Best Of Agent Harnesses
🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
Simon Willison's definitionof the agent itself is the cleanest: "an LLM agent runs tools in a loop to achieve a goal." The harness is everything…
everything-claude-codesuspected star manipulation — ~228k stars / ~35k forks on a repo created 2026-01 with no matching install base,…
Daytonaarchived upstream — kept for citation
DeepSeek-Reasonixarchived upstream — kept for citation
spring-ai-tool-search-toolarchived upstream — kept for citation
coderClawarchived upstream — kept for citation
agenticSeekFully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code…
openfangOpen-source Agent Operating System
evolverThe GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
ZCodeZ.ai's coding agent harness. Powerful, intelligent, extensible.
openevolveOpen-source implementation of AlphaEvolve
reefInfrastructure for continually self-improving agents: records live traffic and feedback, then ships a scored update to…
intentkitIntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
agentscope-javaBuild distributed, production-grade, long-running agents.
vibesdkAn open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare…
ekoEko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
antigravity-sdk-pythonA Python library for building AI agents that leverage the full power of Google Antigravity.
fast-agentCode, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
MIRIXMirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions…
OrcaReplayRecord, replay, fork, and debug any agent run with any model; time travel for AI agents.
placecallSkill and plugins that give Claude Code, Codex, Cursor, and Gemini CLI a hosted MCP server for phone calls to US…
5diveRun a company of agents on a server you own: each agent is an official CLI (Claude Code, Codex, Pi) as a systemd…
llm-wiki-cliProactive memory CLI for AI agents: recall, maintain, and evolve persistent, source-grounded knowledge across sessions.
red-team-blue-team-agent-fabricAI agent security harness for adversarial testing: 600+ executable tests across MCP, A2A, x402/L402, and decision…
mcp-memory-serverMCP memory server backed by a hosted engine: recall that re-ranks on helped or misled feedback, plus shared rooms for…
model-citizenControl plane for Claude Code and Codex: one checkout of rules, skills, and roles projected into each runtime, with…
AutobotAGENTS.md operating contract, on-disk memory, and an independent completion validator for ChatGPT and Codex local…
loopgate_harnessRun any CLI agent in a loop against specs: fresh context each iteration, the repo as durable memory,…
GoodMemoryLocal-first, auditable memory layer for AI apps and coding agents (Codex, Claude Code, MCP, HTTP).
teamcopilotDeploy AI agents for your team to automate business workflows and coding.
nausicaa-harnessTreats an agent run as a dynamic topology of lanes instead of one linear loop; the model decides when to observe or…
atlarix-releasesAtlarix: proprietary desktop agent workstation; hunk-by-hunk diff approval, per-OS sandboxed shell, lexical retrieval,…
dsh-mcp-lensMCP tool search for large catalogs: 1,000 tools behind 2 schemas, exact-schema calls, allow/deny controls.
house-party-protocolEvidence and approval contracts around Claude Code and Codex CLI: done is a recorded exit code, and a verdict from the…
workkitClaude Code plugin that runs work through GitHub Issues: an accepted spec gates each build, a blind verifier reviews,…
laravel-ai-verifyVerification gate for coding agents on Laravel 12/13: runs only the checks a diff needs, fails weakened tests, and…
yylo-benchmarkLongitudinal benchmark for coding-agent runs: sandboxed fresh-repo attempts, deterministic and blinded LLM judging,…
jet-browserPortable WPE WebKit browser runtime for agents: one isolated process driven by ordered JSONL or MCP commands, with…
GiovanniClaude Code plugin for a daily digest loop: parallel source pulls by subagents, drift checks against a constitution in…
agentlinkCoding-agent harness inside VS Code: editor code intelligence as tools, reviewable diffs, an approval policy,…
wippaAGENTInstall-once OpenCode config: one orchestrator with edit and shell denied delegates to 12 specialist subagents behind…
mcp-guardianMCP proxy for tool scoping and context compression: progressive discovery with 3 meta-tools.
minimal-harnessDependency-free acceptance and handoff kernel for coding agents: runs configured checks and fails closed when Git or…
AwesomeAwesome lists on many topics
OpenAI – Harness engineeringEnvironment design, intent, feedback loops, repo-as-system-of-record
Anthropic – Effective harnesses for long-running agentsSession bridging, feature lists, incremental progress, testing
Aakash Gupta (Medium) – 2026 is agent harnessesHarness as moat, minimal intervention, progressive disclosure
YC Paper Club (video) – Why the harness matters more than the modelSeptember 2026 session with the authors of Prime Agent, OpenJarvis, and QM; the history of harnesses runs from 7:00 to…
learn-agent-architectureSection-by-section teardown of how Claude Code and Hermes Agent structure the agent loop, tools, permissions, context,…
LangChain, Anthropic, OpenAI: Official docs for major agent platforms
@baskdufharness-starter-kit · @ahwurm — LocalHarness · @liviux — LoopTroop · @rishabhpoddar — TeamCopilot, on the radar ·…