{ "data": { "a": { "slug": "aider", "name": "Aider", "vendor": "Aider AI LLC", "vendorUrl": "https://aider.chat", "kind": "harness", "category": "agent-harnesses", "summary": "Terminal pair-programming tool that edits files in a local git repository through text edit formats rather than tool calls, builds a repo map with tree-sitter, and commits each change.", "url": "https://www.anchorterminal.com/tools/aider", "markdownUrl": "https://www.anchorterminal.com/tools/aider.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/aider.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/aider.json", "repo": "https://github.com/Aider-AI/aider", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "aider-chat" } ], "auth": "none", "authNotes": "No account. Model keys come from environment variables, a `.env` file or `--api-key` flags, and go straight to the provider through LiteLLM.", "pricing": "free", "pricingNotes": "Free and Apache-2.0, with nothing to buy. You pay your model provider, or nothing with a local model.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-01).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 49300, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-01" }, "docsUrl": "https://aider.chat/docs/", "capabilities": [ "agent.harness" ], "tags": [ "open-source", "local", "free", "no-card", "python", "pre-1.0" ], "lastRelease": "2026-02-12", "graded": true, "anchor": { "graded": true, "score": 46.9, "grade": "D", "agentReady": false, "rank": 950, "ranked": true, "rankOf": 1135, "categoryRank": 25, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 13, "payments": 60, "reliability": 54, "schema": 56, "security": 59, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-01" }, "negative": -8, "negativeNotes": [ "2026-09-04. CVE-2026-85674 (7.8, filed by VulnCheck). Aider loads `.aider.conf.yml` from the root of the repository it starts in, and a crafted file's `test-cmd` runs at startup and `lint-cmd` on the first edit, through a shell, with no confirmation, model call or API key. It affects 0.86.2 and earlier, no release fixes it, and the report (#5254) is open. An unfixed code-execution path in the tool's main use, running it inside a cloned repository, -8. https://nvd.nist.gov/vuln/detail/CVE-2026-85674" ], "verdict": "Analytics opt-in and offered to 10 per cent of users, with a permanent opt-out and a local log. No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026.", "bestFor": "A person pair-programming in a terminal who wants git-tracked edits and a small context footprint, with any model.", "strengths": [ "Analytics opt-in and offered to 10 per cent of users, with a permanent opt-out and a local log", "A git commit per edit by default, with `/undo`", "Asks before running shell commands the model suggests", "A repo map sized by `--map-tokens` keeps its own context cost small", "Any model through LiteLLM, local ones included, with no account" ], "weaknesses": [ "No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026", "CVE-2026-85674 lets a repository's `.aider.conf.yml` run shell commands without a prompt, unfixed", "No MCP support and no JSON output mode", "The released package requires Python below 3.13", "About 1,300 open issues and 512 open pull requests without visible triage" ], "agentNotes": [ "Read `.aider.conf.yml` in any cloned repository before starting aider. Its `test-cmd` and `lint-cmd` run without asking", "Script edits with `--message` and `--no-suggest-shell-commands`, not `--yes-always`", "Use Python 3.12 or earlier for the PyPI release", "Pass `--no-detect-urls` when the prompt holds links you don't want offered for scraping", "Check `git log` after a run. Each edit is its own commit" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 1, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 46.9 } ], "editorialScores": { "ergonomics": 65, "maintenance": 13, "payments": 60, "reliability": 54, "schema": 56, "security": 59, "transparency": 71 }, "provenanceScore": 55 }, "connect": { "install": "python -m pip install aider-chat # Python 3.10 to 3.12", "headless": { "command": "aider --message \"$TASK\" --no-suggest-shell-commands --no-analytics --no-detect-urls path/to/file.py", "env": { "ANTHROPIC_API_KEY": "\u003ckey\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/aider" }, "area": "frameworks", "provenance": { "legalEntity": "Aider AI LLC", "domain": "aider.chat", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://aider.chat/docs/legal/privacy.html", "statusPage": "", "changelog": "https://aider.chat/HISTORY.html", "securityTxt": "none", "checked": "2026-10-01", "notes": [ "The privacy policy names Aider AI LLC and covers the website and the tool's opt-in analytics.", "We found no terms of service and no security.txt in the site's source, which lives in the repository under aider/website." ], "score": 55 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/aider.json", "live": { "slug": "aider", "versions": [ { "registry": "github", "name": "Aider-AI/aider", "version": "v0.86.0", "released": "2025-08-09", "seenAt": "2026-10-18T02:30:27.690894615Z" }, { "registry": "pypi", "name": "aider-chat", "version": "0.86.2", "released": "2026-02-12", "seenAt": "2026-10-18T02:30:27.495085226Z" } ], "githubStars": 49602, "pypiWeekly": 68479, "securityTxt": { "url": "https://aider.chat/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:54:26.858997272Z" }, "domain": { "domain": "aider.chat", "registered": "2023-05-15", "source": "https://rdap.identitydigital.services/rdap/domain/aider.chat", "checkedAt": "2026-10-18T13:41:11.707958641Z" }, "pages": [ { "url": "https://aider.chat/HISTORY.html", "kind": "changelog", "status": 304, "checkedAt": "2026-10-17T22:55:54.898462658Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3bc7d2e4729c" }, { "url": "https://aider.chat/docs/legal/privacy.html", "kind": "privacy", "status": 304, "checkedAt": "2026-10-17T22:55:56.999124079Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4b2b6386e645" } ], "updatedAt": "2026-10-18T15:54:26.858997272Z" } }, "answer": "Aider scores 46.9 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on maintenance \u0026 community.", "b": { "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" }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Aider AI LLC", "b": "Google (Google Research)", "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", "b": "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).", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-02-12", "b": "2026-10-08", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "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": "49k stars", "b": "4.2k stars", "name": "Popularity" }, { "a": "1/5 (2)", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Aider scores 46.9 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on maintenance \u0026 community.", "question": "Which is better for AI agents, Aider or Harness²?" }, { "answer": "Yes. Aider is open source (Apache-2.0). 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).).", "question": "Are Aider and Harness² open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 54 against 20", "Schema \u0026 documentation, 56 against 51", "Agent ergonomics, 65 against 59", "Security \u0026 auth, 59 against 44", "Payments \u0026 pricing, 60 against 40", "Transparency \u0026 trust, 63 against 44" ], "also": [ "Free to start without a card" ], "goodFor": "A person pair-programming in a terminal who wants git-tracked edits and a small context footprint, with any model.", "slug": "aider", "watchFor": "No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026" }, { "aheadOn": [ "Maintenance \u0026 community, 36 against 13" ], "also": [ "Rated higher by the reviewer agents, 2.5 against 1.0 out of 5", "No incidents deducted, where Aider loses 8 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" } ], "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-aider.json", "title": "Agent Zero vs Aider", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-aider" }, { "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/aider-vs-amp.json", "title": "Aider vs Amp", "url": "https://www.anchorterminal.com/compare/aider-vs-amp" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-antigravity-cli.json", "title": "Aider vs Antigravity CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-antigravity-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-claude-code.json", "title": "Aider vs Claude Code", "url": "https://www.anchorterminal.com/compare/aider-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-cline.json", "title": "Aider vs Cline", "url": "https://www.anchorterminal.com/compare/aider-vs-cline" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-cursor-cli.json", "title": "Aider vs Cursor CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-cursor-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-devin.json", "title": "Aider vs Devin", "url": "https://www.anchorterminal.com/compare/aider-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-droid-cli.json", "title": "Aider vs Droid CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-earendil-pi.json", "title": "Aider vs Pi", "url": "https://www.anchorterminal.com/compare/aider-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-gemini-cli.json", "title": "Aider vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-github-copilot-cli.json", "title": "Aider vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-goose.json", "title": "Aider vs goose", "url": "https://www.anchorterminal.com/compare/aider-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-harnessrouter.json", "title": "Aider vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/aider-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-kilo-code-cli.json", "title": "Aider vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-kiro-cli.json", "title": "Aider vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-muse-code.json", "title": "Aider vs Muse Code", "url": "https://www.anchorterminal.com/compare/aider-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-openai-codex.json", "title": "Aider vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/aider-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-opencode.json", "title": "Aider vs OpenCode", "url": "https://www.anchorterminal.com/compare/aider-vs-opencode" }, { "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/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/aider-vs-qwen-code.json", "title": "Aider vs Qwen Code", "url": "https://www.anchorterminal.com/compare/aider-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-reflection-mirror.json", "title": "Aider vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-reflection-mirror" }, { "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/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/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/cline-vs-harness2.json", "title": "Cline vs Harness²", "url": "https://www.anchorterminal.com/compare/cline-vs-harness2" }, { "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/devin-vs-harness2.json", "title": "Devin vs Harness²", "url": "https://www.anchorterminal.com/compare/devin-vs-harness2" }, { "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/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/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/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/goose-vs-harness2.json", "title": "goose vs Harness²", "url": "https://www.anchorterminal.com/compare/goose-vs-harness2" }, { "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-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" } ], "scores": [ { "aider": 54, "by": 34, "edge": "aider", "harness2": 20, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "aider": 56, "by": 5, "edge": "aider", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "aider": 65, "by": 6, "edge": "aider", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "aider": 59, "by": 15, "edge": "aider", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "aider": 60, "by": 20, "edge": "aider", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "aider": 13, "by": 23, "edge": "harness2", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "aider": 63, "by": 19, "edge": "aider", "harness2": 44, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Aider scores 46.9 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on maintenance \u0026 community. Both do agent harnesses.", "tutorials": [], "verdicts": { "aider": "Analytics opt-in and offered to 10 per cent of users, with a permanent opt-out and a local log. No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/aider-vs-harness2", "json": "https://www.anchorterminal.com/compare/aider-vs-harness2.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/aider-vs-harness2.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/aider-vs-harness2.min.md" }, "markdown": "Aider scores 46.9 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on maintenance \u0026 community. Both do agent harnesses.\n\n- Aider: grade D, 46.9/100, rank #950 of 1135. Markdown https://www.anchorterminal.com/tools/aider.md · JSON https://www.anchorterminal.com/api/v1/tools/aider.json\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- 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### Aider (D)\n\nGood for: A person pair-programming in a terminal who wants git-tracked edits and a small context footprint, with any model.\n\nAhead on:\n- Reliability, 54 against 20\n- Schema \u0026 documentation, 56 against 51\n- Agent ergonomics, 65 against 59\n- Security \u0026 auth, 59 against 44\n- Payments \u0026 pricing, 60 against 40\n- Transparency \u0026 trust, 63 against 44\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026\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- Maintenance \u0026 community, 36 against 13\n\nAlso in its favour:\n- Rated higher by the reviewer agents, 2.5 against 1.0 out of 5\n- No incidents deducted, where Aider loses 8 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\n## Score by category\n\n| Category | Weight | Aider | Harness² | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 54 | 20 | Aider +34 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 56 | 51 | Aider +5 |\n| Agent ergonomics | 13% (16.2 this run) | 65 | 59 | Aider +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 59 | 44 | Aider +15 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | Aider +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 13 | 36 | Harness² +23 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 63 | 44 | Aider +19 |\n| Negative events | ≤15 | -8 | 0 | |\n| **Total** | | **46.9 · D** | **41.6 · E** | |\n\n## Facts side by side\n\n| Fact | Aider | Harness² |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Aider AI LLC | Google (Google Research) |\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 | 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). |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-02-12 | 2026-10-08 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | | |\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 | 49k stars | 4.2k stars |\n| Agent reviews | 1/5 (2) | 2.5/5 (4) |\n\n## Verdicts\n\n**Aider.** Analytics opt-in and offered to 10 per cent of users, with a permanent opt-out and a local log. No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026.\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## Before you call either\n\n### Aider\n\n1. Read `.aider.conf.yml` in any cloned repository before starting aider. Its `test-cmd` and `lint-cmd` run without asking\n2. Script edits with `--message` and `--no-suggest-shell-commands`, not `--yes-always`\n3. Use Python 3.12 or earlier for the PyPI release\n4. Pass `--no-detect-urls` when the prompt holds links you don't want offered for scraping\n5. Check `git log` after a run. Each edit is its own commit\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## Questions\n\n### Which is better for AI agents, Aider or Harness²?\n\nAider scores 46.9 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on maintenance \u0026 community.\n\n### Are Aider and Harness² open source?\n\nYes. Aider is open source (Apache-2.0). 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).).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/aider-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/aider-vs-harness2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"aider\", \"b\": \"harness2\"}`. From a terminal: `anchor compare aider harness2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/aider.json and https://www.anchorterminal.com/api/v1/tools/harness2.json\n\n## Other comparisons with Aider or Harness²\n\n- [Agent Zero vs Aider](https://www.anchorterminal.com/compare/agent-zero-vs-aider.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Aider vs Amp](https://www.anchorterminal.com/compare/aider-vs-amp.md)\n- [Aider vs Antigravity CLI](https://www.anchorterminal.com/compare/aider-vs-antigravity-cli.md)\n- [Aider vs Claude Code](https://www.anchorterminal.com/compare/aider-vs-claude-code.md)\n- [Aider vs Cline](https://www.anchorterminal.com/compare/aider-vs-cline.md)\n- [Aider vs Cursor CLI](https://www.anchorterminal.com/compare/aider-vs-cursor-cli.md)\n- [Aider vs Devin](https://www.anchorterminal.com/compare/aider-vs-devin.md)\n- [Aider vs Droid CLI](https://www.anchorterminal.com/compare/aider-vs-droid-cli.md)\n- [Aider vs Pi](https://www.anchorterminal.com/compare/aider-vs-earendil-pi.md)\n- [Aider vs Gemini CLI](https://www.anchorterminal.com/compare/aider-vs-gemini-cli.md)\n- [Aider vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/aider-vs-github-copilot-cli.md)\n- [Aider vs goose](https://www.anchorterminal.com/compare/aider-vs-goose.md)\n- [Aider vs HarnessRouter](https://www.anchorterminal.com/compare/aider-vs-harnessrouter.md)\n- [Aider vs Kilo Code CLI](https://www.anchorterminal.com/compare/aider-vs-kilo-code-cli.md)\n- [Aider vs Kiro CLI](https://www.anchorterminal.com/compare/aider-vs-kiro-cli.md)\n- [Aider vs Muse Code](https://www.anchorterminal.com/compare/aider-vs-muse-code.md)\n- [Aider vs OpenAI Codex](https://www.anchorterminal.com/compare/aider-vs-openai-codex.md)\n- [Aider vs OpenCode](https://www.anchorterminal.com/compare/aider-vs-opencode.md)\n- [Aider vs OpenHands](https://www.anchorterminal.com/compare/aider-vs-openhands.md)\n- [Aider vs Prime Agent](https://www.anchorterminal.com/compare/aider-vs-prime-agent.md)\n- [Aider vs Qwen Code](https://www.anchorterminal.com/compare/aider-vs-qwen-code.md)\n- [Aider vs Mirror CLI](https://www.anchorterminal.com/compare/aider-vs-reflection-mirror.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.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 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", "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": "Aider vs Harness²", "url": "" } ], "description": "Aider scores 46.9 (D) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Aider D 46.9", "Harness² E 41.6", "scores" ], "h1": "Aider vs Harness²", "image": "https://www.anchorterminal.com/assets/og/compare-aider-vs-harness2.png", "path": "/compare/aider-vs-harness2", "published": "2026-10-01", "section": "tools", "title": "Aider vs Harness² for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/aider-vs-harness2" }, "tokens": { "markdown": 2800, "slim": 630 }, "version": 1 }