Best of Agent Harnesses

Browse all 167

Categories

Pick by use case

• I want a turnkey coding agent today — opencode, Cline, Codex, Gemini CLI, OpenHands
• I want an always-on personal agent that lives in my chat apps — OpenClaw, Hermes, Khoj, Agent Zero, OpenHarness (HKUDS)
• I want to extend Claude Code, Codex, or OpenCode with skills and slash commands — Anthropic Skills, wshobson/agents, superpowers, GStack, pmstack
• I want to build my own coding harness from scratch — Claude Agent SDK, Google ADK, AutoHarness, SWE-agent, RepoMaster
• I want a drop-in memory layer for agents — Mem0, Graphiti (Zep), claude-mem, agentlog, letta
• I want to plug hundreds to thousands of tools without context bloat — MCP-Zero, ToolGen, ToolRAG, langgraph-bigtool
• I want multi-agent orchestration — openai-agents-python, crewAI, autogen, Microsoft Agent Framework, PraisonAI
• I want a general LLM app framework — langgraph, langchain, llama-index, pydantic-ai, agno
• I want low-code / visual workflows — langflow, Flowise, Dify, n8n
• I want browser-using agents — browser-use, Stagehand, WebVoyager, puppeteer-real-browser-mcp
• I want sandboxed code execution for agent-generated code — E2B, Agent Sandbox, Daytona, smolagents, OpenHands
• I want to evaluate or benchmark agents — SWE-bench, Terminal-Bench, AgencyBench, inspect_ai, WebArena
• I want a deep research / autonomous research agent — deepagents, gpt-researcher, openagents
• I want a provider-agnostic LLM pipe (not a framework) — LiteLLM, vercel/ai

Decision guides

• Agent evals: SWE-bench vs inspect_ai vs Terminal-Bench — You changed your agent: new model, new prompt, new tools. Did it get better or worse? An eval is how you answer that with a number instead o
• The best AI agent harnesses in 2026, ranked by category — These are the top three agent harnesses in each of the 12 categories of best-of-Agent-Harnesses, a hand-curated list of 167 harnesses re-ran
• Browser agents: browser-use vs Stagehand vs Playwright MCP vs chrome-devtools-mcp — "Browser agent" covers three different kinds of product, and most bad picks here come from comparing across the lanes instead of within one.
• Browser infrastructure for agents: Browserbase vs Steel vs Hyperbrowser — Agent libraries like browser-use and Stagehand decide what to click; something still has to run the browsers they click in. At small scale t
• Claude Code skill packs: superpowers vs GStack vs get-shit-done vs Anthropic Skills — A skill is a folder of instructions (a SKILL.md file, plus any scripts it needs) that a coding agent loads only when the task matches, inste
• Eval and observability platforms: Langfuse vs LangSmith vs Braintrust vs Phoenix — Benchmarks tell you how a model ranks; your production agent still fails in ways no public exam covers. An eval and observability platform i
• How to pick a harness — This is the decision guide for [best-of-Agent-Harnesses](../README.md), a curated, ranked list of the runtimes that turn an AI model into a
• How to test-drive a harness — Spec sheets cannot answer "which harness should I use," because an agent's performance is a property of the *pairing* between harness and mo
• Managed vs self-hosted always-on agents — An always-on agent keeps working between your messages, and in 2026 you can rent one (Grok Bot, Claude Managed Agents), run one for your who
• Agent memory layers: Mem0 vs Zep vs Letta vs claude-mem — Agents forget. A model keeps nothing between sessions, so anything your agent should still know tomorrow (who the user is, what was decided,
• Multi-agent orchestration: OpenAI Agents SDK vs CrewAI vs AutoGen vs Agent Framework vs LangGraph — Orchestration is the layer that coordinates several AI agents working on one job: who acts next, what they share, and what happens when a st
• OpenClaw vs Hermes: the always-on personal-agent debate — An always-on personal agent is a program that runs all day on your own machine, talks to you through the chat apps you already use (WhatsApp
• Context files for agents: AGENTS.md vs CLAUDE.md vs skills vs MCP tool search — A model has a context window: a fixed amount of text it can consider at once. Everything competes for that space: your instructions, the def
• Agent sandboxing: what it is and how to pick — An AI agent does not just suggest code. It runs code, opens web pages, and edits files on a real computer. Agent sandboxing means making tha
• Terminal coding agents: opencode vs Codex vs Gemini CLI vs crush vs goose — The most-asked pick in this list: *"I want a turnkey coding agent in my terminal today."* A terminal coding agent is a program you run in yo
• Why the harness matters more than the model — The same model weights score about 30% on ARC-AGI-3 as a bare model and 95.5% inside a good harness, and that gap is the number agent builde

FAQ

• Which agent harnesses can run unattended (headless)?
• Which agent harnesses survive a crash mid-task (durable)?
• How many of these agent harnesses are open source?
• What is an agent harness?
• Does the harness matter more than the model?
• Is Grok Bot an agent harness?
• How is this list ranked?
• How can an AI agent use this list directly?

All questions →

For agents

This list is published machine-readable so coding and research agents can recommend harnesses directly:

• harnesses.json — every project with tier, tags, axes, license, example, and use-case index.
• llms.txt — the whole list in one agent-readable file.
• llms-full.txt: llms.txt plus the full text of every decision guide, one file.
• harnesses.jsonld — schema.org Dataset + ItemList.
• feed.json — JSON Feed of refreshes.
• MCP server: uvx agent-harnesses-mcp — pick_harness, search_harnesses, get_harness, comparisons.