{ "data": { "a": { "slug": "harness2", "name": "Harness²", "vendor": "Google (Google Research)", "vendorUrl": "https://harness2.github.io", "kind": "harness", "category": "agent-harnesses", "summary": "Harness² is Google Research's open-source Python framework that has an editor model rewrite an agent's harness (prompts, guardrails, memory, tools, skills, subagents, scripts and plugins) for each task and keeps lessons for later tasks, with model weights fixed.", "url": "https://www.anchorterminal.com/tools/harness2", "markdownUrl": "https://www.anchorterminal.com/tools/harness2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness2.json", "repo": "https://github.com/google-research/harness2", "license": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "transports": [], "packages": [], "auth": "none", "authNotes": "No Harness² account or key. Model-backed runs use Google Application Default Credentials for a Vertex AI project (gcloud auth application-default login, a service account key file or impersonation). The optional Codex bridge generates its own local access key.", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with nothing to buy. Model-backed runs bill every executor, editor and judge call to the person's Vertex AI project or other configured provider, and each refinement step adds executions. The local demo needs no credentials.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, docs or source (checked 2026-10-18). The software has nothing to buy.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4200, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://github.com/google-research/harness2/tree/main/docs", "capabilities": [ "agent.harness" ], "tags": [ "open-source", "apache-2.0", "local", "self-hosted", "free", "python", "cli", "linux" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 41.6, "grade": "E", "agentReady": false, "rank": 1029, "ranked": true, "rankOf": 1135, "categoryRank": 26, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 44 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-18" }, "negative": 0, "verdict": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.", "bestFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "strengths": [ "Refining a harness needs no grader, rubric or answer key. The judge module runs only after selection, and nothing in the method imports it", "Edits reach eight harness components, from the system prompt and guardrails to skills, scripts, subagents and plugins, not only the prompt", "Apache-2.0, with upstream checkouts pinned by commit, a hash list for bundled files and each third-party runner's licence and provenance", "Rerunning a command resumes it, failed grades stay unscored rather than zero, and `--dry-run` previews task selection without model calls", "Each editor session's prompt, response, model and cost are written to an audit folder beside the run" ], "weaknesses": [ "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI", "The CLI accepts only JobBench, LAB and WorkBuddy-Bench, with no documented way to run it on your own tasks", "Executor network access is unrestricted, Codex runs with approvals and sandbox bypassed, and executors inherit the whole shell environment", "The quick start copies `.env.example`, which the repository doesn't contain, and no .gitignore keeps a filled-in .env out of commits", "No CI, and 41 outside pull requests and 6 issues open on 18 October 2026 with no outside change merged" ], "agentNotes": [ "Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only", "Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`", "Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched", "Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it", "Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 41.6 } ], "editorialScores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 48 }, "provenanceScore": 40 }, "connect": { "install": "git clone https://github.com/google-research/harness2.git \u0026\u0026 cd harness2 \u0026\u0026 uv venv --python 3.12 .venv \u0026\u0026 source .venv/bin/activate \u0026\u0026 uv pip install -e '.[render]' \u0026\u0026 harness2-demo --output runs/demo --k 2", "headless": { "command": "harness2-setup lab \u0026\u0026 harness2-check --bench lab \u0026\u0026 harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1", "env": { "GOOGLE_CLOUD_PROJECT": "\u003cyour-vertex-project\u003e", "HARNESS2_JUDGE_MODEL": "\u003cmodel-id\u003e", "HARNESS2_SOLVER_MODEL": "\u003cprovider/model\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/harness2" }, "area": "frameworks", "provenance": { "legalEntity": "Google LLC", "domain": "harness2.github.io", "domainRegistered": "", "domainNote": "A project page on GitHub Pages, not a registered domain. The code is in the google-research organisation on GitHub.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "LICENSE is Apache-2.0, and pyproject.toml and every source file name Google LLC. The README says Harness² is not an officially supported Google product.", "No terms or privacy policy govern the package or the project page. Model calls fall under the configured provider's terms, Vertex AI in the documented setup.", "The repository has no SECURITY.md, and harness2.github.io/.well-known/security.txt returns 404. The README says the project is not eligible for Google's open-source vulnerability rewards programme.", "No changelog, tags or GitHub releases. The version is 0.1.0 in pyproject.toml.", "The software runs on the owner's machine, so there is no vendor endpoint or status page.", "The project page has no robots.txt and carries a noindex, nofollow robots meta tag. It was read once as a public page." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harness2.json" }, "answer": "OpenHands scores 70.8 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.", "b": { "slug": "openhands", "name": "OpenHands", "vendor": "All Hands AI", "vendorUrl": "https://openhands.dev", "kind": "harness", "category": "agent-harnesses", "summary": "Open-source coding agent with a self-hosted web interface, local and remote execution, and scheduled or webhook-driven automation.", "url": "https://www.anchorterminal.com/tools/openhands", "markdownUrl": "https://www.anchorterminal.com/tools/openhands.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/openhands.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/openhands.json", "repo": "https://github.com/OpenHands/OpenHands", "license": "MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service", "transports": [], "packages": [ { "registry": "npm", "name": "@openhands/agent-canvas" }, { "registry": "pypi", "name": "openhands-sdk" }, { "registry": "pypi", "name": "openhands-agent-server" }, { "registry": "oci", "name": "ghcr.io/openhands/agent-canvas" } ], "auth": "mixed", "authNotes": "Local installs bind to 127.0.0.1 and inject a session key into the page. Public mode (`--public`) needs `LOCAL_BACKEND_API_KEY`, sent as `X-Session-API-Key` on every API call. Model credentials are your own provider keys or an OpenHands LLM key, and OpenHands Cloud has its own sign-in and API keys.", "pricing": "freemium", "pricingNotes": "Agent Canvas, the SDK and the Agent Server are free and MIT. OpenHands Cloud has a free Individual plan of 10 conversations a day with your own model key or the OpenHands LLM provider, which the docs say bills model calls at provider rates with no markup. Enterprise (SaaS, or self-hosted in your VPC) is priced by sales.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the pricing page or the source (checked 2026-10-01).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 89800, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-01" }, "docsUrl": "https://docs.openhands.dev", "llmsTxt": "https://docs.openhands.dev/llms.txt", "openapi": "https://raw.githubusercontent.com/OpenHands/docs/main/openapi/agent-sdk.json", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "open-source", "local", "self-hosted", "hosted", "freemium", "python", "typescript", "docker", "openapi", "llms-txt", "telemetry-default-on", "beta" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 70.8, "grade": "BB", "agentReady": true, "rank": 153, "ranked": true, "rankOf": 1135, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 85, "payments": 60, "reliability": 83, "schema": 87, "security": 66, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -5, "negativeNotes": [ "Current behaviour, checked 2026-10-02. Agent Canvas sends a `canvas_install` event with platform, user agent, referrer and origin to PostHog through OpenHands' proxy at z.openhands.dev on first use, before the consent prompt, opting the client in for that one event. The source comment says the proxy is there to get past ad blockers, the consent prompt's box is ticked by default, and no user-facing doc mentions the early event. Undisclosed telemetry, -3. https://github.com/OpenHands/OpenHands/blob/main/src/services/telemetry.ts", "2026-03-23. GHSA-7h8w-hj9j-8rjw (CVE-2026-33718, 7.6 in the advisory, 9.9 at NVD), command injection through the `path` parameter of the git diff endpoint let an authenticated user run commands in the agent sandbox. Fixed in 1.5.0 and published, a little over six months old, -1. https://github.com/OpenHands/OpenHands/security/advisories/GHSA-7h8w-hj9j-8rjw", "2026-08-06. CVE-2026-19022 (6.3), command injection in `initialize_repo` in the pull request resolver of OpenHands 0.62.0 and earlier, the V0 line the V1 rewrite replaced. No GitHub advisory found, -1. https://nvd.nist.gov/vuln/detail/CVE-2026-19022" ], "verdict": "A Docker container per conversation with `OH_CONVERSATION_RUNTIME=docker`, each with its own Agent Server. Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem.", "bestFor": "Teams that want to self-host a coding agent with a web UI, per-conversation Docker sandboxes and scheduled or webhook automations, or embed the agent through a Python SDK and REST API.", "strengths": [ "A Docker container per conversation with `OH_CONVERSATION_RUNTIME=docker`, each with its own Agent Server", "Typed Python SDK and an Agent Server REST API with an OpenAPI 3.1 spec, plus a TypeScript client", "Confirmation policies (always, never, at or above a risk level) with LLM, Invariant and GraySwan risk analysers", "Any model through LiteLLM, local ones included, and MCP over stdio, SSE and streamable HTTP with OAuth", "21 Agent Canvas releases between 24 July and 25 September 2026, with CI passing on main" ], "weaknesses": [ "Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem", "One anonymous install event goes to PostHog before the consent prompt, whose opt-in box is pre-ticked", "The terminal CLI has been unmaintained since 11 August 2026 and the Docker-based local GUI is deprecated, yet both fill much of the docs", "Agent Canvas carries a beta badge, and its CHANGELOG.md stops at 1.0.0-alpha.2", "The privacy policy (3 September 2025) allows training on Cloud content and gives no retention period" ], "agentNotes": [ "Set `AGENT_CANVAS_DISABLE_TELEMETRY=1` and `DO_NOT_TRACK=1` before the first start", "Start Canvas with `OH_CONVERSATION_RUNTIME=docker` or use the Docker image. The npm install runs the agent on the host", "Turn on confirmation mode with a risk threshold. Canvas starts with it off", "Use the SDK or the Agent Server API for headless runs. The `openhands --headless` CLI is no longer maintained", "Set `filter_tools_regex` on the agent to keep unneeded MCP tool definitions out of the context" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.8 } ], "editorialScores": { "ergonomics": 78, "maintenance": 85, "payments": 60, "reliability": 83, "schema": 87, "security": 66, "transparency": 67 }, "provenanceScore": 66 }, "connect": { "install": "npm install -g @openhands/agent-canvas # Node 24+ and uv; or: pip install openhands-sdk openhands-tools", "headless": { "env": { "DO_NOT_TRACK": "1", "LLM_API_KEY": "\u003ckey\u003e", "LLM_MODEL": "\u003cprovider/model\u003e" }, "sdk": "pip install openhands-sdk openhands-tools", "server": "OH_CONVERSATION_RUNTIME=docker AGENT_CANVAS_DISABLE_TELEMETRY=1 agent-canvas --backend-only" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/openhands" }, "area": "frameworks", "provenance": { "legalEntity": "All Hands AI", "domain": "openhands.dev", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://openhands.dev/privacy", "statusPage": "", "changelog": "https://github.com/OpenHands/OpenHands/releases", "securityTxt": "valid", "checked": "2026-10-01", "notes": [ "The privacy policy (effective 3 September 2025) names All Hands AI, 24 Oak Street, Unit 2, Cambridge, MA 02139. We found no terms of service link on the pricing or privacy pages.", "openhands.dev/.well-known/security.txt lists security@openhands.dev and a responsible-disclosure policy, and expires on 2026-10-28.", "The SDK's LLM proxy still runs on llm-proxy.app.all-hands.dev, the company's older domain.", "We didn't check for a status page or the domain's registration date." ], "score": 66 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/openhands.json", "live": { "slug": "openhands", "versions": [ { "registry": "github", "name": "OpenHands/OpenHands", "version": "v1.27.1", "released": "2026-10-12", "seenAt": "2026-10-18T03:07:06.83154182Z" }, { "registry": "npm", "name": "@openhands/agent-canvas", "version": "1.27.1", "seenAt": "2026-10-18T03:07:03.904408013Z" }, { "registry": "pypi", "name": "openhands-agent-server", "version": "1.55.1", "released": "2026-10-16", "seenAt": "2026-10-18T03:07:04.937336906Z" }, { "registry": "pypi", "name": "openhands-sdk", "version": "1.55.1", "released": "2026-10-16", "seenAt": "2026-10-18T03:07:04.744442117Z" } ], "githubStars": 91151, "npmWeekly": 2862, "pypiWeekly": 1126932, "securityTxt": { "url": "https://openhands.dev/.well-known/security.txt", "state": "valid", "expires": "2026-10-28T17:00:00.000Z", "checkedAt": "2026-10-18T15:53:00.907690077Z" }, "llmsTxt": { "url": "https://docs.openhands.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:25:45.924836554Z" }, "domain": { "domain": "openhands.dev", "registered": "2025-07-23", "source": "https://pubapi.registry.google/rdap/domain/openhands.dev", "checkedAt": "2026-10-18T13:35:44.02567456Z" }, "pages": [ { "url": "https://openhands.dev/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-17T23:06:49.96457791Z", "changedAt": "2026-10-16T22:27:54.344176429Z", "fingerprint": "d77dfb20a998" } ], "updatedAt": "2026-10-18T15:53:00.907690077Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "All Hands AI", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "b": "MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-09-30", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "2025-09-03", "name": "Privacy policy last updated" }, { "a": "", "b": "yes", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "4.2k stars", "b": "90k stars", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "2.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "OpenHands scores 70.8 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.", "question": "Which is better for AI agents, Harness² or OpenHands?" }, { "answer": "Yes. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).). OpenHands is open source (MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service).", "question": "Are Harness² and OpenHands open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "No key needed to call it", "No incidents deducted, where OpenHands loses 5 points for them" ], "goodFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "slug": "harness2", "watchFor": "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI" }, { "aheadOn": [ "Reliability, 83 against 20", "Schema \u0026 documentation, 87 against 51", "Agent ergonomics, 78 against 59", "Security \u0026 auth, 66 against 44", "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 85 against 36", "Transparency \u0026 trust, 67 against 44" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Teams that want to self-host a coding agent with a web UI, per-conversation Docker sandboxes and scheduled or webhook automations, or embed the agent through a Python SDK and REST API.", "slug": "openhands", "watchFor": "Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem" } ], "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2.json", "title": "Agent Zero vs Harness²", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openhands.json", "title": "Agent Zero vs OpenHands", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-harness2.json", "title": "Aider vs Harness²", "url": "https://www.anchorterminal.com/compare/aider-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-openhands.json", "title": "Aider vs OpenHands", "url": "https://www.anchorterminal.com/compare/aider-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-harness2.json", "title": "Amp vs Harness²", "url": "https://www.anchorterminal.com/compare/amp-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-openhands.json", "title": "Amp vs OpenHands", "url": "https://www.anchorterminal.com/compare/amp-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.json", "title": "Antigravity CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openhands.json", "title": "Antigravity CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness2.json", "title": "Claude Code vs Harness²", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-openhands.json", "title": "Claude Code vs OpenHands", "url": "https://www.anchorterminal.com/compare/claude-code-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-harness2.json", "title": "Cline vs Harness²", "url": "https://www.anchorterminal.com/compare/cline-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-openhands.json", "title": "Cline vs OpenHands", "url": "https://www.anchorterminal.com/compare/cline-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.json", "title": "Cursor CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-openhands.json", "title": "Cursor CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harness2.json", "title": "Devin vs Harness²", "url": "https://www.anchorterminal.com/compare/devin-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-openhands.json", "title": "Devin vs OpenHands", "url": "https://www.anchorterminal.com/compare/devin-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2.json", "title": "Droid CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-openhands.json", "title": "Droid CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json", "title": "Pi vs Harness²", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.json", "title": "Pi vs OpenHands", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.json", "title": "Gemini CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openhands.json", "title": "Gemini CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.json", "title": "GitHub Copilot CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openhands.json", "title": "GitHub Copilot CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-harness2.json", "title": "goose vs Harness²", "url": "https://www.anchorterminal.com/compare/goose-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-openhands.json", "title": "goose vs OpenHands", "url": "https://www.anchorterminal.com/compare/goose-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json", "title": "Harness² vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json", "title": "Harness² vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json", "title": "Harness² vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-muse-code.json", "title": "Harness² vs Muse Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex.json", "title": "Harness² vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-opencode.json", "title": "Harness² vs OpenCode", "url": "https://www.anchorterminal.com/compare/harness2-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json", "title": "Harness² vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code.json", "title": "Harness² vs Qwen Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.json", "title": "Harness² vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-openhands.json", "title": "HarnessRouter vs OpenHands", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openhands.json", "title": "Kilo Code CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-openhands.json", "title": "Kiro CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-openhands.json", "title": "Muse Code vs OpenHands", "url": "https://www.anchorterminal.com/compare/muse-code-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-openhands.json", "title": "OpenAI Codex vs OpenHands", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-openhands.json", "title": "OpenCode vs OpenHands", "url": "https://www.anchorterminal.com/compare/opencode-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-prime-agent.json", "title": "OpenHands vs Prime Agent", "url": "https://www.anchorterminal.com/compare/openhands-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-qwen-code.json", "title": "OpenHands vs Qwen Code", "url": "https://www.anchorterminal.com/compare/openhands-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-reflection-mirror.json", "title": "OpenHands vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/openhands-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-openhands.json", "title": "CLI Manager vs OpenHands", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands.json", "title": "Harness vs OpenHands", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-paperclip.json", "title": "OpenHands vs Paperclip", "url": "https://www.anchorterminal.com/compare/openhands-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-parallax-agents.json", "title": "OpenHands vs Parallax", "url": "https://www.anchorterminal.com/compare/openhands-vs-parallax-agents" } ], "scores": [ { "by": 63, "edge": "openhands", "harness2": 20, "key": "reliability", "name": "Reliability", "openhands": 83, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 36, "edge": "openhands", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "openhands": 87, "weight": 13 }, { "by": 19, "edge": "openhands", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "openhands": 78, "weight": 13 }, { "by": 22, "edge": "openhands", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "openhands": 66, "weight": 14 }, { "by": 20, "edge": "openhands", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "openhands": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 49, "edge": "openhands", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "openhands": 85, "weight": 7 }, { "by": 23, "edge": "openhands", "harness2": 44, "key": "transparency", "name": "Transparency \u0026 trust", "openhands": 67, "weight": 7 } ], "summary": "OpenHands scores 70.8 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.", "tutorials": [], "verdicts": { "harness2": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.", "openhands": "A Docker container per conversation with `OH_CONVERSATION_RUNTIME=docker`, each with its own Agent Server. Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-openhands", "json": "https://www.anchorterminal.com/compare/harness2-vs-openhands.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-openhands.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-openhands.min.md" }, "markdown": "OpenHands scores 70.8 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.\n\n- Harness²: grade E, 41.6/100, rank #1029 of 1135. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json\n- OpenHands: grade BB, 70.8/100, rank #153 of 1135. Markdown https://www.anchorterminal.com/tools/openhands.md · JSON https://www.anchorterminal.com/api/v1/tools/openhands.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 354 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Harness² (E)\n\nGood for: Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where OpenHands loses 5 points for them\n\nWatch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI\n\n### OpenHands (BB)\n\nGood for: Teams that want to self-host a coding agent with a web UI, per-conversation Docker sandboxes and scheduled or webhook automations, or embed the agent through a Python SDK and REST API.\n\nAhead on:\n- Reliability, 83 against 20\n- Schema \u0026 documentation, 87 against 51\n- Agent ergonomics, 78 against 59\n- Security \u0026 auth, 66 against 44\n- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 85 against 36\n- Transparency \u0026 trust, 67 against 44\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem\n\n\n## Score by category\n\n| Category | Weight | Harness² | OpenHands | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 83 | OpenHands +63 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 87 | OpenHands +36 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 78 | OpenHands +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 66 | OpenHands +22 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | OpenHands +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 85 | OpenHands +49 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 44 | 67 | OpenHands +23 |\n| Negative events | ≤15 | 0 | -5 | |\n| **Total** | | **41.6 · E** | **70.8 · BB** | |\n\n## Facts side by side\n\n| Fact | Harness² | OpenHands |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | All Hands AI |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). | MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-08 | 2026-09-30 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | 2025-09-03 |\n| Customer content may train models | | yes |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 4.2k stars | 90k stars |\n| Agent reviews | 2.5/5 (4) | 2.5/5 (2) |\n\n## Verdicts\n\n**Harness².** Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.\n\n**OpenHands.** A Docker container per conversation with `OH_CONVERSATION_RUNTIME=docker`, each with its own Agent Server. Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem.\n\n## Before you call either\n\n### Harness²\n\n1. Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only\n2. Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`\n3. Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched\n4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it\n5. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up\n\n### OpenHands\n\n1. Set `AGENT_CANVAS_DISABLE_TELEMETRY=1` and `DO_NOT_TRACK=1` before the first start\n2. Start Canvas with `OH_CONVERSATION_RUNTIME=docker` or use the Docker image. The npm install runs the agent on the host\n3. Turn on confirmation mode with a risk threshold. Canvas starts with it off\n4. Use the SDK or the Agent Server API for headless runs. The `openhands --headless` CLI is no longer maintained\n5. Set `filter_tools_regex` on the agent to keep unneeded MCP tool definitions out of the context\n\n## Questions\n\n### Which is better for AI agents, Harness² or OpenHands?\n\nOpenHands scores 70.8 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.\n\n### Are Harness² and OpenHands open source?\n\nYes. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).). OpenHands is open source (MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-openhands.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-openhands.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"openhands\"}`. From a terminal: `anchor compare harness2 openhands`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/openhands.json\n\n## Other comparisons with Harness² or OpenHands\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs OpenHands](https://www.anchorterminal.com/compare/agent-zero-vs-openhands.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs OpenHands](https://www.anchorterminal.com/compare/aider-vs-openhands.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs OpenHands](https://www.anchorterminal.com/compare/amp-vs-openhands.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs OpenHands](https://www.anchorterminal.com/compare/antigravity-cli-vs-openhands.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs OpenHands](https://www.anchorterminal.com/compare/claude-code-vs-openhands.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs OpenHands](https://www.anchorterminal.com/compare/cline-vs-openhands.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs OpenHands](https://www.anchorterminal.com/compare/cursor-cli-vs-openhands.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs OpenHands](https://www.anchorterminal.com/compare/devin-vs-openhands.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs OpenHands](https://www.anchorterminal.com/compare/droid-cli-vs-openhands.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs OpenHands](https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs OpenHands](https://www.anchorterminal.com/compare/gemini-cli-vs-openhands.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs OpenHands](https://www.anchorterminal.com/compare/github-copilot-cli-vs-openhands.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs OpenHands](https://www.anchorterminal.com/compare/goose-vs-openhands.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)\n- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)\n- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)\n- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)\n- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)\n- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)\n- [Harness² vs Qwen Code](https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md)\n- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)\n- [HarnessRouter vs OpenHands](https://www.anchorterminal.com/compare/harnessrouter-vs-openhands.md)\n- [Kilo Code CLI vs OpenHands](https://www.anchorterminal.com/compare/kilo-code-cli-vs-openhands.md)\n- [Kiro CLI vs OpenHands](https://www.anchorterminal.com/compare/kiro-cli-vs-openhands.md)\n- [Muse Code vs OpenHands](https://www.anchorterminal.com/compare/muse-code-vs-openhands.md)\n- [OpenAI Codex vs OpenHands](https://www.anchorterminal.com/compare/openai-codex-vs-openhands.md)\n- [OpenCode vs OpenHands](https://www.anchorterminal.com/compare/opencode-vs-openhands.md)\n- [OpenHands vs Prime Agent](https://www.anchorterminal.com/compare/openhands-vs-prime-agent.md)\n- [OpenHands vs Qwen Code](https://www.anchorterminal.com/compare/openhands-vs-qwen-code.md)\n- [OpenHands vs Mirror CLI](https://www.anchorterminal.com/compare/openhands-vs-reflection-mirror.md)\n- [CLI Manager vs OpenHands](https://www.anchorterminal.com/compare/cli-manager-vs-openhands.md)\n- [Harness vs OpenHands](https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands.md)\n- [OpenHands vs Paperclip](https://www.anchorterminal.com/compare/openhands-vs-paperclip.md)\n- [OpenHands vs Parallax](https://www.anchorterminal.com/compare/openhands-vs-parallax-agents.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Harness² vs OpenHands", "url": "" } ], "description": "OpenHands scores 70.8 (BB) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 41.6", "OpenHands BB 70.8", "scores" ], "h1": "Harness² vs OpenHands", "image": "https://www.anchorterminal.com/assets/og/compare-harness2-vs-openhands.png", "path": "/compare/harness2-vs-openhands", "published": "2026-10-01", "section": "tools", "title": "Harness² vs OpenHands for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/harness2-vs-openhands" }, "tokens": { "markdown": 3000, "slim": 680 }, "version": 1 }