{ "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": 1040, "ranked": true, "rankOf": 1146, "categoryRank": 37, "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": "Jules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "jules", "name": "Jules", "vendor": "Google LLC", "vendorUrl": "https://jules.google", "kind": "harness", "category": "agent-harnesses", "summary": "Jules is Google's asynchronous coding agent, which clones a GitHub repository into a cloud virtual machine, plans, edits and opens pull requests. Outside agents drive it through an alpha REST API, a TypeScript SDK, an MCP package and a CLI.", "url": "https://www.anchorterminal.com/tools/jules", "markdownUrl": "https://www.anchorterminal.com/tools/jules.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/jules.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/jules.json", "repo": "https://github.com/google-labs-code/jules-sdk", "license": "Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed", "transports": [ "http", "stdio" ], "packages": [ { "registry": "npm", "name": "@google/jules" }, { "registry": "npm", "name": "@google/jules-sdk" }, { "registry": "npm", "name": "@google/jules-mcp" } ], "auth": "mixed", "authNotes": "The REST API takes an API key in the `X-Goog-Api-Key` header. Keys are created by a person in Settings in the Jules web app, at most three at a time, shown once and revocable there, and publicly exposed keys are disabled automatically. Keys carry no scopes. The discovery document also lists Google OAuth with the broad cloud-platform scope. The Jules Tools CLI signs in with a Google account in the browser (`jules login`). Repository sources need the Jules GitHub app installed through the web app.", "pricing": "freemium", "pricingNotes": "Free plan with 15 tasks a day and 3 concurrent tasks. Jules in Pro (100 a day, 15 concurrent) and Jules in Ultra (300 a day, 60 concurrent) come with the Google AI Pro and Ultra plans, and the Google AI plans page lists AI Plus with expanded Jules limits (jules.google/docs/usage-limits and one.google.com/about/google-ai-plans, checked 2026-10-18). Paid plans are for personal @gmail.com accounts, with an interest form for business users. The plan prices render per locale and weren't read. No per-task or per-call price.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Jules docs, the API reference, the discovery document or the plans pages (checked 2026-10-18).", "endpoints": [] }, "toolCount": 8, "popularity": { "githubStars": null, "npmWeekly": 1269, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://jules.google/docs/", "llmsTxt": "https://jules.google/docs/llms.txt", "openapi": "https://jules.googleapis.com/$discovery/rest?version=v1alpha", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "hosted", "cloud-agent", "closed-source", "api-key", "alpha", "llms-txt", "mcp", "no-status-page", "stale-release", "freemium" ], "lastRelease": "2026-03-09", "graded": true, "anchor": { "graded": true, "score": 44.5, "grade": "E", "agentReady": false, "rank": 1000, "ranked": true, "rankOf": 1146, "categoryRank": 35, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 18, "payments": 30, "reliability": 13, "schema": 76, "security": 57, "transparency": 44 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-18" }, "negative": 0, "verdict": "The API is described by a public Google discovery document, takes only a prompt to start a session, and logs every plan, shell command and diff as activities. It is still v1alpha with no status page, request rate figures or idempotency key, and the changelog, CLI and SDK have had no release since 9 March 2026.", "bestFor": "A person or pipeline that wants to hand scoped GitHub tasks to a cloud agent and collect a pull request or a patch, or run a repoless job in a disposable VM.", "strengths": [ "Public discovery document for jules.googleapis.com v1alpha with 13 methods, typed schemas, enums and required fields, revision 20261015", "Only `prompt` is required to create a session. A session without `sourceContext` runs repoless in a fresh cloud VM", "Activities record plans, messages, bash commands with exit codes and git patches, and can be filtered by `create_time` to fetch only new events", "Four ways in for an outside agent, the REST API, the Apache-2.0 TypeScript SDK, an 8-tool stdio MCP server and the Jules Tools CLI", "Free plan of 15 tasks a day and 3 concurrent tasks with a Google account, and docs served as Markdown with an llms.txt index" ], "weaknesses": [ "The REST API has been v1alpha since 3 October 2025 and the docs say specifications and API keys may change", "Newest changelog entry is 9 March 2026, the CLI's last npm release 0.1.42 was on 16 December 2025, and the SDK and MCP packages last published 0.2.0 on 9 March 2026", "No status page, no request rate figures, no Retry-After guidance and no idempotency key on session creation were found", "API sessions auto-approve their plans unless `requirePlanApproval` is true, and the MCP server defaults to an automated run that opens a pull request", "A person must sign in with Google, install the Jules GitHub app and create the key in the web app. Keys carry no scopes" ], "agentNotes": [ "Set `requirePlanApproval: true` on sessions that touch shared branches, then call `:approvePlan` yourself. API sessions otherwise run their plan without review", "Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another", "Poll activities with a `create_time` filter and cache them. Activities never change once written", "Read the request fields from the discovery document at https://jules.googleapis.com/$discovery/rest?version=v1alpha. The field tables on jules.google render empty", "Budget against the daily task quota of 15, 100 or 300 by plan. New sessions are refused until the rolling 24 hours reset" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.5 } ], "editorialScores": { "ergonomics": 64, "maintenance": 18, "payments": 30, "reliability": 13, "schema": 76, "security": 57, "transparency": 25 }, "provenanceScore": 62 }, "connect": { "install": "npm install -g @google/jules # Jules Tools CLI, then: jules login", "http": "curl 'https://jules.googleapis.com/v1alpha/sessions' -X POST -H \"Content-Type: application/json\" -H \"x-goog-api-key: $JULES_API_KEY\" -d '{\"prompt\": \"Add a test for parseQueryString in utils.js\", \"sourceContext\": {\"source\": \"sources/github/OWNER/REPO\", \"githubRepoContext\": {\"startingBranch\": \"main\"}}, \"requirePlanApproval\": true}'", "config": { "mcpServers": { "jules": { "args": [ "@google/jules-mcp" ], "command": "npx", "env": { "JULES_API_KEY": "\u003capi-key\u003e" } } } }, "headless": { "run": "jules remote new --repo . --session \"write unit tests\"" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/jules" }, "area": "frameworks", "provenance": { "legalEntity": "Google LLC", "domain": "jules.google", "domainRegistered": "2025-01-16", "endpointOnVendorDomain": true, "terms": "https://policies.google.com/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "", "changelog": "https://jules.google/docs/changelog/", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "The jules.google footer links the Google Terms of Service and Privacy Policy. The Jules privacy notice at jules.google.com/legal answered 'Jules is not yet available in your region' to our request and wasn't read.", "jules.google returns 404 for /.well-known/security.txt. www.google.com has a valid security.txt (expires 2030-04-01) pointing to g.co/vulnz and the Google VRP.", "The API answers at jules.googleapis.com, Google's API domain. RDAP for jules.google gives a registration date of 2025-01-16.", "No status page for Jules was found." ], "score": 62 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/jules.json", "live": { "slug": "jules", "pages": [ { "url": "https://jules.google/docs/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-18T23:32:10.654949702Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6add211f604a" } ], "updatedAt": "2026-10-18T23:32:10.654949702Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Google LLC", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, stdio", "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": "Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed", "name": "Licence" }, { "a": "none", "b": "8", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-03-09", "name": "Last release" }, { "a": "no document linked", "b": "2026-07-30", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-10-01", "name": "Privacy policy last updated" }, { "a": "", "b": "yes", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "4.2k stars", "b": "1.3k npm/wk", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Jules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Harness² or Jules?" }, { "answer": "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).). No open-source release is listed for Jules.", "question": "Are Harness² and Jules open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 20 against 13", "Payments \u0026 pricing, 40 against 30", "Maintenance \u0026 community, 36 against 18" ], "also": [ "No key needed to call it", "Open source" ], "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": [ "Schema \u0026 documentation, 76 against 51", "Agent ergonomics, 64 against 59", "Security \u0026 auth, 57 against 44" ], "also": [ "Runs on your own machine" ], "goodFor": "A person or pipeline that wants to hand scoped GitHub tasks to a cloud agent and collect a pull request or a patch, or run a repoless job in a disposable VM.", "slug": "jules", "watchFor": "The REST API has been v1alpha since 3 October 2025 and the docs say specifications and API keys may change" } ], "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-jules.json", "title": "Agent Zero vs Jules", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-jules" }, { "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-jules.json", "title": "Aider vs Jules", "url": "https://www.anchorterminal.com/compare/aider-vs-jules" }, { "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-jules.json", "title": "Amp vs Jules", "url": "https://www.anchorterminal.com/compare/amp-vs-jules" }, { "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-jules.json", "title": "Antigravity CLI vs Jules", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-harness2.json", "title": "Auggie CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/auggie-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-jules.json", "title": "Auggie CLI vs Jules", "url": "https://www.anchorterminal.com/compare/auggie-vs-jules" }, { "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-jules.json", "title": "Claude Code vs Jules", "url": "https://www.anchorterminal.com/compare/claude-code-vs-jules" }, { "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-jules.json", "title": "Cline vs Jules", "url": "https://www.anchorterminal.com/compare/cline-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-harness2.json", "title": "Crush vs Harness²", "url": "https://www.anchorterminal.com/compare/crush-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-jules.json", "title": "Crush vs Jules", "url": "https://www.anchorterminal.com/compare/crush-vs-jules" }, { "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-jules.json", "title": "Cursor CLI vs Jules", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.json", "title": "DeepSeek Harness (dsh) vs Harness²", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-jules.json", "title": "DeepSeek Harness (dsh) vs Jules", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-jules" }, { "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-jules.json", "title": "Devin vs Jules", "url": "https://www.anchorterminal.com/compare/devin-vs-jules" }, { "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-jules.json", "title": "Droid CLI vs Jules", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-jules" }, { "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-jules.json", "title": "Pi vs Jules", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-jules" }, { "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-jules.json", "title": "Gemini CLI vs Jules", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-jules" }, { "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-jules.json", "title": "GitHub Copilot CLI vs Jules", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-jules" }, { "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-jules.json", "title": "goose vs Jules", "url": "https://www.anchorterminal.com/compare/goose-vs-jules" }, { "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-junie.json", "title": "Harness² vs Junie CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-junie" }, { "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-kimi-code-cli.json", "title": "Harness² vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kimi-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-mini-swe-agent.json", "title": "Harness² vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.json", "title": "Harness² vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-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-qoder-cli.json", "title": "Harness² vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-qoder-cli" }, { "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/harness2-vs-rovo-dev-cli.json", "title": "Harness² vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-warp.json", "title": "Harness² vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/harness2-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-jules.json", "title": "HarnessRouter vs Jules", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-junie.json", "title": "Jules vs Junie CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-kilo-code-cli.json", "title": "Jules vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-kimi-code-cli.json", "title": "Jules vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-kiro-cli.json", "title": "Jules vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-mini-swe-agent.json", "title": "Jules vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/jules-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-mistral-vibe-cli.json", "title": "Jules vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-muse-code.json", "title": "Jules vs Muse Code", "url": "https://www.anchorterminal.com/compare/jules-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-openai-codex.json", "title": "Jules vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/jules-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-opencode.json", "title": "Jules vs OpenCode", "url": "https://www.anchorterminal.com/compare/jules-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-openhands.json", "title": "Jules vs OpenHands", "url": "https://www.anchorterminal.com/compare/jules-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-prime-agent.json", "title": "Jules vs Prime Agent", "url": "https://www.anchorterminal.com/compare/jules-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-qoder-cli.json", "title": "Jules vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-qwen-code.json", "title": "Jules vs Qwen Code", "url": "https://www.anchorterminal.com/compare/jules-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-reflection-mirror.json", "title": "Jules vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-rovo-dev-cli.json", "title": "Jules vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/jules-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-warp.json", "title": "Jules vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/jules-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-jules.json", "title": "CLI Manager vs Jules", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-jules.json", "title": "Harness vs Jules", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-paperclip.json", "title": "Jules vs Paperclip", "url": "https://www.anchorterminal.com/compare/jules-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-parallax-agents.json", "title": "Jules vs Parallax", "url": "https://www.anchorterminal.com/compare/jules-vs-parallax-agents" } ], "scores": [ { "by": 7, "edge": "harness2", "harness2": 20, "jules": 13, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 25, "edge": "jules", "harness2": 51, "jules": 76, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 5, "edge": "jules", "harness2": 59, "jules": 64, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 13, "edge": "jules", "harness2": 44, "jules": 57, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "harness2", "harness2": 40, "jules": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 18, "edge": "harness2", "harness2": 36, "jules": 18, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 0, "edge": "", "harness2": 44, "jules": 44, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Jules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments \u0026 pricing and maintenance \u0026 community. 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.", "jules": "The API is described by a public Google discovery document, takes only a prompt to start a session, and logs every plan, shell command and diff as activities. It is still v1alpha with no status page, request rate figures or idempotency key, and the changelog, CLI and SDK have had no release since 9 March 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-jules", "json": "https://www.anchorterminal.com/compare/harness2-vs-jules.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-jules.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-jules.min.md" }, "markdown": "Jules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments \u0026 pricing and maintenance \u0026 community. Both do agent harnesses.\n\n- Harness²: grade E, 41.6/100, rank #1040 of 1146. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json\n- Jules: grade E, 44.5/100, rank #1000 of 1146. Markdown https://www.anchorterminal.com/tools/jules.md · JSON https://www.anchorterminal.com/api/v1/tools/jules.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 713 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- Reliability, 20 against 13\n- Payments \u0026 pricing, 40 against 30\n- Maintenance \u0026 community, 36 against 18\n\nAlso in its favour:\n- No key needed to call it\n- Open source\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### Jules (E)\n\nGood for: A person or pipeline that wants to hand scoped GitHub tasks to a cloud agent and collect a pull request or a patch, or run a repoless job in a disposable VM.\n\nAhead on:\n- Schema \u0026 documentation, 76 against 51\n- Agent ergonomics, 64 against 59\n- Security \u0026 auth, 57 against 44\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: The REST API has been v1alpha since 3 October 2025 and the docs say specifications and API keys may change\n\n\n## Score by category\n\n| Category | Weight | Harness² | Jules | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 13 | Harness² +7 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 76 | Jules +25 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 64 | Jules +5 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 57 | Jules +13 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 30 | Harness² +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 18 | Harness² +18 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 44 | 44 | even |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **41.6 · E** | **44.5 · E** | |\n\n## Facts side by side\n\n| Fact | Harness² | Jules |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Google LLC |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | HTTP, stdio |\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). | Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed |\n| Tools exposed | none | 8 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-08 | 2026-03-09 |\n| Terms last updated | no document linked | 2026-07-30 |\n| Privacy policy last updated | no document linked | 2026-10-01 |\n| Customer content may train models | | yes |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\n| Popularity | 4.2k stars | 1.3k npm/wk |\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**Jules.** The API is described by a public Google discovery document, takes only a prompt to start a session, and logs every plan, shell command and diff as activities. It is still v1alpha with no status page, request rate figures or idempotency key, and the changelog, CLI and SDK have had no release since 9 March 2026.\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### Jules\n\n1. Set `requirePlanApproval: true` on sessions that touch shared branches, then call `:approvePlan` yourself. API sessions otherwise run their plan without review\n2. Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another\n3. Poll activities with a `create_time` filter and cache them. Activities never change once written\n4. Read the request fields from the discovery document at https://jules.googleapis.com/$discovery/rest?version=v1alpha. The field tables on jules.google render empty\n5. Budget against the daily task quota of 15, 100 or 300 by plan. New sessions are refused until the rolling 24 hours reset\n\n## Questions\n\n### Which is better for AI agents, Harness² or Jules?\n\nJules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments \u0026 pricing and maintenance \u0026 community.\n\n### Are Harness² and Jules open source?\n\nHarness² 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).). No open-source release is listed for Jules.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-jules.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-jules.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"jules\"}`. From a terminal: `anchor compare harness2 jules`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/jules.json\n\n## Other comparisons with Harness² or Jules\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Jules](https://www.anchorterminal.com/compare/agent-zero-vs-jules.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Jules](https://www.anchorterminal.com/compare/aider-vs-jules.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Jules](https://www.anchorterminal.com/compare/amp-vs-jules.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Jules](https://www.anchorterminal.com/compare/antigravity-cli-vs-jules.md)\n- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)\n- [Auggie CLI vs Jules](https://www.anchorterminal.com/compare/auggie-vs-jules.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Jules](https://www.anchorterminal.com/compare/claude-code-vs-jules.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Jules](https://www.anchorterminal.com/compare/cline-vs-jules.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Crush vs Jules](https://www.anchorterminal.com/compare/crush-vs-jules.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Jules](https://www.anchorterminal.com/compare/cursor-cli-vs-jules.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs Jules](https://www.anchorterminal.com/compare/deepseek-harness-vs-jules.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Jules](https://www.anchorterminal.com/compare/devin-vs-jules.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Jules](https://www.anchorterminal.com/compare/droid-cli-vs-jules.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Jules](https://www.anchorterminal.com/compare/earendil-pi-vs-jules.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Jules](https://www.anchorterminal.com/compare/gemini-cli-vs-jules.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Jules](https://www.anchorterminal.com/compare/github-copilot-cli-vs-jules.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Jules](https://www.anchorterminal.com/compare/goose-vs-jules.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Junie CLI](https://www.anchorterminal.com/compare/harness2-vs-junie.md)\n- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)\n- [Harness² vs Kimi Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli.md)\n- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)\n- [Harness² vs mini-swe-agent](https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md)\n- [Harness² vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-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 Qoder CLI](https://www.anchorterminal.com/compare/harness2-vs-qoder-cli.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- [Harness² vs Rovo Dev CLI](https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli.md)\n- [Harness² vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harness2-vs-warp.md)\n- [HarnessRouter vs Jules](https://www.anchorterminal.com/compare/harnessrouter-vs-jules.md)\n- [Jules vs Junie CLI](https://www.anchorterminal.com/compare/jules-vs-junie.md)\n- [Jules vs Kilo Code CLI](https://www.anchorterminal.com/compare/jules-vs-kilo-code-cli.md)\n- [Jules vs Kimi Code CLI](https://www.anchorterminal.com/compare/jules-vs-kimi-code-cli.md)\n- [Jules vs Kiro CLI](https://www.anchorterminal.com/compare/jules-vs-kiro-cli.md)\n- [Jules vs mini-swe-agent](https://www.anchorterminal.com/compare/jules-vs-mini-swe-agent.md)\n- [Jules vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/jules-vs-mistral-vibe-cli.md)\n- [Jules vs Muse Code](https://www.anchorterminal.com/compare/jules-vs-muse-code.md)\n- [Jules vs OpenAI Codex](https://www.anchorterminal.com/compare/jules-vs-openai-codex.md)\n- [Jules vs OpenCode](https://www.anchorterminal.com/compare/jules-vs-opencode.md)\n- [Jules vs OpenHands](https://www.anchorterminal.com/compare/jules-vs-openhands.md)\n- [Jules vs Prime Agent](https://www.anchorterminal.com/compare/jules-vs-prime-agent.md)\n- [Jules vs Qoder CLI](https://www.anchorterminal.com/compare/jules-vs-qoder-cli.md)\n- [Jules vs Qwen Code](https://www.anchorterminal.com/compare/jules-vs-qwen-code.md)\n- [Jules vs Mirror CLI](https://www.anchorterminal.com/compare/jules-vs-reflection-mirror.md)\n- [Jules vs Rovo Dev CLI](https://www.anchorterminal.com/compare/jules-vs-rovo-dev-cli.md)\n- [Jules vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/jules-vs-warp.md)\n- [CLI Manager vs Jules](https://www.anchorterminal.com/compare/cli-manager-vs-jules.md)\n- [Harness vs Jules](https://www.anchorterminal.com/compare/harness-autonomous-vs-jules.md)\n- [Jules vs Paperclip](https://www.anchorterminal.com/compare/jules-vs-paperclip.md)\n- [Jules vs Parallax](https://www.anchorterminal.com/compare/jules-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": "2026-10-19", "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 Jules", "url": "" } ], "description": "Jules scores 44.5 (E) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 41.6", "Jules E 44.5", "scores" ], "h1": "Harness² vs Jules", "image": "https://www.anchorterminal.com/assets/og/compare-harness2-vs-jules.png", "path": "/compare/harness2-vs-jules", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Jules for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/harness2-vs-jules" }, "tokens": { "markdown": 3550, "slim": 780 }, "version": 1 }