Skip to content
80

Best Of Agent Harnesses

🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.

1.5k stars104 forks51 entriesLast push Nov 15, 2026 (today)License CC-BY-SA-4.0

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

What is an agent harness?

Simon Willison's definition

of the agent itself is the cleanest: "an LLM agent runs tools in a loop to achieve a goal." The harness is everything around that loop: which tools exist, what needs approval, what the model sees each turn, what survives a crash. Andrej Karpathy named the architecture back in 2023: the model is…

Graveyard

everything-claude-code

suspected star manipulation — ~228k stars / ~35k forks on a repo created 2026-01 with no matching install base, dependents, or discussion; fork-to-star ratio and growth curve are inconsistent with organic adoption

In 7 listsDetails

Daytona

archived upstream — kept for citation

In 3 lists

DeepSeek-Reasonix

archived upstream — kept for citation

In 4 listsDetails

spring-ai-tool-search-tool

archived upstream — kept for citation

coderClaw

archived upstream — kept for citation

On the radar

agenticSeek

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

In 3 lists

openfang

Open-source Agent Operating System

In 2 lists

evolver

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

In 2 lists

ZCode

Z.ai's coding agent harness. Powerful, intelligent, extensible.

In 2 lists

openevolve

Open-source implementation of AlphaEvolve

In 4 listsDetails

reef

Infrastructure for continually self-improving agents: records live traffic and feedback, then ships a scored update to model weights or the harness.

In 4 listsDetails

intentkit

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

In 2 lists

agentscope-java

Build distributed, production-grade, long-running agents.

In 3 lists

vibesdk

An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack

In 3 lists

eko

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

antigravity-sdk-python

A Python library for building AI agents that leverage the full power of Google Antigravity.

fast-agent

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

MIRIX

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data…

OrcaReplay

Record, replay, fork, and debug any agent run with any model; time travel for AI agents.

In 14 listsDetails

placecall

Skill and plugins that give Claude Code, Codex, Cursor, and Gemini CLI a hosted MCP server for phone calls to US businesses.

In 5 listsDetails

5dive

Run a company of agents on a server you own: each agent is an official CLI (Claude Code, Codex, Pi) as a systemd service, sharing one task queue.

In 6 listsDetails

llm-wiki-cli

Proactive memory CLI for AI agents: recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

In 6 listsDetails

red-team-blue-team-agent-fabric

AI agent security harness for adversarial testing: 600+ executable tests across MCP, A2A, x402/L402, and decision governance.

mcp-memory-server

MCP memory server backed by a hosted engine: recall that re-ranks on helped or misled feedback, plus shared rooms for multi-agent work.

In 5 listsDetails

model-citizen

Control plane for Claude Code and Codex: one checkout of rules, skills, and roles projected into each runtime, with hook guardrails and cost records.

Autobot

AGENTS.md operating contract, on-disk memory, and an independent completion validator for ChatGPT and Codex local projects on a Mac.

loopgate_harness

Run any CLI agent in a loop against specs: fresh context each iteration, the repo as durable memory, lint/types/tests/security enforced by git hooks so bad c…

GoodMemory

Local-first, auditable memory layer for AI apps and coding agents (Codex, Claude Code, MCP, HTTP).

In 5 listsDetails

teamcopilot

Deploy AI agents for your team to automate business workflows and coding.

nausicaa-harness

Treats an agent run as a dynamic topology of lanes instead of one linear loop; the model decides when to observe or fan out.

atlarix-releases

Atlarix: proprietary desktop agent workstation; hunk-by-hunk diff approval, per-OS sandboxed shell, lexical retrieval, any model. Release repo only.

dsh-mcp-lens

MCP tool search for large catalogs: 1,000 tools behind 2 schemas, exact-schema calls, allow/deny controls.

In 4 lists

house-party-protocol

Evidence and approval contracts around Claude Code and Codex CLI: done is a recorded exit code, and a verdict from the builder's own lane is refused.

workkit

Claude Code plugin that runs work through GitHub Issues: an accepted spec gates each build, a blind verifier reviews, and hooks enforce the test gate.

laravel-ai-verify

Verification gate for coding agents on Laravel 12/13: runs only the checks a diff needs, fails weakened tests, and blocks Claude Code from stopping early.

yylo-benchmark

Longitudinal benchmark for coding-agent runs: sandboxed fresh-repo attempts, deterministic and blinded LLM judging, hash-bound evidence.

In 4 listsDetails

jet-browser

Portable WPE WebKit browser runtime for agents: one isolated process driven by ordered JSONL or MCP commands, with native input and screenshots.

In 3 lists

Giovanni

Claude Code plugin for a daily digest loop: parallel source pulls by subagents, drift checks against a constitution in git, and lint limits on memory.

agentlink

Coding-agent harness inside VS Code: editor code intelligence as tools, reviewable diffs, an approval policy, sandboxed commands, resumable sessions.

wippaAGENT

Install-once OpenCode config: one orchestrator with edit and shell denied delegates to 12 specialist subagents behind audit and review gates.

mcp-guardian

MCP proxy for tool scoping and context compression: progressive discovery with 3 meta-tools.

In 2 lists

minimal-harness

Dependency-free acceptance and handoff kernel for coding agents: runs configured checks and fails closed when Git or contract evidence goes stale.

Awesome

Awesome lists on many topics

In 23 listsDetails

OpenAI – Harness engineering

Environment design, intent, feedback loops, repo-as-system-of-record

In 6 listsLink may be dead

Anthropic – Effective harnesses for long-running agents

Session bridging, feature lists, incremental progress, testing

In 5 listsDetails

Aakash Gupta (Medium) – 2026 is agent harnesses

Harness as moat, minimal intervention, progressive disclosure

Link may be dead

YC Paper Club (video) – Why the harness matters more than the model

September 2026 session with the authors of Prime Agent, OpenJarvis, and QM; the history of harnesses runs from 7:00 to 17:00

learn-agent-architecture

Section-by-section teardown of how Claude Code and Hermes Agent structure the agent loop, tools, permissions, context, and memory, with a small runnable Python demo per mechanism

In 2 lists

LangChain

, Anthropic, OpenAI: Official docs for major agent platforms

Thank you, contributors

@baskduf

harness-starter-kit · @ahwurm — LocalHarness · @liviux — LoopTroop · @rishabhpoddar — TeamCopilot, on the radar · @abilliontokens — oh-my-pi · @pranshuchittora — agent-qa · @claudiusthebot — Talon · @madarco — AgentBox · @jmthomasofficial — JMT x402 Agent Tools · @ShukantPal — Proliferate ·…

See category
100

Table of Contents

hesreallyhim/awesome-claude-code

A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team…

Fresh★ 58k252 entriesPushed today
100

Awesome Agent Skills

VoltAgent/awesome-agent-skills

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

Fresh★ 37k965 entriesPushed today
98

Awesome Production Machine Learning

EthicalML/awesome-production-machine-learning

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Fresh★ 21k535 entriesPushed 4 days ago
96

Static Analysis

analysis-tools-dev/static-analysis

⚙️ A curated list of static analysis (SAST) tools and linters for all programming languages, config files, build tools, and more. The focus is on tools which improve…

Fresh★ 15k532 entriesPushed 3 days ago
96

Awesome Nano Banana Pro Prompts

YouMind-OpenLab/awesome-nano-banana-pro-prompts

🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source.

Fresh★ 14k173 entriesPushed today
95

Contents

ossu/computer-science

🎓 Path to a free self-taught education in Computer Science!

Fresh★ 211k65 entriesPushed 7 days ago