per game tick.

terrarium

A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world.

typesafe-chess

Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision.

shady-town

Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev.

siege

SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.

Agent-JEV-Tetris

Using the new model JEV to play the game tetris.

jev-plays-pokemon

Pokemon-playing experiment where Jev chooses actions.

Jev RPS

Commit-reveal rock-paper-scissors game where Jev scores player behavior, predicts the next move, and chooses its own move before the player acts.

The Chess of Life × Jev

Editable Game of Life ruleset bench where Jev evaluates legal cells and chooses each intervention while code advances and verifies the board.

In 2 lists

5 projects added on 2026-11-12 >Demos & playgrounds (67)

jev-leftpad

Left-pad strings with TypeSafe AI's Jev. For reasons.

jev-paint

Use Jev to make art!.

In 2 lists

jeview

An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.

In 2 lists

jev-explained

Jev Explained.

Jev-Quantum

Random Jev-compatible baseline that emits Noul, Choice, and Score probabilities for mocks, lower-bound comparisons, and router evaluation.

is-jeven

Is it even? Ask Jev.

jev-design-test

Jev shadcn-block generator.

killmyidea

Describe your startup idea. Jev decides: kill it, fix it or ship it.

Pi-Jev-Guide

Jev checks configurable Pi agent rules for risk, output redaction, repeated failures, and missing verification at selected workflow stages.

typesafe-playground

Community playground with editable Jev use cases, games, dilemmas, challenges, and A/B comparisons.

Jev

Six live, side-by-side demos of TypeSafe's Jev — a "System One" model that returns typed, probabilistic decisions (70–500 ms, $0.042 per 1M input tokens, output free) instead of generated text.

jev-studio

if you're experimenting with jev it will be easier from here.

In 2 lists

typesafe-ai-playground (BunsDev)

Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.

pix-golpe

Split-screen demo where Jev detects Pix-payment scams and traces the fraud chain.

jevbot

Discord bot demo that lets users converse with Jev-backed typed behavior.

jev-me

A grill-me style interrogation of your idea, with Jev doing the grilling.

Awesome Jev Use Cases (whyashthakker)

Fifty runnable visual demos comparing Jev typed decisions with an OpenAI structured-output baseline, with fixtures and explicit methodology limits.

away-together-starter

Jev-inspired travel decision tutorial with classifier training; the browser demo uses recorded model outputs.

Instinct

Instinct: describe a case in free text and Jev picks the UI from a fixed catalog without generating a line of code or copy.

tryjev

Browser playground for editable Jev Choice, Score, and Noul questions through TypeSafe, OpenRouter, or Vercel AI Gateway providers.

Trio-Spark demos

Open clients, evaluation tools, and runnable text/image/video decision demos for the hosted System One-compatible Trio-Spark service; model weights and training code are closed.

In 2 lists

jev-autopilot

This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.

typesafe-ai-playground

Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.

clarity-judge

Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.

jev-system-one

A polished OpenAI + TypeSafe Jev terminal interface for answers with transparent decision reports.

Should AI Kill Us All?

Live verdict page: feeds Jev the day’s Florida Man, odd-news, politics and world headlines and asks all three primitives whether AI should kill us all, refreshed every ten minutes.

typesafe-arena

A playground for TypeSafeAI's Jev Model.

jev-playground (Little-Planet-Labs)

A small Next.js app for experimenting with TypeSafe AI's Jev model (System One).

typesafe-ai-playground (markjaquith)

A playground for experiments around Jev, TypeSafe's System One model.

toolgate

Agent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev.

guard-jev

Comment-moderation playground: paste a comment, Jev decides what to do with it.

got-jev

Jev (TypeSafe AI) PoC through Game of Thrones.

gpt-vs-jev

Compare GPT generated language with JEV structured Noul decisions on the same input.

harden-jev-decides

JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.

Jev by Example

Ten runnable agent-decision examples covering memory, retries, context selection, and handoffs, with offline fixtures and optional live Jev calls.

In 2 lists

human-compiler

A compiler for human language. Paste text, get diagnostics. Measured by TypeSafe Jev.

jev-demos

Demos to test the effectiveness of TypeSafe's "Jev" System One Model.

jev-ad-preflight

Typesafe/Jev public X demo.

jev-should-i-apply

Typesafe/Jev public X demo.

jev-user-jury

Typesafe/Jev public X demo.

extremely-specific-council

Twelve members. Zero qualifications. A playful TypeSafe AI council with animated votes, inspectable decisions, and shareable verdicts.

jev-bun1

TypeSafe の Jev を TypeScript SDK で使ってみる最初の 1 歩.

jev-paper-judge

Feedback on your paper in seconds.

Probably

Probably: live BTC, ETH, and XRP prices with a shared TypeSafe buy-or-wait demonstration. No trades placed.

tiny-jev

Small browser experiment for TypeSafe Jev decisions.

forma-system1-experiment

Design experiment where Jev picks a design in about a second and Luna writes only the words.

jev-dev

同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ(affectus + Vercel AI Gateway).

Jev Gamecast

Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data.

cartshield

CartShield — SMB checkout fraud disposition via TypeSafe Jev.

harnessjudge

Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev.

hiresignal

HireSignal — resume first-pass fit+interview via TypeSafe Jev.

jevplay

TypeSafe Jev playground — custom Choice/Score/Noul builder with live distributions.

lanebreak

LaneBreak — support ticket priority+routing via TypeSafe Jev.

mcpmatch

Match user goals to MCP catalog (two-stage) via TypeSafe Jev.

pulselane

PulseLane — clinic triage decisions via TypeSafe Jev.

spendbrake

Agent budget brake — continue / downgrade_model / stop via TypeSafe Jev.

swarmrouter

Route tasks to research/code/browser/support/writer agents via TypeSafe Jev.

trustgate

TrustGate — indie media T&S gate via TypeSafe Jev.

typesafe-jev-examples

Worked ticket-triage and reranking examples for Jev, runnable through OpenRouter with sample data and a Makefile.

In 2 lists

Search-Function-Test

A test project based on Jev AI, the goal is to build a search function for a blog/article website that has 100s of articles to search from, So the user can actually use the search as chat to question anything and find related answers/articles.

jev-board-lab

Interactive explorer and Jev question workspace for Jev Board datasets.

Job Risk Analyzer

Job Risk Analyzer: CLI and REST API that uses Jev to score an occupation's exposure to AI-driven layoffs and its resilience.

typesafe-image-diffusion

Diffusion-style pixel art out of a classifier: 256 parallel per-pixel Jev questions plus refinement passes.

jev-playground (wustep)

Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI.

jev-calculator

A probabilistic calculator where Jev emits one answer character at a time from 13 fixed choices and the UI displays every step’s probability distribution.

In 2 lists

Magic Jev Ball (mikecann)

3D Magic 8 Ball on Convex where Jev scores twenty classic answers and the app displays their probabilities.

In 2 lists

Jev Hub

Bilingual Jev tracker and interactive playground whose templates submit typed Choice, Score, and Noul questions through a Cloudflare proxy and display structured results. No repository-level license file was found during review.

5 projects added on 2026-11-12 >Benchmarks & research (119)

NanoJev

Open 0.6B Jev replica with parallel decisions, complete probability distributions, training pipeline, weights, dataset, and live demos.

In 2 lists

jevlike

Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.

In 2 lists

SREGym

When enabled for Codex runs, Jev reviews diagnostic tests and incident-resolution submissions from the supplied evidence.

jev-align

Build calibrated AI Functions from human feedback using Jev and GEPA.

In 2 lists

tasksource

Tasksource recasts hundreds of classification datasets into Jev-compatible typed questions, answers, and procedural training examples.

jev-visual

An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.

Convex Decision Evals

Benchmark comparing Jev Choice answers with LLMs on four-option questions about Convex.

decider

One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.

In 2 lists

jev-arena

Jev model introduction and actual measurement: use Choice / Score / Noul to convert natural language into typed judgments and probabilities for classification, scoring and routing; supports comparison of comment marking, speed and results with models such as DeepSeek, including CSV/Excel import,…

jev-eval-agent

Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.

reflex

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

WindTunnel

WebMCP benchmark comparing browser-agent interfaces, with Jev included as one of the evaluated configurations.

In 2 lists

jevbench

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

open-jev (daseinlabs)

One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.

In 2 lists

jev-dataops

An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.

jevmlx

Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.

typesafe-ai-benchmark

This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.

jev-calibrate

Calibrate Jev questions against your own labels: tune criteria on labelled examples, confirm on a held-out set, get a verdict per question. Unofficial.

Verdict-open-jev

Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground.

mini-jev

Mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.

In 2 lists

jev-capability-atlas

Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文为主的双语 repo。.

LitJev

A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.

In 2 lists

jev-on-a-laptop

Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.

jev-column-race

Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper.

open-alternative-jev

Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks.

In 2 lists

openjev (zhihz)

Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.

In 2 lists

jeval

Measures what your Jev classifier's confidence is really worth, and sets the human hand-off line from what a mistake costs.

VerdictAD

Few-shot industrial anomaly detection using Clef-Flash typed visual decisions to refine image anomaly scores and regional anomaly maps.

In 2 lists

system-one

Batched single-token choice inference for open language models, compatible with TypeSafe.

jev-rag-benchmark

Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG.

system-one-open

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal).

jevbetter

A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.

In 2 lists

TypeAR

Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev.

jev-benchmarks

Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

jev-as-a-judge

Using Jev as an evaluator.

Jev_apps

看看 Jev 能做什么:用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.

dejevu

Browser-agent comparison that benchmarks a one-look open-model policy against the Jev demo.

jevify

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

In 2 lists

openvons

Openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド.

jev_stock

An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.

In 2 lists

jevcal

Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.

In 2 lists

jevfire

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

Eikos Arena

Reproducible paper-trading arena that gives Eikos and Jev identical market states and typed questions, then compares equity and probability forecasts.

typesafe-local

Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.

LegalForecastBench

LegalForecast-MTD benchmark alpha and official evaluation workflows.

In 2 lists

jev-korean-benchmark

Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.

jev-lm

A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval.

Decision Index

Reproduction kit for a 38-benchmark typed-decision index with frozen public-source suites, resumable runners, official scorers, and Jev-compatible HTTP engines.

daf-jev

Daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill.

jev-little-airways

A show-and-tell capability study for Jev, TypeSafe's System One decision model.

jev-search-rerank-eval

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

jev-ood-calibration

Reproducible evaluation of Jev calibration on synthetic support tickets and public classification benchmarks.

In 2 lists

jev-chat

A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.

jev-curate

High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).

In 2 lists

jev-harness

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.

In 2 lists

openjev (DECRUX9812)

Open, local reimplementation of a Jev-style decision layer for job postings.

jev-behavior-study

Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.

jev-dspy-lab

Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows

system-one-gemma

Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.

jev-rerank-bench

Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.

jevgpt

A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively).

calibre

Calibration and confidence-based routing measured on Banking77: 80.2% accuracy at $0.103 per 500 decisions.

jev-for-engineers

Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.

jev-sec-bench

Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.

jev-research-eval

Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.

In 2 lists

trade-jev

Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data.

mcts-agent

Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini.

jev-gate

Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

jev-exploration

Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code.

jev-benchmark

Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs.

jev-does-not-play-dice

Reproducible experiments on Jev probability calibration, uncertainty, and forecast preservation.

jev-phishing-bench

Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.

paper-package

Reproducible Jev research manuscript, evidence, and paper package.

decisionbridge

A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.

RISC-jeV

I tortured Jev into being a RISC-V CPU.

jev-freeform

An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice.

typed-decisions

Jev-shaped typed-decision models with measured latency, accuracy, calibration, and training cost.

jev-synergy-screening

Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels.

qwen-rlcd

Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.

In 2 lists

kyotsu-ai-bench

AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).

jev-agent-failure-benchmark

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

jev-routing-experiment

Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena.

openjev-experiments

Experiments with openjev, an open Jev-style option-logit runner, on local models.

padflow-jev-evals

Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.

stuntdouble

Drop-in /v1/systemone shadow proxy that forwards requests to Jev and local decision models, recording agreement, calibration, latency, cost, and policy-level differences.

Typesafe_chess_eval

An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.

jev-spam-eval

Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.

In 2 lists

jev-shadcn-lint-eval

A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.

system-one-adapter-rust

Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations).

jev-deferred-crispification

Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).

jev-alpha-bench

Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall.

jev-headline-bench

Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.

jev-report

发明 RLHF 的人,这次做了个不会说话的模型:Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表.

jev-playground (hegargarcia)

Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.

In 2 lists

jev-finance-benchmark

Typesafe.ai model jev finance benchmark.

jev-anotacao-sentencas

Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo.

jev-vs-luna

Reproducible review-classification comparison measuring Jev and Luna accuracy, latency, and cost.

jev-lab

TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.

misereru-slide-jev

Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.

shade-arena-jev-monitor

Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.

PocketJev

On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits.

jev-jp-address

Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証.

jev-trace-classifier

Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next.

jev-secret-detection

Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets.

FinancialPredictionJev

Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good).

typesafe-oracles

Evaluating TypeSafe's System One primitives (Choice/Score/Noul) — where a typed oracle beats an LLM call.

jev-pick-and-place-study

A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.

thaiexam-jev-charts

Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.

jev-calibration-audit

Independent API-only calibration audit of TypeSafe AI's Jev decision model

labs

Research workspace containing reproducible TypeSafe Jev evaluation and safety-judgment experiments.

jev-certify

Research toolkit applying conformal risk control and prediction-powered inference to certify Jev routing thresholds.

jevals-data

Independent benchmark data for TypeSafe's Jev (System One model) vs LLMs: accuracy, calibration, cost. Boards + per-decision logs, CC-BY-4.0

jev-eval

TypeSafe's Jev vs gpt-5.4-mini and gpt-5.6-luna on four public classification sets: cases, per-item answers, scoring, charts

jev-evaluation

Adversarial Jev evaluation suite with preregistered predictions, request logs, and reproducible experiment artifacts.

jev-orderby-bench

Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.

In 2 lists

Jev no ENEM

Reproducible evaluation of Jev Choice decisions on 182 valid ENEM 2025 questions, with raw results, accuracy, calibration, and latency analysis.

jev-skillbench

Benchmark of Jev as a malicious agent-skill detector on MalSkillBench with verify-and-escalate evaluation.

Decision Models as Guardrails

Reproducible guardrail benchmark that compares Jev and other decision systems using typed Noul checks and a fixed 0.5 blocking threshold, with public scoring contracts and author-run results.

In 2 lists

jev-multilingual-benchmark

Reproducible multilingual moderation benchmark comparing Jev typed policy decisions with chat and guard models on names and comments.

In 2 lists

5 projects added on 2026-11-12 >Repository-level code references

agentgateway Jev guardrail example

—

In 5 listsDetails

TrainLCD Jev rerank

—

Milvus Search with Jev

Python

In 2 lists

What Jev is

Choice

Select one option from a known set

Score

Place something on an ordered rubric

Noul

Estimate whether a statement is true

Official resources

TypeSafe AI

Product overview and access.

Documentation

Official concepts, API, SDK, patterns, and cookbook pages.

API reference

Current request and response contract.

Models

Current aliases, versions, pricing, and limits.

Workflow evaluations

TypeSafe's published workflow methodology and results.

LINUX DO

新的理想型社区,一群热爱技术、乐于分享的开发者聚集地。

In 8 listsLink may be dead
See category
99

Awesome DeepSeek Harness (DSH) Plugin

awesome-dsh-plugin/awesome-dsh-plugin

A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表

Fresh★ 25k1416 entriesPushed today
98

Awesome OpenClaw Skills

VoltAgent/awesome-openclaw-skills

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Fresh★ 54k843 entriesPushed 16 days ago
96

Awesome Prompts

ai-boost/awesome-prompts

Curated prompts, frameworks and papers for LLMs and agents, with an engineering bias. Prompt engineering, context engineering, agent harnesses, red teaming.

Fresh★ 9.3k365 entriesPushed today
96

Awesome Open Source Alternatives

piotrkulpinski/open-source-alternatives

Curated list of open source alternatives to proprietary software.

Fresh★ 6.9k860 entriesPushed today
95

Awesome README

matiassingers/awesome-readme

A curated list of awesome READMEs

Fresh★ 22k144 entriesPushed 5 days ago
94

Awesome Persona Distill Skills

xixu-me/awesome-persona-distill-skills

Curated list of Agent Skills centered on people, relationships, commemorative scenes, and methodological perspectives

Fresh★ 4.7k72 entriesPushed today