{ "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": "Prime Agent scores 60.5 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on schema \u0026 documentation.", "b": { "slug": "prime-agent", "name": "Prime Agent", "vendor": "Prime Intellect", "vendorUrl": "https://www.primeintellect.ai", "kind": "harness", "category": "agent-harnesses", "summary": "Prime Agent is an open-source coding and research agent from Prime Intellect, run from a terminal. The model works through a persistent Python REPL, spawns subagents as function calls and keeps sessions running in a background daemon.", "url": "https://www.anchorterminal.com/tools/prime-agent", "markdownUrl": "https://www.anchorterminal.com/tools/prime-agent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/prime-agent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/prime-agent.json", "repo": "https://github.com/PrimeIntellect-ai/prime-agent", "license": "MIT", "transports": [], "packages": [], "auth": "none", "authNotes": "No account of its own is required. `/login` on first launch picks a subscription or an API-key provider, and provider keys can also come from environment variables such as `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `OPENROUTER_API_KEY` or `PRIME_API_KEY`.", "pricing": "free", "pricingNotes": "Free and MIT-licensed, with nothing to buy for the agent itself. The model provider is paid separately, and Prime Intellect's own inference service is one of the providers.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 21614, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://github.com/PrimeIntellect-ai/prime-agent#readme", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "open-source", "local", "free", "no-card", "rust", "mcp", "telemetry-default-on", "pre-1.0", "beta" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 60.5, "grade": "C", "agentReady": false, "rank": 560, "ranked": true, "rankOf": 1135, "categoryRank": 12, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 79, "payments": 60, "reliability": 65, "schema": 42, "security": 50, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas.", "bestFor": "Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.", "strengths": [ "MIT licence, with CI on main passing on 8 October 2026 (fmt, clippy with warnings as errors, sharded tests, cargo-deny)", "Three model tools (bash, edit, ipython). MCP tools are found and called from Python, so their definitions stay out of the prompt", "Autonomous mode takes limits on turns, tokens, time and continuations, plus user-defined quality gates with retries", "A daemon supervises one worker per session, restarts it with backoff and restores from append-only JSONL session files", "Telemetry is disclosed on first run, carries primitive values only and has four documented ways to turn it off" ], "weaknesses": [ "No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox", "The stable channel (v0.9.8, 29 September 2026) is the TypeScript build. The Rust code on main ships only as nightly betas", "No documentation site for Prime Agent. Headless, JSON, RPC and ACP modes are described only in source and crate READMEs", "Usage telemetry is on by default, and the vendor privacy policy (updated 23 February 2024) does not describe it", "No SECURITY.md in the repository, and public issues and unsolicited pull requests are closed automatically" ], "agentNotes": [ "Run it in a disposable clone, container or VM. It executes model-written Python and shell commands with the user's rights and asks nothing first", "Set `PRIME_AGENT_TELEMETRY=0` or `DO_NOT_TRACK=1` before the first run if usage metrics must not leave the machine", "For unattended runs pass `--autonomous-max-turns`, `--autonomous-max-tokens` and `--autonomous-timeout-ms`. Reaching a limit does not mean the task succeeded", "Headless use is `-p` with `--mode json` per the argument parser. A provider key must already be configured, because `/login` is interactive", "The `-t/--tools`, `-nt/--no-tools` and `-nbt/--no-builtin-tools` flags were removed and now fail as unknown options" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.5 } ], "editorialScores": { "ergonomics": 73, "maintenance": 79, "payments": 60, "reliability": 65, "schema": 42, "security": 50, "transparency": 67 }, "provenanceScore": 61 }, "connect": { "install": "curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/prime-agent" }, "area": "frameworks", "provenance": { "legalEntity": "Prime Intellect, Inc.", "domain": "primeintellect.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://www.primeintellect.ai/terms-of-service", "privacy": "https://www.primeintellect.ai/privacy-policy", "statusPage": "https://status.primeintellect.ai", "changelog": "https://github.com/PrimeIntellect-ai/prime-agent/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The site footer, terms and privacy policy name Prime Intellect, Inc. of Dover, Delaware. The repository LICENSE names Prime Intellect Ltd. as copyright holder.", "www.primeintellect.ai/.well-known/security.txt returned 404 on 8 October 2026. A security policy with a reporting address is at https://www.primeintellect.ai/security.", "The status page covers Prime Intellect's hosted platform (API, inference, sandboxes), not the locally run agent.", "The LICENSE adds that the software is a port of the Prime Agent TypeScript product, originally copyright 2025 Mario Zechner, used under the MIT licence. GitHub's licence detector reports the file as unrecognised." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/prime-agent.json", "live": { "slug": "prime-agent", "vendorStatus": { "page": "https://status.primeintellect.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-18T16:51:55.331092468Z" }, "versions": [ { "registry": "github", "name": "PrimeIntellect-ai/prime-agent", "version": "v0.10.0", "released": "2026-10-09", "seenAt": "2026-10-18T03:13:23.10365612Z" } ], "githubStars": 22098, "securityTxt": { "url": "https://primeintellect.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:54:16.038222493Z" }, "domain": { "domain": "primeintellect.ai", "registered": "2023-08-22", "source": "https://rdap.identitydigital.services/rdap/domain/primeintellect.ai", "checkedAt": "2026-10-18T13:40:47.69730239Z" }, "pages": [ { "url": "https://www.primeintellect.ai/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-17T23:19:19.427855304Z", "changedAt": "2026-10-16T22:40:19.183107547Z", "fingerprint": "bb7d733da519" }, { "url": "https://www.primeintellect.ai/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-10-17T23:19:21.584696973Z", "changedAt": "2026-10-16T22:40:21.483306034Z", "fingerprint": "5901c2293df5" } ], "updatedAt": "2026-10-18T16:51:55.331092468Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Prime Intellect", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "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", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-10-07", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "4.2k stars", "b": "22k stars", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Prime Agent scores 60.5 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on schema \u0026 documentation.", "question": "Which is better for AI agents, Harness² or Prime Agent?" }, { "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).). Prime Agent is open source (MIT).", "question": "Are Harness² and Prime Agent open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 51 against 42" ], "also": null, "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, 65 against 20", "Agent ergonomics, 73 against 59", "Security \u0026 auth, 50 against 44", "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 79 against 36", "Transparency \u0026 trust, 64 against 44" ], "also": [ "Free to start without a card" ], "goodFor": "Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.", "slug": "prime-agent", "watchFor": "No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox" } ], "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-prime-agent.json", "title": "Agent Zero vs Prime Agent", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent" }, { "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-prime-agent.json", "title": "Aider vs Prime Agent", "url": "https://www.anchorterminal.com/compare/aider-vs-prime-agent" }, { "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-prime-agent.json", "title": "Amp vs Prime Agent", "url": "https://www.anchorterminal.com/compare/amp-vs-prime-agent" }, { "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-prime-agent.json", "title": "Antigravity CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-prime-agent" }, { "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-prime-agent.json", "title": "Claude Code vs Prime Agent", "url": "https://www.anchorterminal.com/compare/claude-code-vs-prime-agent" }, { "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-prime-agent.json", "title": "Cline vs Prime Agent", "url": "https://www.anchorterminal.com/compare/cline-vs-prime-agent" }, { "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-prime-agent.json", "title": "Cursor CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent" }, { "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-prime-agent.json", "title": "Devin vs Prime Agent", "url": "https://www.anchorterminal.com/compare/devin-vs-prime-agent" }, { "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-prime-agent.json", "title": "Droid CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-prime-agent" }, { "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-prime-agent.json", "title": "Pi vs Prime Agent", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent" }, { "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-prime-agent.json", "title": "Gemini CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent" }, { "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-prime-agent.json", "title": "GitHub Copilot CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-prime-agent" }, { "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-prime-agent.json", "title": "goose vs Prime Agent", "url": "https://www.anchorterminal.com/compare/goose-vs-prime-agent" }, { "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-openhands.json", "title": "Harness² vs OpenHands", "url": "https://www.anchorterminal.com/compare/harness2-vs-openhands" }, { "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-prime-agent.json", "title": "HarnessRouter vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-prime-agent.json", "title": "Kilo Code CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.json", "title": "Kiro CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-prime-agent.json", "title": "Muse Code vs Prime Agent", "url": "https://www.anchorterminal.com/compare/muse-code-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent.json", "title": "OpenAI Codex vs Prime Agent", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-prime-agent.json", "title": "OpenCode vs Prime Agent", "url": "https://www.anchorterminal.com/compare/opencode-vs-prime-agent" }, { "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/prime-agent-vs-qwen-code.json", "title": "Prime Agent vs Qwen Code", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/prime-agent-vs-reflection-mirror.json", "title": "Prime Agent vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-prime-agent.json", "title": "CLI Manager vs Prime Agent", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent.json", "title": "Harness vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.json", "title": "Paperclip vs Prime Agent", "url": "https://www.anchorterminal.com/compare/paperclip-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/parallax-agents-vs-prime-agent.json", "title": "Parallax vs Prime Agent", "url": "https://www.anchorterminal.com/compare/parallax-agents-vs-prime-agent" } ], "scores": [ { "by": 45, "edge": "prime-agent", "harness2": 20, "key": "reliability", "name": "Reliability", "prime-agent": 65, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 9, "edge": "harness2", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "prime-agent": 42, "weight": 13 }, { "by": 14, "edge": "prime-agent", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "prime-agent": 73, "weight": 13 }, { "by": 6, "edge": "prime-agent", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "prime-agent": 50, "weight": 14 }, { "by": 20, "edge": "prime-agent", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "prime-agent": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 43, "edge": "prime-agent", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "prime-agent": 79, "weight": 7 }, { "by": 20, "edge": "prime-agent", "harness2": 44, "key": "transparency", "name": "Transparency \u0026 trust", "prime-agent": 64, "weight": 7 } ], "summary": "Prime Agent scores 60.5 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on schema \u0026 documentation. 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.", "prime-agent": "Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent", "json": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.min.md" }, "markdown": "Prime Agent scores 60.5 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on schema \u0026 documentation. 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- Prime Agent: grade C, 60.5/100, rank #560 of 1135. Markdown https://www.anchorterminal.com/tools/prime-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/prime-agent.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\nAhead on:\n- Schema \u0026 documentation, 51 against 42\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### Prime Agent (C)\n\nGood for: Long-running research and coding work where one model drives subagents, schedules and goals from code, and where the owner can isolate the machine.\n\nAhead on:\n- Reliability, 65 against 20\n- Agent ergonomics, 73 against 59\n- Security \u0026 auth, 50 against 44\n- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 79 against 36\n- Transparency \u0026 trust, 64 against 44\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: No approval prompts and no sandbox. The README says the worker and kernel processes are not a security sandbox\n\n\n## Score by category\n\n| Category | Weight | Harness² | Prime Agent | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 65 | Prime Agent +45 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 42 | Harness² +9 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 73 | Prime Agent +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 50 | Prime Agent +6 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | Prime Agent +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 79 | Prime Agent +43 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 44 | 64 | Prime Agent +20 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **41.6 · E** | **60.5 · C** | |\n\n## Facts side by side\n\n| Fact | Harness² | Prime Agent |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Prime Intellect |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\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 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-08 | 2026-10-07 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | no date given |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | yes |\n| Terms or service can change without notice | | yes |\n| Arbitration or class-action waiver | | yes |\n| Popularity | 4.2k stars | 22k stars |\n| Agent reviews | 2.5/5 (4) | 2.8/5 (4) |\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**Prime Agent.** Budgets for turns, tokens and time bound an autonomous run, and sessions survive a closed terminal through a supervising daemon. Model-written Python and shell commands run with the user's rights, with no approval step and no sandbox, and the Rust build on the main branch ships only as nightly betas.\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### Prime Agent\n\n1. Run it in a disposable clone, container or VM. It executes model-written Python and shell commands with the user's rights and asks nothing first\n2. Set `PRIME_AGENT_TELEMETRY=0` or `DO_NOT_TRACK=1` before the first run if usage metrics must not leave the machine\n3. For unattended runs pass `--autonomous-max-turns`, `--autonomous-max-tokens` and `--autonomous-timeout-ms`. Reaching a limit does not mean the task succeeded\n4. Headless use is `-p` with `--mode json` per the argument parser. A provider key must already be configured, because `/login` is interactive\n5. The `-t/--tools`, `-nt/--no-tools` and `-nbt/--no-builtin-tools` flags were removed and now fail as unknown options\n\n## Questions\n\n### Which is better for AI agents, Harness² or Prime Agent?\n\nPrime Agent scores 60.5 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on schema \u0026 documentation.\n\n### Are Harness² and Prime Agent 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).). Prime Agent is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-prime-agent.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"prime-agent\"}`. From a terminal: `anchor compare harness2 prime-agent`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/prime-agent.json\n\n## Other comparisons with Harness² or Prime Agent\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Prime Agent](https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Prime Agent](https://www.anchorterminal.com/compare/aider-vs-prime-agent.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Prime Agent](https://www.anchorterminal.com/compare/amp-vs-prime-agent.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Prime Agent](https://www.anchorterminal.com/compare/antigravity-cli-vs-prime-agent.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Prime Agent](https://www.anchorterminal.com/compare/claude-code-vs-prime-agent.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Prime Agent](https://www.anchorterminal.com/compare/cline-vs-prime-agent.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Prime Agent](https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Prime Agent](https://www.anchorterminal.com/compare/devin-vs-prime-agent.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Prime Agent](https://www.anchorterminal.com/compare/droid-cli-vs-prime-agent.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Prime Agent](https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Prime Agent](https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Prime Agent](https://www.anchorterminal.com/compare/github-copilot-cli-vs-prime-agent.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Prime Agent](https://www.anchorterminal.com/compare/goose-vs-prime-agent.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 OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.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 Prime Agent](https://www.anchorterminal.com/compare/harnessrouter-vs-prime-agent.md)\n- [Kilo Code CLI vs Prime Agent](https://www.anchorterminal.com/compare/kilo-code-cli-vs-prime-agent.md)\n- [Kiro CLI vs Prime Agent](https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.md)\n- [Muse Code vs Prime Agent](https://www.anchorterminal.com/compare/muse-code-vs-prime-agent.md)\n- [OpenAI Codex vs Prime Agent](https://www.anchorterminal.com/compare/openai-codex-vs-prime-agent.md)\n- [OpenCode vs Prime Agent](https://www.anchorterminal.com/compare/opencode-vs-prime-agent.md)\n- [OpenHands vs Prime Agent](https://www.anchorterminal.com/compare/openhands-vs-prime-agent.md)\n- [Prime Agent vs Qwen Code](https://www.anchorterminal.com/compare/prime-agent-vs-qwen-code.md)\n- [Prime Agent vs Mirror CLI](https://www.anchorterminal.com/compare/prime-agent-vs-reflection-mirror.md)\n- [CLI Manager vs Prime Agent](https://www.anchorterminal.com/compare/cli-manager-vs-prime-agent.md)\n- [Harness vs Prime Agent](https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent.md)\n- [Paperclip vs Prime Agent](https://www.anchorterminal.com/compare/paperclip-vs-prime-agent.md)\n- [Parallax vs Prime Agent](https://www.anchorterminal.com/compare/parallax-agents-vs-prime-agent.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 Prime Agent", "url": "" } ], "description": "Prime Agent scores 60.5 (C) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 41.6", "Prime Agent C 60.5", "scores" ], "h1": "Harness² vs Prime Agent", "image": "https://www.anchorterminal.com/assets/og/compare-harness2-vs-prime-agent.png", "path": "/compare/harness2-vs-prime-agent", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Prime Agent for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent" }, "tokens": { "markdown": 3050, "slim": 680 }, "version": 1 }