Skip to content

Entry

mu

Appears in 6 awesome lists

Open-source coding agent harness built on pi that moves routine loop decisions into a "judgment kernel": a small, fast judge model answers bounded questions at 40 decision points, covering which tool output enters the context, command risk and permission approvals, prompt injection in web pages…

Open github.comqybaihe/mu

Found in these lists

Awesome AI Security Tools

Section: Runtime Protection & Enforcement · 🟢 — CLI and desktop coding agent with judge-assisted tool permissions and prompt-injection screening of selected web, search and MCP results. Caveat: guards cover mu's own calls, not a standalone security boundary. Full access bypasses ordinary permission prompts; write-sandbox exits retain…;…

FreshScore 91

Awesome Harness Engineering

Section: Demo Harnesses · Open-source coding agent harness built on pi that moves routine loop decisions into a "judgment kernel": a small, fast judge model answers bounded questions at 40 decision points, covering which tool output enters the context, command risk and permission approvals, prompt injection in web pages…

FreshScore 93

awesome-jev

Section: Agent Decisions · Coding agents: a pi-based coding agent and desktop app that asks Jev Noul, Choice and Score questions at 40 decision points inside its loop, such as which chunks of a long tool output enter the context, whether a rule-flagged command was actually asked for, whether a fetched page or MCP result…

FreshScore 85

Awesome Mac

Section: AI Tools · Open-source coding agent with a CLI and a desktop app, in which a small judge model makes routine calls such as what enters the context and whether a flagged command was asked for.

FreshScore 98

Awesome Jev

Section: Agent tooling (239) · Coding-agent workspace where Jev or a local Laya judge gates bounded decisions such as context retention, approvals, routing, drift, and inter-agent sharing.

FreshScore 85

Awesome Harness Engineering

Section: Coding-Agent Harnesses · MIT-licensed coding agent built on pi that hands routine harness decisions (tool-output admission, stale-context forgetting, command risk, prompt-injection screening, completion checks) to a small judge model as bounded questions, with per-decision active/shadow/off modes and a ledger of every…

FreshScore 93

Jev Social

Read-only Instagram, TikTok and LinkedIn research app where Jev selects bounded operations, the local socai CLI runs them in the user's Chrome, and captured evidence becomes cited reports; TikTok media is optional and explicit-request only.

In 12 listsDetails

browser-use

Open-source browser agent (Python and TypeScript) whose loop injects serialized DOM state each step, exposes browser actions as registered tools, and runs the same code against a local Chrome or a cloud browser. It has grown from a minimal reference into a full framework (~70k lines of Python…

In 11 listsDetails

Bifrost

🟢🟠 — Apache-licensed AI and MCP gateway with multi-provider routing, virtual-key access controls, budgets, rate limits, MCP aggregation, OAuth, automatic fallbacks, and load balancing. (Maxim) — note: model-provider credentials and proxied request/response data are sensitive; restrict and…;…

In 11 listsDetails

Codex CLI

OpenAI's official autonomous coding agent CLI — the open-source reference implementation of the Codex harness with sandboxed tool execution, multi-file editing, and a streaming agent loop. Worth studying because it is the most widely adopted terminal-native coding agent harness and exposes the…

In 10 listsDetails

Future AGI

🟢🟠 — Self-hostable evaluation and tracing platform with an OpenAI-compatible Go gateway for inline model-traffic checks, MCP/tool permissions and optional external guardrail services. (Future AGI) Caveat: the core is Apache-2.0; enterprise components have a separate commercial license. Gateway…;…

In 9 listsDetails

AutoGPT

AutoGPT provides accessible AI tools for building and using AI agents, offering a comprehensive framework including Forge for agent creation, agbenchmark for performance evaluation, a leaderboard for competition, a user-friendly UI, and CLI for seamless integration and management github | github…

In 10 listsDetails

Pipecat

The open-source Python framework for real-time voice & multimodal conversational agents — every pipeline is an agent: multi-agent handoff, parallel fan-out, and sidecar workers over a shared bus, local or distributed; pluggable STT/LLM/TTS and transports (WebSocket/WebRTC), built-in Pipecat Flows…

In 8 listsDetails

deepagents

LangChain's batteries-included agent harness (released April 2026) with built-in planning, filesystem tools, shell access, sub-agents, and auto-summarization. The clearest open-source demonstration of how a general-purpose coding agent harness can be made ready-to-run out of the box while…

In 8 listsDetails