Best of Agent Harnesses and Harness Techniques
🏆 Curated list of AI agent harnesses, orchestration frameworks, and harness techniques for reliable agentic systems.
🌐 Browse the searchable site — one page per harness, filter by capability, autonomy & recovery.
🤖 Agents can query this list — an MCP server (recommend, pick_harness, …), llms.txt & JSON, so your agent recommends harnesses too.
What is an agent harness?
A model answers; an agent acts. An agent harness is the runtime that turns one into the other: the model thinks, the harness decides what that thinking is allowed to touch.
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 "the kernel process of a new Operating System", and the harness is the rest of that OS, its scheduler, permissions, and memory. The SWE-agent paper proved the stakes by coining the agent-computer interface: how tools and feedback are presented changes what a model can do, independent of the model. The field's advice has since converged on investing here rather than in framework plumbing, from Anthropic's build-simple guidance to Jerry Liu's argument that the framework era is over and the layers that matter now are skills, tools, and context quality. Those are the layers this list catalogs.
Why harnesses matter
Better models make harnesses more important: more capabilities mean more failure modes, and production needs retry logic, fallbacks, and validation. Harness quality, not just model quality, determines whether agents actually ship. This list ranks projects by relevance to harness concerns (environment, orchestration, lifecycle, guardrails) and by stars/activity.
The benchmark data now backs this up. On SWE-bench Pro, "swapping the agent harness changed pass@1 more than many model upgrades do" (AINews, Aug 8 2026, citing analysis by @joelniklaus). Same model, different harness: 23% to 52% pass@1 on GLM-5.2, and 15% to 36% on Gemma 4 26B. Harness rankings barely transfer across models (rank correlation -0.05), so a small model in the right harness can approach a much larger model in the wrong one.
That is the problem the MCP server in this repo solves. Point your agent at it and it can call recommend or pick_harness to choose a harness matched to your model and task, instead of inheriting whichever harness someone else benchmarked.
The landscape at a glance
Every project in the list, plotted by adoption surface area (the simplicity ↔ capability axis) against GitHub stars. Colors are categories; the largest projects in each tier are labeled.
The same projects placed by how much unsupervised rope they're designed to give (autonomy) and what happens when a run dies (recovery). In the tables below, ★ marks headless-ready projects and ✱ marks durable ones. Both charts regenerate from the list data on every refresh.
How to Pick a Harness
Start with the guide, then the head-to-head decision pages — grounded in the same data as the tables below:
- How to pick a harness: six questions that turn this list into a decision, plus the chart to internalize first (the harness moves scores more than the model)
- How to test-drive a harness: the two-week trial protocol, with a fair setup, tasks from your own repos, seven measurements, and the walk-away test
- OpenClaw vs Hermes — the always-on personal-agent debate: presence vs discipline, plus what the field reports actually say
- Terminal coding agents — opencode vs Codex vs Gemini CLI vs crush vs goose
- Multi-agent orchestration — OpenAI Agents SDK vs CrewAI vs AutoGen vs LangGraph
- Agent memory layers — Mem0 vs Letta vs claude-mem
- Agent sandboxing: what it is, the key concepts, and the field (E2B vs Daytona vs Modal and more)
- Agent evals (SWE-bench vs inspect_ai vs Terminal-Bench)
- Eval and observability platforms (Langfuse vs LangSmith vs Braintrust vs Phoenix)
- Browser agents (browser-use vs Stagehand vs Playwright MCP vs chrome-devtools-mcp)
- Browser infrastructure (Browserbase vs Steel vs Hyperbrowser)
- Claude Code skill packs (superpowers vs GStack vs get-shit-done vs Anthropic Skills)
- Context files for agents (AGENTS.md vs CLAUDE.md vs skills vs MCP tool search)
Pick by use case
Reader's index: pick by what you want to do, not by category. Tag chips (e.g. mcp · memory) next to each row let you cross-filter by capability — see TAGS.md for the full cross-reference.
- I want a turnkey coding agent today — opencode, Cline, Codex, Gemini CLI, OpenHands, crush, Roo Code · see Coding agent products (IDEs, CLIs, full suites)
- I want an always-on personal agent that lives in my chat apps — OpenClaw, Hermes, Khoj, Agent Zero, OpenHarness (HKUDS) · see Personal agent runtimes
- I want to extend Claude Code, Codex, or OpenCode with skills and slash commands — Anthropic Skills, wshobson/agents, superpowers, GStack, pmstack · see Coding harness configs and SDKs
- I want to build my own coding harness from scratch — Claude Agent SDK, Google ADK, AutoHarness, SWE-agent, RepoMaster, claw-code-agent · see Coding harness configs and SDKs
- I want a drop-in memory layer for agents — Mem0, Graphiti (Zep), claude-mem, agentlog, letta · see Plugins, MCPs, CLI tools
- I want to plug hundreds to thousands of tools without context bloat — MCP-Zero, ToolGen, ToolRAG, langgraph-bigtool · see Progressive disclosure harnesses
- I want multi-agent orchestration — openai-agents-python, crewAI, autogen, Microsoft Agent Framework, PraisonAI, agent-squad · see Multi-agent and orchestration
- I want a general LLM app framework — langgraph, langchain, llama-index, pydantic-ai, agno · see Frameworks
- I want low-code / visual workflows — langflow, Dify, n8n · see Frameworks
- I want browser-using agents — browser-use, Stagehand, WebVoyager, puppeteer-real-browser-mcp · see Plugins, MCPs, CLI tools
- I want sandboxed code execution for agent-generated code — E2B, Agent Sandbox, Daytona, smolagents, OpenHands · see Libraries and SDKs
- I want to evaluate or benchmark agents — SWE-bench, Terminal-Bench, AgencyBench, inspect_ai, WebArena, VitaBench · see Evaluation and benchmarking harnesses
- I want a deep research / autonomous research agent — deepagents, gpt-researcher, openagents · see Research and task-specific harnesses
- I want a provider-agnostic LLM pipe (not a framework) — LiteLLM, vercel/ai · see Libraries and SDKs
For agents
This list is also published in machine-readable form, so coding agents and research agents can recommend harnesses — not just humans browsing GitHub:
- harnesses.json — every project with category, complexity tier, capability tags, stars, license signal, and a concrete example link, plus the full use-case index.
- llms.txt — the entire list in one agent-readable file. Point any agent at the raw URL.
- MCP server —
recommend(one opinionated pick + alternatives + what to avoid, e.g. repos flagged for star manipulation),compare/compare_for(2–4 harnesses side by side — by id or by task — who leads on which axis incl. researched sandboxing/memory/hooks/prompt-optimization ratings, graveyard warnings, the matching decision guide),pick_harness(ranked, with complexity/autonomy/recovery filters),pick_infrastructure(picks at any level of the infra stack plus a live GitHub/Hacker News discovery pass, so answers aren't limited to this list),search_harnesses,get_harness,list_categories, pluslist_comparisons/get_comparisonfor the decision guides. Published to PyPI and the official MCP registry asio.github.RyanAlberts/agent-harnesses. One-line install (needs uv):
claude mcp add agent-harnesses -- uvx agent-harnesses-mcp
Or hire a skeleton
Don't just read the list — agents/ ships three agent skeletons: open-source agents that run on the AI subscription you already pay for. Clone the file, customize the instructions, done. All three work against the current week's data and deliver to Slack or Notion when either is connected:
- harness-scout — describe what you're building; it picks your harness, with evidence and a graveyard check.
- stack-auditor — flags the harnesses in your codebase that died, and can trace your agent session logs to show how the harness steers your technical decisions.
- harness-radar — weekly movement briefing: climbers, arrivals, deaths, graduations.
curl -fsSL https://raw.githubusercontent.com/RyanAlberts/best-of-Agent-Harnesses/main/agents/harness-scout.md -o .claude/agents/harness-scout.md
Contents
- The landscape at a glance
- How to Pick a Harness
- Pick by use case
- For agents: harnesses.json, llms.txt, MCP server, agent templates
- FAQ
- Progressive disclosure harnesses 8 projects
- Coding agent products (IDEs, CLIs, full suites) 22 projects
- Coding harness configs and SDKs 17 projects
- Personal agent runtimes 10 projects
- Frameworks 25 projects
- Multi-agent and orchestration 12 projects
- Plugins, MCPs, CLI tools 19 projects
- Memory and state 5 projects
- Evaluation and benchmarking harnesses 18 projects
- Observability and eval-ops 4 projects
- Research and task-specific harnesses 5 projects
- Libraries and SDKs 15 projects
Guide to rankings
- ⭐ Stars — GitHub star count, captured 2026-08-16; tables sort by stars descending.
- ⚖️ Simplicity ↔ capability — adoption surface, 4 tiers: super simple (a format, one concept) → mostly simple (thin layer) → slightly complex (real SDK) → complex (product suite).
- ★ Headless-ready — designed for unattended runs, batches, and fleets (the top of the autonomy scale: step-gated → checkpoint-gated → bounded → headless).
- ✱ Durable — persisted execution state survives restarts mid-task (the top of the recovery scale: none → retry → resumable → durable).
- ✅ Open source — ✅ standard OSS license · ⚠️ source-available/restricted · ❓ no or unclear license.
- 🏷️ Tags — capability chips auto-derived from descriptions; full cross-reference in TAGS.md.
- 🎯 Examples — one concrete "show me it in action" link per project, not a docs root.
Every project's full autonomy and recovery tier is plotted in the grid above and carried in harnesses.json and llms.txt; scores are editorial, from public docs — maintainer corrections via issue/PR are merged fast.
Progressive disclosure harnesses
Formats, runtimes, and patterns that reveal context, tools, or instructions in layers—index first, details on demand—to control tokens and improve agent focus (the "map, not encyclopedia" principle).
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | Headroom | 66.5k | Compresses tool outputs, logs, files, and RAG chunks with content-aware compressors before they reach the model—claimed 20% fewer tokens for coding agents and 60–95% fewer for JSON, same answers. Ships as a library, HTTP proxy, or MCP server, so it drops in front of whatever harness you already run. mcp · rag |
✅ | mostly simple (compression library/proxy/MCP server) | Project README |
| 2 | awesome-cursorrules | 40.6k | Curated .cursorrules and skills that leverage Cursor's index-then-load model; the canonical collection for rules-as-progressive-disclosure in the IDE. ide |
✅ | super simple (content bundle) | PyTorch cursorrules |
| 3 | agents.md | 23.7k | Open format for repo-scoped agent briefings; nested AGENTS.md files scope instructions per directory, so agents get a map of what exists and load only what's relevant. Read by 20+ tools including Codex, Cursor, and Copilot. ide · typescript |
✅ | super simple (format only) | Self-hosting AGENTS.md |
| 4 | context-mode | 19.9k | Context-window optimization layer that sandboxes tool output before it reaches the model (claimed 98% reduction) and persists session memory across 17 agent platforms via MCP and hooks—progressive disclosure applied to tool results, not just instructions. mcp · memory · sandbox |
⚠️ Elastic-2.0 | mostly simple (output sandboxing, cross-platform) | Project README |
| 5 | langgraph-bigtool ✱ | 554 | Build LangGraph agents with large tool sets; retrieval and on-demand tool loading so agents scale beyond context without stuffing every schema upfront. tool-discovery · python |
✅ | slightly complex (large tool sets) | Math-library tool agent |
| 6 | MCP-Zero | 506 | Active tool discovery for autonomous agents: model requests tools by requirement; hierarchical semantic routing over 308 servers / 2,797 tools with ~98% token reduction (APIBank). tool-discovery |
✅ | complex (3k tools, full routing) | APIBank experiment |
| 7 | ToolGen | 184 | ICLR 2025: unified tool retrieval and calling via generation; 47k+ tools without context stuffing—retrieval and invocation in one generative step. tool-discovery · python |
❓ | complex (47k+ tools) | Full eval pipeline |
| 8 | ToolRAG | 33 | Semantic tool retrieval for LLMs; serves only the tools the user query demands (MCP-compatible), unlimited tool sets with zero context penalty. mcp · tool-discovery |
✅ | mostly simple (query-driven retrieval) | MCP server retrieval |
Coding agent products (IDEs, CLIs, full suites)
Turnkey coding agents you install and run: IDE extensions, terminal CLIs, Dockerized workspaces. Each entry notes which part is the harness (the agent loop, tool wiring, approval model) versus the UI shell (VS Code extension, TUI, browser client).
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | opencode ★ | 198k | Open-source terminal coding agent (formerly sst/opencode; transferred to anomalyco). The harness is a multi-provider tool-call loop (Claude, OpenAI, Gemini, local) with strong plugin and MCP support; the TUI is the shell. 100% OSS, very actively shipped. mcp · provider-agnostic · cli · tui · typescript |
✅ | slightly complex (multi-provider, plugins, MCP) | Agent system page |
| 2 | Gemini CLI | 107k | Google's first-party terminal agent for Gemini. The harness is the plugin/MCP tool-call loop; the terminal is the shell—Google's parallel to Claude Code / Codex, not just an API. mcp · cli · typescript |
✅ | slightly complex (official CLI, plugins, MCP) | MCP server setup |
| 3 | Codex | 106k | OpenAI's terminal coding agent. The harness is the sandboxed tool-call loop with multi-provider support; the CLI is the shell. Reference implementation for "official CLI that ships code." sandbox · provider-agnostic · cli |
✅ | slightly complex (reference CLI, sandboxed) | Sandboxing concept |
| 4 | pi | 91.3k | The upstream AI agent toolkit behind this list's oh-my-pi fork: a unified multi-provider LLM API, agent loop, and TUI shell providing the harness that oh-my-pi's Rust rewrite builds on. provider-agnostic · tui · rust |
❓ | slightly complex (multi-provider agent loop, TUI) | Project README |
| 5 | OpenHands ★ | 84.2k | Dockerized software-engineering agent. The harness is the bash/editor/browser toolset with micro-agents and event-stream session bridging; Docker is the sandbox. Main OSS choice for teams self-hosting autonomous repo work. memory · browser · sandbox · python |
⚠️ (multi-license) | complex (Docker runtime, multi-surface agent — product suite) | Repository microagents |
| 6 | Open Interpreter | 68k | Lightweight terminal coding agent oriented to open models (DeepSeek, Kimi, Qwen). The harness is a code-execution loop — the model writes code, the harness executes it with confirmation gates; the CLI is the shell. The original "let the LLM run code on my machine" project, reborn for open weights. cli · python |
✅ | mostly simple (lean code-exec loop) | Quick start |
| 7 | Cline | 66.3k | VS Code extension whose harness is a plan-then-act loop with per-step human approval and cost transparency; the VS Code integration is the UI shell. Open-source counterweight to Cursor. ide · typescript |
✅ | slightly complex (plan-then-act, approval gates) | Plan & Act mode |
| 8 | goose ★ | 52.9k | Block-originated Rust agent, now stewarded by the Linux Foundation's Agentic AI Foundation (aaif-goose/goose). The harness is the MCP/ACP extension model with recipes and provider choice; there's no fixed UI slot—you bolt it into whatever shell you use. mcp · rust |
✅ | slightly complex (extensions, MCP/ACP) | Goose recipes guide |
| 9 | DeepSeek-Reasonix | 34.6k | DeepSeek-native terminal coding agent. The harness is engineered around prefix-cache stability for long-running sessions; the TUI is the shell. memory · cli · tui · typescript |
❓ | slightly complex (terminal agent, prefix-cache tuned) | Project README |
| 10 | vibe-kanban | 27.8k | Kanban-style fleet manager for running Claude Code, Codex, or any coding agent across many tasks at once. The harness contribution is the task-queue/review layer on top of whichever agent executes; not an agent loop itself. | ❓ | slightly complex (task-fleet manager) | Project README |
| 11 | crush | 27.4k | Charm's terminal coding agent (Charm's fork of the original OpenCode). The harness is the tool-calling loop with session persistence; the Bubble Tea TUI is the shell. memory · cli · tui |
⚠️ FSL-1.1-MIT | slightly complex (terminal agent, TUI) | Crush launch post |
| 12 | qwen-code | 27.1k | Alibaba's official terminal coding agent, forked from Gemini CLI's agent loop and retuned for Qwen models. The harness is the same sandboxed tool-call loop as its upstream; the terminal is the shell. sandbox · cli · typescript |
❓ | slightly complex (official CLI, Gemini-CLI fork) | Project README |
| 13 | Kilo Code | 26.9k | VS Code extension and CLI in the Cline/Roo-Code lineage — a natural pick now that Roo-Code is archived upstream. The harness is an approval-gated autonomous-mode loop with a provider/tool marketplace; the IDE is the shell. mcp · cli · ide · typescript |
❓ | slightly complex (IDE extension + CLI, MCP) | Project README |
| 14 | Symphony ★ | 26.7k | OpenAI's harness for fanning a task out into many isolated, autonomous coding-agent implementation runs and surfacing the ones that pass, so a team manages outcomes instead of supervising each session. sandbox |
❓ | complex (parallel isolated runs — product suite) | Project README |
| 15 | oh-my-pi | 25.2k | Terminal coding agent (fork of Pi) that wires the IDE into the harness: hash-anchored edits, a 32-tool loop tuned per-model, LSP rename/references/diagnostics on every write, a real DAP debugger (lldb/dlv/debugpy), long-lived Python + Bun execution kernels that call back into the agent's tools, browser control, and 40+ providers (Claude/OpenAI/Gemini/local). ~55k-line Rust core. browser · provider-agnostic · cli · ide · rust |
✅ | slightly complex (terminal agent, LSP/DAP, multi-provider) | LSP wired into edits |
| 16 | Roo Code | 24.3k | VS Code/Cursor extension in the Cline lineage. The harness is the approval-gated agent with custom modes and a strong MCP story; the IDE is the UI. Popular community fork when you want that workflow without the upstream extension. mcp · workflow · ide · typescript |
✅ | slightly complex (IDE extension, MCP-first) | Custom modes guide |
| 17 | jcode | 17.7k | Rust terminal coding agent pitched as the most RAM-efficient harness in its class; MCP support, multi-provider (Claude/OpenAI). mcp · memory · provider-agnostic · cli · rust |
❓ | slightly complex (terminal agent, low-memory) | Project README |
| 18 | eigent | 15k | Open-source desktop harness positioned as a local, free alternative to Claude Cowork and Codex: multi-agent workspace orchestration in a self-hosted app rather than a hosted product. multi-agent · local |
❓ | complex (desktop multi-agent workspace — product suite) | Project README |
| 19 | cc-haha | 14.1k | Local-first desktop workspace harness for Claude Code and other agents: multi-agent sessions, Git worktrees, code diffs, a skill marketplace, and chat-app access (WeChat, Telegram, WhatsApp). memory · multi-agent · typescript |
❓ | complex (desktop workspace, multi-agent — product suite) | Project README |
| 20 | claw-code-agent | 543 | Python reimplementation of the Claude Code agent architecture with zero external dependencies; interactive chat, streaming, plugin runtime, nested agent delegation, cost tracking, MCP transport—portable harness without the Rust/TS toolchain. mcp · rust · python · typescript |
❓ | slightly complex (pure Python, plugin runtime) | Quick Start guide |
| 21 | AgentBox | 352 | Runs multiple coding agents in parallel, each in its own sandboxed VM, locally or in the cloud, from one command. The harness contribution is the VM-per-agent isolation and fleet fan-out layer; whichever agent runs inside owns the loop. sandbox · typescript |
✅ | slightly complex (VM-per-agent sandbox, parallel fan-out) | Parallel agents quick start |
| 22 | Proliferate | 167 | Open-source AI IDE for Claude Code, Codex, OpenCode, and more. The harness contribution is the workspace/session orchestration layer: run multiple coding agents in parallel, locally or in the cloud, with isolated workspaces, reusable workflows, and shared team context. multi-agent · sandbox · ide · typescript |
✅ | complex (multi-agent workspace orchestration — product suite) | Product README |
Coding harness configs and SDKs
Skill packs, slash-command libraries, meta-prompting frameworks, and official SDKs that give you the harness (the agent loop, planning, memory, hooks) without bundling a specific IDE or CLI shell.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | superpowers | 273k | Performance-oriented harness pack for Claude Code and 13 other harnesses (Codex, Cursor, OpenCode, Gemini CLI, more): skills, instincts, memory, security, research-first workflows. Treats harness engineering itself as the performance lever. memory · cli · ide |
✅ | complex (multi-IDE skill stack — product suite) | TDD skill |
| 2 | Anthropic Skills | 170k | Anthropic's official Agent Skills repository: SKILL.md-based folders (instructions, scripts, resources) Claude dynamically loads on Claude Code, Claude.ai, and the API. The reference for progressive-disclosure skill packs in 2026. | ⚠️ Anthropic terms | mostly simple (official skills format) | docx skill |
| 3 | GStack | 128k | Garry Tan's Claude Code skill stack: 23 slash-command modes (CEO/eng/design review, QA, ship, browse, retro, …) that structure one assistant as a virtual engineering team. Daily driver while running YC. typescript |
✅ | slightly complex (multi-role slash-command harness) | /ship SKILL.md |
| 4 | addyosmani/agent-skills | 87.7k | Addy Osmani's production-grade skill pack: 24 engineering skills and 4 specialist agent personas that encode senior-dev workflows (spec through deploy) across 70+ coding agents including Claude Code, Cursor, and Copilot. The harness contribution is the skill/workflow layer, not a new agent loop. workflow · ide |
✅ | mostly simple (skills bundle, cross-agent) | Project README |
| 5 | awesome-claude-code | 52.4k | Large community-curated index of Claude Code skills, slash commands, status lines, and plugins—resources for extending the harness, not a harness itself, but the most-followed catalog of the genre. | ❓ | super simple (curated resource index) | Project README |
| 6 | wshobson/agents | 38.9k | Cross-harness marketplace of drop-in subagents and skills for Claude Code, Codex CLI, Cursor, OpenCode, and Copilot; specialized, production-ready agent definitions you install rather than hand-write. multi-agent · cli · ide |
✅ | super simple (drop-in agent packs) | Agent catalog |
| 7 | planning-with-files | 26.2k | Skill for persistent, file-based planning across long-running coding-agent sessions: crash-proof markdown plans, session recovery after /clear/compaction, and a deterministic completion gate—Manus-style planning as a drop-in harness layer via the Agent Skills standard. memory |
❓ | mostly simple (skill, file-based state) | Project README |
| 8 | SWE-agent ★ | 20.1k | LM-driven harness built for SWE-bench: edit state, command execution, and issue-focused loop—the reference agent stack next to the benchmark itself. memory · evals · python |
✅ | slightly complex (SWE-bench pairing, stateful edits) | Default agent config |
| 9 | get-shit-done | 8.3k | Goal-backward planning and wave-based execution over fresh context windows; avoids context rot by design. Python/JS meta-prompting for Claude Code, OpenCode, Gemini CLI. cli · python |
✅ | mostly simple (meta-prompting, you own stack) | gsd:ship command |
| 10 | Claude Agent SDK ★ | 7.9k | Official Anthropic SDK (Python + TypeScript, demos, quickstarts): built-in tools, MCP, long-running coding agents with session bridging. mcp · memory · python · typescript |
✅ | complex (full SDK, session bridging — product suite) | Research agent demo |
| 11 | agents-cli | 5.6k | Google's official CLI and skill pack that layers agent-creation, evaluation, and deployment skills on top of whatever coding assistant you already run, rather than shipping its own agent loop—the harness as a config/skills add-on, not a new runtime. evals · cli |
❓ | mostly simple (skills/CLI layer, no new runtime) | Project README |
| 12 | skillhub | 4.9k | iFlytek's self-hosted registry for publishing, versioning, and governing agent skill packages—the harness config layer treated as an enterprise artifact store rather than a CLI or IDE shell. local · cli · ide |
❓ | mostly simple (skill registry/governance) | Project README |
| 13 | Meta-Harness | 1.4k | Reference implementation from the Meta-Harness paper: an academic testbed for harness-engineering research, not a product—useful as a citation-grade baseline rather than something you'd run in production. | ❓ | slightly complex (research reference implementation) | Project README |
| 14 | RepoMaster ★ | 542 | Repo-scoped research harness: builds function-call and module-dependency graphs to explore only what's needed; large relative gains on MLE-bench and GitTaskBench with lower token use. workflow · python |
❓ | slightly complex (graph-based exploration) | PDF-parse case study |
| 15 | AutoHarness | 367 | Lightweight governance harness: wraps any LLM client in ~2 lines for automated harness engineering—6–14 step pipeline, YAML constitution, risk-pattern matching, session persistence with cost tracking, multi-agent profiles. memory · multi-agent · provider-agnostic · python |
✅ | super simple (2-line wrapper, YAML gov) | Full pipeline demo |
| 16 | LoopTroop | 119 | Config layer that chains LLM councils for planning, Ralph loops for iterative refinement, and OpenCode worktrees for shipping. The harness contribution is the council → loop → worktree pipeline; OpenCode underneath executes. typescript |
✅ | mostly simple (config pipeline over OpenCode) | Council → loop → worktree pipeline |
| 17 | pmstack | 8 | Claude Code config for AI product managers: CLAUDE.md plus skills for competitive analysis, PRD-from-signal, metric frameworks, stakeholder briefs, and agent eval design. "GStack for PMs." evals |
✅ | super simple (skills bundle, PM-focused) | PRD-from-signal skill |
Personal agent runtimes
Always-on, self-hosted agents you run as a daemon and talk to from chat apps: gateway runtimes, second brains, and self-improving assistants. The agent as a product you operate, not a library you build with.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | OpenClaw ★ | 386k | Self-hosted, always-on personal agent (formerly Clawdbot/Moltbot): a gateway + event-loop runtime that treats messages, heartbeats, crons, and webhooks as one input queue, persists state to local files, and lives in your chat apps (WhatsApp, Telegram, Slack, Discord). 13,700+ community skills; the fastest-growing repo in GitHub history. typescript · multi-agent |
✅ | complex (always-on runtime, channels, skill ecosystem — product suite) | Agent runtime architecture |
| 2 | Hermes ★ | 231k | Nous Research's self-improving agent: a learning loop turns experience into reusable skills, builds a persistent user model across sessions, and checkpoints state to disk with rollback; lean enough for a $5 VPS, driven from chat, and model-agnostic (Nous Portal, OpenRouter, OpenAI, or any endpoint). memory · python · provider-agnostic |
✅ | slightly complex (lean runtime, learning loop, disk-first memory) | Built-in skills |
| 3 | nanobot | 47.1k | Ultra-lightweight, self-hosted personal agent framework: the harness is a Python daemon wiring tools, memory, and MCP into chat/webhook front ends (Telegram, Discord, web); minimal footprint alternative to heavier personal-runtime stacks. mcp · memory · local · python |
❓ | mostly simple (lightweight daemon, chat/MCP) | Project README |
| 4 | CowAgent | 46.5k | Self-hosted harness (formerly chatgpt-on-wechat) that plans tasks, runs tools/skills, and self-evolves via memory; multi-model, multi-channel (WeChat, Telegram, etc.), one-line install. memory · python |
❓ | slightly complex (multi-channel, self-evolving) | Project README |
| 5 | Khoj ★ | 36.5k | Self-hostable "AI second brain": answers over your docs and the web, custom agents, scheduled automations, and multi-client reach (web, Obsidian, Emacs, WhatsApp). A personal-agent harness with retrieval at the core. python |
✅ | complex (server + clients — product suite) | Feature tour |
| 6 | Eliza ★ | 19.1k | Open "agentic operating system" (elizaOS): persistent multi-agent runtime with character files, a plugin ecosystem, and social/platform integrations — the harness behind a large share of autonomous social agents. memory · multi-agent · typescript |
✅ | complex (runtime + plugin ecosystem — product suite) | Agent quickstart |
| 7 | Agent Zero | 18.9k | Organic, prompt-defined personal agent framework: hierarchical sub-agents, persistent memory, browser and code tools, and self-modifying behavior; runs in Docker with a web UI. memory · multi-agent · browser · sandbox · python |
❓ | slightly complex (prompt-defined, Docker + web UI) | Framework tour |
| 8 | OpenHarness (HKUDS) | 15.4k | Open agent harness with a built-in personal agent ("Ohmo") that runs across Feishu, Slack, Telegram, and Discord; core tool-use, skills, memory, multi-agent coordination with auto-compaction for multi-day sessions. memory · multi-agent |
✅ | complex (personal agent + multi-channel — product suite) | harness-eval skill |
| 9 | AIlice | 1.4k | Fully autonomous general-purpose agent; one binary, Docker-ready, for when you want "set goal and walk away" without a framework. sandbox · python |
✅ | slightly complex (autonomous, one binary) | Task showcase |
| 10 | Talon ★ | 71 | Multi-platform personal agent living in Telegram, Discord, Teams, and the terminal. The harness is a pluggable-backend loop (Claude, Kilo, OpenCode, Codex, OpenAI Agents) with full MCP tool access and persistent background agents (Goals, Heartbeat, Dream); the chat apps are shells. mcp · memory · cli · typescript |
✅ | slightly complex (multi-platform, pluggable backends, MCP) | Multi-platform setup |
Frameworks
General-purpose agent and LLM application frameworks (the app layer, not harnesses per se).
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | n8n ★ ✱ | 201k | Fair-code workflow engine with 400+ nodes and native AI nodes; the self-hosted Zapier that actually does agents and LangChain. workflow · local · typescript |
⚠️ Fair-code | complex (400+ nodes, workflow engine — product suite) | Agent vs chain workflow |
| 2 | AutoGPT ★ | 187k | The original autonomous loop: goal in, agent iterates with tools and memory; Forge is the dev framework, Benchmark the eval harness. memory · evals · python |
⚠️ Polyform-SU | complex (autonomous loop, tools, memory — product suite) | Medium blogger graph |
| 3 | langflow ★ | 153k | Low-code UI to build and deploy LangChain/LangGraph flows; visual DAG editor and one-click run. low-code · python |
✅ | complex (low-code, visual — product suite) | Chat with RAG flow |
| 4 | Dify ★ | 153k | One-stop LLM app platform: visual workflows, RAG pipeline, 50+ tools, model management; "ship from prototype to prod" in a single UI. low-code · rag · python |
⚠️ Fair-code | complex (one-stop platform — product suite) | Customer-service bot |
| 5 | langchain | 144k | Chains, tools, retrievers, and agents; the usual entry point for "add tools to an LLM" in Python/JS. python |
✅ | complex (kitchen-sink ecosystem — product suite) | Build an agent notebook |
| 6 | browser-use | 109k | Python web-agent harness: natural-language goals become browser actions, driven directly over the Chrome DevTools Protocol (it dropped Playwright in August 2025). The biggest community in the browser-agent category. browser · python |
✅ | slightly complex (LLM + browser, CDP) | Grocery shopping agent |
| 7 | llama-index | 51.7k | Data-centric: indexing, RAG, and query engines; agent abstractions sit on top of your data pipelines. rag · python |
✅ | complex (RAG + agents — product suite) | Research assistant workflow |
| 8 | agno | 41.7k | Python agents with memory, knowledge bases, tools, and structured outputs; continues the PhiData-era product line under the Agno name—production apps, evals, and pipelines. memory · evals · python |
✅ | complex (memory, KB, observability — product suite) | Agent with tools |
| 9 | langgraph ★ ✱ | 39.8k | State-machine graphs over LLM steps; checkpointing, human-in-the-loop, and durable execution so workflows survive restarts. workflow · python |
✅ | slightly complex (graphs, checkpointing, durable exec) | Customer support agent |
| 10 | semantic-kernel | 28.5k | Microsoft's plugin and planner layer for LLMs; C#, Python, Java; strong on enterprise auth and orchestration. python |
✅ | complex (enterprise, multi-language — product suite) | Chat completion agent |
| 11 | mastra ✱ | 27.2k | TypeScript-first; agents, tools, and workflows with a single runtime and minimal boilerplate. typed · typescript |
⚠️ Elastic-2.0 | slightly complex (TS-first, minimal boilerplate) | Durable research agent |
| 12 | Haystack | 26.2k | Open-source orchestration framework for context-engineered LLM apps: modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation—closer to LangChain's territory than a coding-agent harness. memory · rag · python |
✅ | complex (modular pipelines, RAG + agents — product suite) | Project README |
| 13 | letta ★ ✱ | 24.3k | Python agent runtime with tool use and control flow; lean API; stateful agents with long-horizon memory. memory · python |
✅ | mostly simple (lean API) | Loop .af agent file |
| 14 | Stagehand | 24k | Browserbase's SDK for browser agents: natural-language actions (act, extract, observe) and deterministic Playwright code mix in one script, so agent flexibility and repeatable automation live in the same harness. browser · typescript |
✅ | slightly complex (NL + code browser SDK) | Act/extract/observe quickstart |
| 15 | rasa ★ | 21.3k | Conversational AI stack (NLU, dialogue, actions); long-standing OSS choice for chat and voice bots. voice · python |
✅ | complex (full stack — product suite) | Sara conversational demo |
| 16 | Google ADK ★ | 21.1k | Google's official Agent Development Kit: code-first Python toolkit for building, evaluating, and deploying agents. Optimized for Gemini but model-agnostic; deploys to Cloud Run / Vertex AI; ships a dev UI with eval and a code-execution sandbox. evals · sandbox · python |
✅ | complex (official Google SDK, eval, deploy — product suite) | Travel concierge agent |
| 17 | botpress ★ | 14.9k | Visual bot builder and runtime; multi-channel, open-source alternative to commercial bot platforms. low-code · typescript |
✅ | complex (visual builder, multi-channel — product suite) | Inter-bot delegation |
| 18 | R2R ★ | 8k | RAG-first: hybrid search, knowledge graphs, multimodal; the framework for "production RAG" when you care more about retrieval than chat UI. vision · rag · workflow · python |
✅ | complex (production RAG — product suite) | hello_r2r RAG example |
| 19 | agent-squad | 7.7k | AWS-originated orchestrator (now under 2FastLabs): intent classification, streaming, SupervisorAgent; "agent-as-tools" so one agent delegates to a squad. multi-agent |
✅ | slightly complex (squad orchestration) | E-commerce support sim |
| 20 | AgentVerse ★ | 5.1k | Task-solving and simulation envs for multi-LLM agents; deploy many agents in custom environments without building infra from scratch. multi-agent · python |
✅ | complex (simulation envs, multi-agent — product suite) | NLP classroom sim |
| 21 | youtu-agent | 4.6k | Tencent Cloud's agent framework: a minimal tool-calling harness designed to perform well with open-source models, positioned as a lighter alternative to heavier orchestration frameworks. | ❓ | mostly simple (minimal loop, open-model focus) | Project README |
| 22 | Bee Agent Framework | 3.4k | Python + TypeScript, LF AI–backed; MCP/ACP, workflows, Requirement Agent; the one that pushes "production multi-agent" without LangChain. mcp · multi-agent · python · typescript |
✅ | complex (production multi-agent — product suite) | ReAct agent example |
| 23 | AgentStack | 2.2k | Scaffolds full agent projects; plugs in CrewAI, LangGraph, OpenAI Swarm, LlamaStack and wires AgentOps observability from day one. | ✅ | slightly complex (scaffold, multi-backend) | Research assistant crew |
| 24 | AgentSilex | 454 | ~300 lines of readable agent code on top of LiteLLM; the "I want to see the whole loop" option for learning or minimal production. python |
✅ | super simple (~300 LOC) | Simple weather agent |
| 25 | SuperAgentX | 203 | Lightweight multi-agent orchestrator with an AGI-angle; minimal surface, docs-first, for teams that want orchestration without the kitchen sink. multi-agent · python |
✅ | mostly simple (minimal surface) | Parallel marketing agents |
Multi-agent and orchestration
Harnesses and patterns for multi-agent coordination and handoffs.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | MetaGPT ★ | 69.9k | The "AI software company" multi-agent framework: role-played PM, architect, and engineer agents turn a one-line requirement into specs, designs, and code along an SOP assembly line. The landmark of the genre; development pace has slowed in 2026. multi-agent · python |
✅ | complex (role pipeline, SOPs — product suite) | Build a customized agent |
| 2 | autogen | 60.5k | Conversable agents and group chats; code execution and human-in-the-loop; Microsoft origin, AG2 ecosystem. ⚠️ In maintenance mode since late 2025: no new features, and Microsoft directs new users to Agent Framework. multi-agent · python |
✅ CC-BY | complex (group chat, code exec, AG2 — product suite) | Distributed group chat |
| 3 | OpenManus | 58k | Open, invite-free general agent from the MetaGPT team: planning plus tool use over a multi-agent loop, aimed at reproducing Manus-style autonomous task completion on your own keys. multi-agent · python |
✅ | complex (multi-agent + tools) | Quickstart |
| 4 | crewAI | 57.2k | Role-based agents (roles, goals, backstories) in Crews; Flows add event-driven and hierarchical control for production. python |
✅ | complex (roles, Flows, production — product suite) | Trip planner crew |
| 5 | ChatDev ★ | 34k | Multi-agent software-company simulation (CEO, CTO, programmer, tester) built on chat chains with communicative dehallucination; ChatDev 2.0 continues the line. MetaGPT's conversational sibling. python |
✅ | slightly complex (chat-chain simulation) | Company simulation quickstart |
| 6 | openai-agents-python | 28.7k | Handoffs, guardrails, and multi-LLM routing; minimal surface so you own the loop. python |
✅ | mostly simple (minimal surface) | Airline customer service handoffs |
| 7 | Microsoft Agent Framework | 12.8k | Microsoft's convergence of AutoGen and Semantic Kernel: build, orchestrate, and deploy agents and multi-agent workflows in Python and .NET, with graph-based workflows and checkpointing — the designated successor harness for both lines. multi-agent · workflow · python |
✅ | slightly complex (Python/.NET SDK, graph workflows) | Python samples |
| 8 | hive | 10.9k | Self-hosted multi-agent harness aimed at production workloads: human-in-the-loop checkpoints and a self-improving agent loop, distinct from single-session coding-agent shells. multi-agent · python |
❓ | complex (multi-agent, human-in-the-loop — product suite) | Project README |
| 9 | omnigent | 8.9k | Open-source meta-harness: orchestrates Claude Code, Codex, Cursor, Pi, and custom agents behind one policy/sandboxing layer so teams swap harnesses without rewriting workflows. sandbox · ide · python |
❓ | complex (meta-harness, policy + sandboxing — product suite) | Project README |
| 10 | PraisonAI | 8.9k | Autonomous multi-agent teams with a single entry point; emphasis on minimal config. multi-agent · python |
✅ | mostly simple (single entry, minimal config) | Orchestrator-workers pattern |
| 11 | AG2 | 4.9k | AG2 (formerly AutoGen): the community-governed continuation of the original AutoGen project after Microsoft's fork diverged—conversable multi-agent groups, code execution, and human-in-the-loop under an open-source AgentOS banner. Graduated off the radar this cycle. multi-agent · python |
❓ | complex (conversable multi-agent, AgentOS — product suite) | Project README |
| 12 | AgentRL ★ | 339 | Multitask, multiturn RL for LLM agents; Ray-based scaling, rollout/actor workers—for teams that want to train agents, not just run them. training · python |
✅ | complex (RL, Ray, train agents — product suite) | Async GRPO trainer |
Plugins, MCPs, CLI tools
IDE plugins, concrete MCP servers, and CLI tools that give agents tools and context.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | MCP Servers | 89.6k | The official reference collection of Model Context Protocol servers (filesystem, git, fetch, memory, time, and more)—the canonical, vetted toolset agents connect to, and the pattern every other MCP server is measured against. mcp · memory · typescript |
✅ | mostly simple (reference servers) | Server catalog |
| 2 | Context7 | 60.8k | MCP server that injects up-to-date, version-specific library docs into an agent's context on demand; kills the stale-training-data hallucinations that plague codegen. mcp · training · typescript |
✅ | super simple (drop-in MCP) | Docs |
| 3 | chrome-devtools-mcp | 49.3k | Google's official Chrome DevTools MCP server: exposes console, network, and performance-trace inspection as tool calls agents can drive directly, instead of a human clicking through the DevTools panel. mcp · browser · typescript |
✅ | mostly simple (official browser-debug MCP) | Project README |
| 4 | aider | 48.3k | Git-aware CLI pair programmer; edits in-repo, supports multiple models and MCP so agents see version control and tools. mcp · cli · python |
✅ | slightly complex (CLI, git-aware, MCP) | Repo map source |
| 5 | Playwright MCP | 36.2k | Playwright's official MCP server: structured browser control (navigate, click, fill, extract) via the accessibility tree rather than screenshots, so web tasks stay fast and deterministic. mcp · vision · browser · typescript |
✅ | mostly simple (browser MCP) | Setup & config |
| 6 | continue | 35.5k | Open-source IDE extension (VS Code, JetBrains); in-editor completion and chat with local or API models. ide · typescript |
✅ | complex (IDE extension, multi-editor — product suite) | VS Code extension demos |
| 7 | github-mcp-server | 32.3k | GitHub's official MCP server (Go): repos, issues, PRs, code search, Actions. Replaces the older community cyanheads/github-mcp-server as the canonical way to give agents GitHub access. mcp |
✅ | slightly complex (official GitHub MCP) | Remote server toolsets |
| 8 | MCP Python SDK | 24k | Official SDK to build and consume MCP servers/clients in Python; stdio and SSE transports. mcp · python |
✅ | mostly simple (SDK only) | Website fetcher server |
| 9 | MCP TypeScript SDK | 13.2k | Official MCP implementation for Node/TS; reference for the protocol. mcp · typescript |
✅ | mostly simple (protocol reference) | Streamable HTTP server |
| 10 | MCP Inspector | 10.7k | GUI to test and debug MCP servers; inspect tools, resources, and prompts. mcp · typescript |
✅ | super simple (debug GUI) | Inspector UI walkthrough |
| 11 | MCP Registry | 7.2k | Official, community-driven registry for MCP servers—the "app store" MCP clients use to discover servers. Maintained by Anthropic + ecosystem maintainers; v0.1 API frozen, production-grade. mcp |
✅ | slightly complex (official discovery layer) | Registry seed entries |
| 12 | Agent Governance Toolkit | 6k | Microsoft's policy-enforcement layer for autonomous agents: zero-trust identity, execution sandboxing, and OWASP Agentic Top-10 coverage sit in front of the agent loop as a harness security layer—the governance counterpart to Infisical's agent-vault. sandbox · python |
✅ | slightly complex (policy engine, zero-trust, sandboxing) | Project README |
| 13 | mcp-context-forge | 4.3k | IBM's official AI gateway/registry/proxy that sits in front of any MCP, A2A, or REST/gRPC API: unified endpoint, centralized discovery, guardrails, and plugin support—the enterprise front door for harness tool calling. Graduated off the radar this cycle. mcp · python |
❓ | complex (gateway, federation, guardrails — product suite) | Project README |
| 14 | cocoindex-code | 2.6k | Embedded, tree-sitter/AST-based code-search CLI and MCP server that gives coding agents fast semantic lookups over a repo instead of grepping or re-reading whole files into context. mcp · cli |
❓ | mostly simple (embedded CLI + MCP server) | Project README |
| 15 | agent-vault | 2.1k | Infisical's HTTP credential proxy that fronts secrets for Claude Code, OpenClaw, and other agent harnesses so the agent's tool calls never see raw credentials—a harness security layer, not an agent loop itself. | ❓ | mostly simple (credential proxy) | Project README |
| 16 | Docker MCP Gateway | 1.5k | Docker's official MCP CLI plugin / gateway; container-aware MCP tooling from Docker (replaces deprecated docker/mcp-servers path). mcp · sandbox · cli |
✅ | slightly complex (Docker-aware MCPs) | Gateway usage walkthrough |
| 17 | puppeteer-real-browser-mcp | 27 | Puppeteer MCP with real-browser and anti-detection; for agents that need to drive sites that block headless. mcp · browser · typescript |
❓ | mostly simple (real browser, anti-detect) | 11 anti-detection tools |
| 18 | Better-OpenCodeMCP | 9 | MCP server for OpenCode/Crush: async task execution, model bridging (e.g. Claude→Gemini), process pooling. mcp · typescript |
✅ | mostly simple (MCP server, model bridging) | opencode delegate tool |
| 19 | agentlog | 1 | Persistent decision memory for any project: remember, recall, reflect. Single-file Python CLI that stores decisions as JSONL and uses Claude or Gemini to retrieve and synthesize patterns—Karpathy's LLM Wiki concept as a CLI. memory · cli · python |
✅ | super simple (one file, three commands) | Sample decisions.jsonl |
Memory and state
Persistent memory layers that give agents recall across turns and sessions: knowledge graphs, vector stores, and session-capture tools that survive a restart. The state a harness needs but rarely ships with.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | claude-mem | 90.9k | Session-memory plugin for Claude Code, Codex, OpenClaw, Gemini, Copilot, and more: captures everything an agent does during a session, AI-compresses it, and injects the relevant context into future sessions. Session-to-session memory as a drop-in. memory |
✅ | slightly complex (session capture + compression) | Lifecycle hooks config |
| 2 | Mem0 | 63.4k | Universal memory layer for AI agents: stores user/org/session memory, retrieves on demand. Apache-2.0; the de-facto memory primitive paired with most harnesses in 2026. memory · python |
✅ | slightly complex (memory layer, multi-platform) | Next.js memory demo |
| 3 | cognee | 30.1k | Open-source memory layer for agents: an extract–cognify–load pipeline that turns your data into a queryable knowledge graph plus vector store, so agents recall facts and relationships across sessions instead of re-reading context. memory · rag · workflow · python |
✅ | slightly complex (graph + vector memory) | Quickstart |
| 4 | Graphiti (Zep) | 30k | Zep's open-source memory engine: real-time temporal knowledge graphs that track how facts about users and entities change over time, so agents can answer "what was true when." The layer behind Zep's hosted memory platform. memory · rag · workflow · python |
✅ | slightly complex (temporal knowledge graph) | Temporal graph quickstart |
| 5 | beads | 26.4k | Portable persistent-memory layer for coding agents: tracks decisions and task state outside the harness's own context window so it survives session resets and model swaps. memory |
❓ | mostly simple (portable memory store) | Project README |
Evaluation and benchmarking harnesses
Agentic eval systems, reasoning benchmarks, and open agent benchmarks.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | Agent Lightning ★ | 17.5k | Microsoft's training-oriented harness: optimization loops for agent behavior—when you need to improve policies over rollouts, not only score a fixed prompt. evals · training · python |
✅ | complex (agent training, Microsoft stack — product suite) | APO room-booking example |
| 2 | SWE-bench ★ | 5.6k | LMs resolve real GitHub issues; Docker harness, instance IDs; standard for code-agent evals. evals · sandbox · python |
✅ | slightly complex (real GitHub issues, standard) | SWE-bench Verified leaderboard |
| 3 | AgentBench ★ | 3.7k | ICLR'24 benchmark: agents across AlfWorld, DB, knowledge graphs, OS, webshop; Docker Compose, function-calling interface. evals · sandbox · rag · workflow · python |
✅ | complex (multi-env, Docker Compose — product suite) | AgentBench ICLR'24 paper |
| 4 | inspect_ai ★ | 2.6k | Inspect AI core: composable eval tasks, sandboxes, scorers, and multi-model runs; the framework behind inspect_evals, not just the task bundle. evals · sandbox · python |
✅ | complex (eval framework, AISI stack — product suite) | Inspect tutorial example |
| 5 | WebArena ★ | 1.6k | Realistic web env (e.g. e‑commerce, CMS, dev tools); 812 tasks; measures end-to-end web agent success. python |
✅ | complex (812 tasks, web env — product suite) | WebArena leaderboard |
| 6 | WebVoyager ★ | 1.1k | End-to-end web agent with LMMs: screenshots + actions on real sites; benchmark on 15 sites, GPT-4V for automatic eval. evals · vision |
✅ | slightly complex (LMMs, screenshots, 15 sites) | 643 web tasks dataset |
| 7 | agent-qa ★ | 843 | Self-improving QA harness for web and mobile apps: natural-language tests, memory-backed self-healing, dashboard/CLI, MCP and skills support, plus sandboxed hooks for production regression checks. mcp · memory · sandbox · cli · typescript |
⚠️ FSL-1.1-ALv2 | slightly complex (web/mobile QA, memory, MCP) | Natural-language QA harness |
| 8 | swe-smith ★ | 742 | Data generation for SWE agents; 50k+ instances across 128 repos; used for SWE-agent-LM training. training · python |
✅ | slightly complex (50k+ instances, data gen) | SWE-smith trajectories |
| 9 | ARC-AGI-2 | 733 | ARC Prize task set: grid-based abstraction/reasoning; public and private splits for generalization. | ✅ | super simple (task set) | ARC Prize leaderboard |
| 10 | SWE-Gym ★ | 721 | Training and evaluation for SWE agents and verifiers (ICML 2025). evals · training · python |
✅ | slightly complex (training + eval, ICML) | SWE-Gym ICML 2025 paper |
| 11 | inspect_evals ★ | 627 | UK AISI/Arcadia/Vector: GAIA and other evals in Inspect AI; level 1–3, sandboxed, tool-calling solvers. evals · sandbox |
✅ | slightly complex (Inspect AI, UK gov) | inspect SWE-bench eval |
| 12 | Terminal-Bench ★ | 499 | The terminal-task benchmark coding agents now cite next to SWE-bench: hard, containerized terminal tasks scored end to end. Terminal-Bench 2.0 runs on the harbor evaluation framework; the 1.0 tasks live on in the org's terminal-bench-1 repo. evals · cli · python |
✅ | slightly complex (containerized terminal tasks) | Terminal-Bench leaderboard |
| 13 | arc-agi-benchmarking ★ | 362 | Runner for ARC-AGI: multi-provider (OpenAI, Anthropic, Gemini, etc.), rate limits, retries, and scoring. evals · provider-agnostic · python |
✅ | mostly simple (runner, multi-provider) | o3 prompt example |
| 14 | VitaBench ★ | 164 | ICLR'26: 66 tools, real-world apps (delivery, travel, retail); 100 cross-scenario + 300 single-scenario tasks; adopted by Qwen/Seed. | ✅ | complex (66 tools, cross-scenario — product suite) | VitaBench paper |
| 15 | AgencyBench ★ | 93 | Long-horizon agent benchmark: 32 scenarios, 138 tasks, ~1M tokens and ~90 tool calls; Docker sandbox and rubric-based + LLM judges. evals · sandbox · python |
✅ | complex (32 scenarios, Docker, judges — product suite) | AgencyBench leaderboard |
| 16 | letta-evals ★ | 83 | Eval harness for stateful Letta agents; configurable suites and grading (LLM or rule-based) so you can measure what you ship. memory · python |
✅ | mostly simple (Letta-specific harness) | LoCoMo memory benchmark |
| 17 | SUPER ★ | 58 | Agents that set up and run ML/NLP from GitHub repos; 45 expert problems, 152 masked tasks, 602 AutoGen tasks; Docker-based. sandbox · python |
✅ | slightly complex (ML/NLP repos, Docker) | SUPER EMNLP paper |
| 18 | TRAIL | 22 | Trace reasoning and agentic issue localization; 148 long-context traces, 841 errors, 20+ error types; Hugging Face dataset. | ✅ | mostly simple (traces, Hugging Face) | TRAIL dataset card |
Observability and eval-ops
Tracing, monitoring, and production evaluation for live agent runs: capture every step, tool call, and token, then score and debug in the loop. Distinct from the fixed-task benchmarks above—this is what you run against your own traffic.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | Langfuse | 33.2k | Open-source LLM engineering platform: full-trace observability, online and offline evals, prompt management, and cost metrics for agent runs in production—the monitoring layer most harnesses lack out of the box. evals · typescript |
✅ | slightly complex (tracing + evals platform) | Docs |
| 2 | MLflow | 27.5k | Mature ML platform now covering GenAI: MLflow Tracing captures every agent step, tool call, and token, with built-in LLM evals and prompt versioning—observability for teams already standardized on MLflow. evals · python |
✅ | complex (full ML + GenAI platform) | Docs |
| 3 | Opik | 21.4k | Comet's open-source agent observability and evaluation platform: tracing, scoring, and experiment comparison with the whole core feature set free to self-host under Apache-2.0. evals · python |
✅ | slightly complex (tracing + evals platform) | Docs |
| 4 | Arize Phoenix | 11.1k | Arize's source-available, local-first tracing and eval layer: run it on your laptop or your own infra, and graduate to the managed Arize AX platform only when you need it. evals · python |
⚠️ Elastic-2.0 | slightly complex (local-first tracing + evals) | Docs |
Research and task-specific harnesses
Deep research, document QA, and domain-specific agent loops.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | DeerFlow ★ | 80.1k | ByteDance's long-horizon research harness: a LangGraph-based agent loop that researches, codes, and creates using sandboxes, memory, tools, and subagents behind a message gateway—an alternative to the reference gpt-researcher stack for multi-hour tasks. memory · multi-agent · sandbox · python |
✅ | complex (sandboxes, memory, subagents — product suite) | Project README |
| 2 | gpt-researcher | 29k | Autonomous deep-research agent: web + local sources, citation-grounded reports, multi-agent and deep-research modes. The reference open-source research harness. multi-agent · python |
✅ | complex (deep research, multi-agent — product suite) | Multi-agent LangGraph walkthrough |
| 3 | AutoResearchClaw | 14k | Fully autonomous, self-evolving research harness: multi-agent debate and citation verification carry a project from idea to a written paper without a human in the loop. multi-agent |
❓ | complex (autonomous research, multi-agent debate — product suite) | Project README |
| 4 | MiroThinker ★ | 8.4k | Deep-research harness tuned for long browsing-and-reasoning chains; benchmarked on BrowseComp, GAIA, and HLE by pairing a dedicated agent loop with its own MiroThinker models rather than bolting search onto a generic chat agent. evals |
❓ | slightly complex (benchmark-tuned research loop) | Project README |
| 5 | openagents ★ | 446 | Platform for autonomous agents and autopilot-style workflows; decentralized/Nostr-oriented (Pylon runtime, actively shipped in 2026). | ✅ | complex (platform, decentralized — product suite) | Production earning proof |
Libraries and SDKs
Lightweight runtimes, tool loops, and provider-agnostic harness primitives.
| # | Project | ⭐ Stars | Description | Open source | Simplicity ↔ capability | Examples |
|---|---|---|---|---|---|---|
| 1 | Daytona | 72k | Elastic dev environments for AI-generated code: workspaces, Git, previews—infra harness between "the model wrote a patch" and "it ran in a real machine." ⚠️ Public repo unmaintained since June 2026: core development moved to a private codebase (final open release v0.190.0, AGPL-3.0). sandbox |
✅ | slightly complex (dev env API, isolation) | Charts in sandbox |
| 2 | LiteLLM | 56.5k | One interface to 100+ LLMs; routing, caching, budgets. Not an agent framework—the pipe every agent framework uses. provider-agnostic · python |
✅ | mostly simple (LLM pipe only) | Anthropic Agent SDK gateway |
| 3 | Composio | 29.7k | 1,000+ toolkits with auth, tool search, and a sandboxed workbench—drop-in tool layer so agents stop reinventing OAuth + integrations. Python and TypeScript. sandbox · tool-discovery · python · typescript |
✅ | complex (1k+ tools, auth, search — product suite) | HackerNews agent quickstart |
| 4 | smolagents | 28.8k | Code-as-action agents: model outputs Python executed in sandbox (E2B, Modal, etc.); ~1k LOC core. sandbox · python |
✅ | mostly simple (code-as-action, ~1k LOC) | RAG code agent |
| 5 | deepagents ✱ | 27.8k | LangChain's Python+TypeScript agent harness on top of LangGraph: planning tool, virtual filesystem, shell sandbox, sub-agent spawning—the "Claude Code-style" harness as a reusable library. multi-agent · sandbox · python · typescript |
✅ | slightly complex (planning, files, sub-agents) | Deep research agent |
| 6 | vercel/ai | 26.2k | React and Node SDK for streaming, tool calls, and agent-style UIs; provider-agnostic. provider-agnostic · typescript |
✅ | slightly complex (React/Node SDK, provider-agnostic) | Next.js agent example |
| 7 | pydantic-ai ✱ | 19.3k | Type-safe Python agents with Pydantic I/O; multi-provider, MCP, Logfire observability, and human-in-the-loop. mcp · typed · provider-agnostic · python |
✅ | slightly complex (type-safe, MCP, Logfire) | Bank support agent |
| 8 | E2B | 13.4k | Firecracker sandboxes for executing agent-generated code; the hosted isolation layer many tool-calling demos use instead of running arbitrary LLM output on your laptop. sandbox · python |
✅ | slightly complex (sandbox API, code execution) | Claude Code in sandbox |
| 9 | Steel | 7.5k | Open-source browser API for agents: cloud or self-hosted Chrome sessions with stealth, residential proxies, CAPTCHA solving, and persistent profiles. The only open-source core in the hosted browser-infrastructure lane (Browserbase and Hyperbrowser are closed). memory · browser · local |
✅ | slightly complex (browser sessions API, self-hostable) | Sessions API docs |
| 10 | strands-agents | 6.9k | Model-driven Python SDK; decorators for tools, native MCP, multi-agent; "minimal code" without sacrificing provider choice. mcp · multi-agent · typed · python |
✅ | mostly simple (decorators, MCP, minimal code) | First agent tutorial |
| 11 | Cloudflare Agents ★ ✱ | 5.4k | Persistent, stateful agents on Durable Objects: state, websockets, scheduling, and AI chat baked in. The serverless answer to "where does the agent live?" memory · typescript |
✅ | slightly complex (Durable Objects, stateful) | SDK playground app |
| 12 | openai-agents-js | 3.6k | Official OpenAI Agents SDK for Node/TS: handoffs, guardrails, voice; the JS counterpart to openai-agents-python. multi-agent · voice · typescript |
✅ | slightly complex (handoffs, guardrails, voice) | Financial research agent |
| 13 | Agent Sandbox | 3.5k | Kubernetes-native sandbox primitive for agent runtimes: a Sandbox resource plus warm pools and claims for fast-start, isolated, stateful workloads. The self-hosted answer to hosted sandbox APIs, from the Kubernetes SIGs org. memory · sandbox · local |
✅ | slightly complex (Kubernetes resource, warm pools) | Sandbox resource quickstart |
| 14 | open-harness | 598 | TypeScript Agent class on Vercel AI SDK; streaming events, filesystem/bash tools, MCP, and subagent delegation. mcp · multi-agent · typescript |
✅ | slightly complex (streaming, tools, subagents) | Terminal CLI agent |
| 15 | Community-curated agent lists | 15 | Broader directories: e.g. brandonhimpfen/awesome-ai-agents, axioma-ai-labs/awesome-ai-agent-frameworks, mb-mal/awesome-ai-agents-frameworks—differ by scope and update cadence. | ❓ | super simple (curated lists) | Frameworks section |
⚰️ Graveyard
Archived upstream, or flagged for curation integrity (e.g. suspected star manipulation). Kept here — not deleted — for citation and transparency; excluded from the ranked count, the landscape chart, and harnesses.json's main list. Curation is the point: a starred repo is not automatically a credible one.
| Project | Last ⭐ Stars | Since | Why it's here |
|---|---|---|---|
| everything-claude-code | 240k | 2026-07-11 | 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 |
| Flowise | 55.4k | 2026-08-16 | archived upstream — kept for citation |
| spring-ai-tool-search-tool | 78 | 2026-07-03 | archived upstream — kept for citation |
| coderClaw | 3 | 2026-07-03 | archived upstream — kept for citation |
🔭 On the radar
Up-and-coming candidates — surfaced by the weekly discovery scan or submitted by the community — that haven't cleared the curation bar or a vetting pass yet. Stars refresh weekly from the discovery queue; descriptions are the projects' own, unvetted. Entries graduate into the ranked list above or drop off.
| Project | ⭐ Stars | What it says it is | Via |
|---|---|---|---|
| agenticSeek | 26.9k | 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. | weekly discovery |
| openfang | 18.1k | Open-source Agent Operating System | weekly discovery |
| evolver | 9k | The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai | weekly discovery |
| openevolve | 7.2k | Open-source implementation of AlphaEvolve | weekly discovery |
| open-multi-agent | 6.8k | TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it… | weekly discovery |
| intentkit | 6.5k | IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you. | weekly discovery |
| vibesdk | 5.3k | An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack | weekly discovery |
| agentscope-java | 5.1k | Build distributed, production-grade, long-running agents. | weekly discovery |
| eko | 4.9k | Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai | weekly discovery |
| fast-agent | 3.9k | Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support | weekly discovery |
| MIRIX | 3.4k | Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data… | weekly discovery |
| antigravity-cli | 1.9k | Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal. | weekly discovery |
| teamcopilot | 14 | Deploy AI agents for your team to automate business workflows and coding. | community · PR #21 |
FAQ
Which agent harnesses can run unattended (headless)?
Harnesses designed for unattended runs, batches, and fleets: opencode, OpenHands, goose, Symphony, SWE-agent, Claude Agent SDK, RepoMaster, OpenClaw.
Which agent harnesses survive a crash mid-task (durable)?
Harnesses whose execution state persists across restarts: langgraph-bigtool, n8n, langgraph, mastra, letta, deepagents, pydantic-ai, Cloudflare Agents.
How many of these agent harnesses are open source?
118 of 160 carry a standard open-source license; the rest are source-available or unclear, and flagged per row.
What is an agent harness?
The runtime that turns a model into an agent: it decides what the model's reasoning is allowed to touch, and supplies the orchestration, tool wiring, memory, error recovery, and guardrails around per-turn inference.
How is this list ranked?
By relevance to harness concerns (environment, orchestration, lifecycle, guardrails) and by GitHub stars (captured 2026-08-16); each project also carries an adoption-surface tier and autonomy/recovery scores.
How can an AI agent use this list directly?
Three machine-readable surfaces: harnesses.json (structured), llms.txt (one file), and an MCP server (uvx agent-harnesses-mcp) exposing recommend, compare, pick_harness, and search_harnesses.
Related Resources
- Awesome: Awesome lists on many topics
- OpenAI – Harness engineering: Environment design, intent, feedback loops, repo-as-system-of-record
- Anthropic – Effective harnesses for long-running agents: Session bridging, feature lists, incremental progress, testing
- Aakash Gupta (Medium) – 2026 is agent harnesses: Harness as moat, minimal intervention, progressive disclosure
- LangChain, Anthropic, OpenAI: Official docs for major agent platforms
🧡 Thank you, contributors
The people who stopped mid-scroll, found a gap, and wrote it up — this list is better for each of them:
@baskduf — harness-starter-kit · @ahwurm — LocalHarness · @liviux — LoopTroop · @rishabhpoddar — TeamCopilot, on the radar · @oldschoola — oh-my-pi · @pranshuchittora — agent-qa · @claudiusthebot — Talon · @madarco — AgentBox · @jmthomasofficial — JMT x402 Agent Tools · @ShukantPal — Proliferate · @hjqcan — GoodMemory · @777genius — Agent Teams AI · @S1LV3RJ1NX — mcp-guardian · @AmariahAK — Atlarix · @hardness1020 — awesome-agent-architecture · @razzant — Claudexor, Ouroboros · @allenshi16 — Nexus AI Pulse, HomeOffice AI · @ryanpettry — fractal · @reacher-z — ClawBench evaluation harness · @HelpMatey — Pin mcp2 · @rxdt — L∞pGate · @msaleme — red-team-blue-team-agent-fabric · @JackChen-me — Open Multi-Agent · @Q00 — Ouroboros · @danawoodman — PR #78 · @JanYork — LWC Local Wiki CLI · @labmimors — MCP Lens
Accepted submissions land with co-author credit on the commit that ships them. Promising projects that are still early aren't turned away — they get pinned to 🔭 On the radar and graduate as they grow. Add yours →
Contribution
Contributions are welcome. To add or suggest projects:
- Open an issue with the repo URL, category, and a short description.
- Or submit a pull request against scripts/generate.py — this README, projects.yaml, and TAGS.md are generated from it, so direct edits to them can't merge.
Promising projects that don't clear the curation bar yet get pinned to 🔭 On the radar — a submission that lands there isn't rejected, it's queued.
For contribution guidelines, see CONTRIBUTING.md and the Code of Conduct.
Show your listing
If your project is in this list, you're welcome to show it in your README:
[](https://github.com/RyanAlberts/best-of-Agent-Harnesses)
License
