{ "data": { "a": { "slug": "devin", "name": "Devin", "vendor": "Cognition AI, Inc.", "vendorUrl": "https://devin.ai", "kind": "harness", "category": "agent-harnesses", "summary": "Devin is Cognition's hosted coding agent. It works in its own cloud virtual machine to plan, edit code, run commands and open pull requests. Outside agents start and steer sessions through a REST API and a remote MCP server.", "url": "https://www.anchorterminal.com/tools/devin", "markdownUrl": "https://www.anchorterminal.com/tools/devin.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/devin.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/devin.json", "license": "Proprietary service under Cognition's Platform Terms of Service", "transports": [ "http" ], "remoteUrl": "https://mcp.devin.ai/mcp", "packages": [], "auth": "api-key", "authNotes": "A Bearer token with the `cog_` prefix on every request to https://api.devin.ai/v3. Service-user keys are provisioned by a person in Settings \u003e Devin API, shown once, and carry a role (Admin or Member on Teams, custom roles on Enterprise). Personal access tokens act as the user who made them and can expire. Legacy `apk_` keys work only with the deprecated v1 and v2 APIs. The MCP server takes the same keys, and enterprise keys and personal tokens add an `X-Org-Id` header. Access is self-serve, with no app review or sales approval for Teams.", "pricing": "freemium", "pricingNotes": "Free $0, Pro $20 a month, Max $200 a month, Teams $80 a month minimum with full seats at $40 each, Enterprise by quote (devin.ai/pricing, checked 2026-10-08). Paid plans include a daily or weekly usage quota, then prepaid on-demand credits described as usage at API pricing, with no unit rate on the page. The pricing page lists cloud agents from Pro upward, while the docs say Free includes limited Devin usage. Whether the API works on Free, and whether signup needs a card, wasn't established.", "priceSummary": "$20 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the v3 OpenAPI spec or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 13, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.devin.ai", "llmsTxt": "https://docs.devin.ai/llms.txt", "openapi": "https://docs.devin.ai/v3-openapi.yaml", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "hosted", "cloud-agent", "closed-source", "api-key", "rbac", "openapi", "llms-txt", "mcp", "status-page", "soc2", "freemium" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 55.7, "grade": "C", "agentReady": false, "rank": 724, "ranked": true, "rankOf": 1135, "categoryRank": 21, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 63, "payments": 20, "reliability": 30, "schema": 80, "security": 72, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "The v3 API is well specified, with a public OpenAPI 3.1 file covering 239 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records three critical and several major incidents on the cloud agent between 22 July and 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.", "bestFor": "A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.", "strengths": [ "Public OpenAPI 3.1 spec for the v3 API with 239 operations, each declaring 401, 403, 404, 409, 422 and 429 responses in RFC 9457 problem+json", "Service-user keys carry a role, every endpoint except GET /v3/self names the permission it needs, and audit logs list service users separately from people", "Security profiles can limit a session to a network allowlist, an MCP server allowlist, read-only git and a read-only Devin MCP", "Remote MCP server at mcp.devin.ai/mcp with 13 documented tools for sessions, playbooks, knowledge, schedules and repository documentation", "Dated release notes several times a week, the newest on 7 October 2026, and a separate API release notes page" ], "weaknesses": [ "www.devinstatus.com lists three critical incidents (22 July, 13 August, 24 September 2026) and six major ones on the cloud agent or web app since 10 July 2026", "No rate limit figures, Retry-After or backoff guidance found in the API docs, and v3 session creation has no idempotency key", "Customer data may be used for model training by default on self-serve plans. The opt-out is for paid plans only, per section 3.3.1 of the platform terms", "A person must sign up and provision the service user in the web app. No key-creation route exists for an agent starting from nothing", "No official SDK found, and the Devin MCP server was not found in the official MCP registry" ], "agentNotes": [ "Use a `cog_` service-user key with the Member role. Legacy `apk_` keys fail against v3 and the MCP server with 401 or 403", "Set `max_acu_limit` on every session you create. Usage is metered by the work done and has no published unit rate", "Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again", "Enterprise keys and personal access tokens must send `X-Org-Id` to the MCP server. Organisation-scoped keys resolve it automatically", "Create scheduled work as an automation. POST to the schedules endpoint returns 403 for migrated organisations since 24 September 2026" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.7 } ], "editorialScores": { "ergonomics": 62, "maintenance": 63, "payments": 20, "reliability": 30, "schema": 80, "security": 72, "transparency": 61 }, "provenanceScore": 77 }, "connect": { "http": "curl -X POST \"https://api.devin.ai/v3/organizations/$DEVIN_ORG_ID/sessions\" -H \"Authorization: Bearer $DEVIN_API_KEY\" -H \"Content-Type: application/json\" -d '{\"prompt\": \"Create a simple Python script that prints Hello World\"}'", "config": { "mcpServers": { "devin": { "headers": { "Authorization": "Bearer \u003cAPI_KEY\u003e", "X-Org-Id": "\u003cYOUR_ORG_ID\u003e" }, "serverUrl": "https://mcp.devin.ai/mcp" } } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/devin" }, "area": "frameworks", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 20, "note": "one user, daily and weekly usage quota" }, { "item": "Max plan", "unit": "month", "usd": 200, "note": "one user, larger weekly quota" }, { "item": "Teams full seat", "unit": "seat-month", "usd": 40, "note": "$80 a month minimum per team, flex seats free and billed from shared credits" } ], "provenance": { "legalEntity": "Cognition AI, Inc.", "domain": "devin.ai", "domainRegistered": "2022-12-06", "endpointOnVendorDomain": true, "terms": "https://cognition.com/legal/platform-terms-of-service", "privacy": "https://cognition.com/legal/privacy-policy", "statusPage": "https://www.devinstatus.com", "changelog": "https://docs.devin.ai/release-notes/overview", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Platform Terms of Service (last updated 30 June 2026) name Cognition AI, Inc. and govern the Cognition Platform for customers who register and use the services. Enterprise customers sign separate Enterprise Terms of Service.", "The privacy policy (last updated 9 March 2026) names Cognition AI, Inc and covers Devin and Windsurf as well as cognition.com. The data processing agreement gives the address 550 Third Street, San Francisco, CA 94107.", "devin.ai, cognition.com and api.devin.ai all return 404 for /.well-known/security.txt. The docs give security@cognition.ai for vulnerability reports.", "The API answers at api.devin.ai and the MCP server at mcp.devin.ai. status.devin.ai redirects to www.devinstatus.com.", "RDAP for devin.ai gives a registration date of 2022-12-06." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/devin.json", "live": { "slug": "devin", "probe": { "target": "https://mcp.devin.ai/mcp", "method": "get", "lastAt": "2026-10-18T19:13:38.16463911Z", "lastOk": true, "lastStatus": 406, "lastMs": 444, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 444, "p95ms24h": 553, "samples24h": 253, "samples30d": 2521, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 205, "ok": 205 } ] }, "vendorStatus": { "page": "https://www.devinstatus.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-18T19:17:26.014744725Z" }, "securityTxt": { "url": "https://devin.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:53:14.290052543Z" }, "llmsTxt": { "url": "https://docs.devin.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:24:51.995648304Z" }, "domain": { "domain": "devin.ai", "registered": "2022-12-06", "source": "https://rdap.identitydigital.services/rdap/domain/devin.ai", "checkedAt": "2026-10-18T13:30:21.547724429Z" }, "pages": [ { "url": "https://docs.devin.ai/release-notes/overview", "kind": "changelog", "status": 304, "checkedAt": "2026-10-17T23:00:53.646759957Z", "changedAt": "2026-10-17T22:49:44.25820372Z", "fingerprint": "58f909a8fd53" }, { "url": "https://cognition.com/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-17T22:57:51.756553345Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0ab177a921b1" }, { "url": "https://cognition.com/legal/platform-terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-10-17T22:57:49.737098368Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e794136b2fe5" } ], "updatedAt": "2026-10-18T19:17:26.014744725Z" } }, "answer": "Devin scores 55.7 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing.", "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": "Cognition AI, Inc.", "b": "Google (Google Research)", "name": "Vendor" }, { "a": "https://mcp.devin.ai/mcp", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Cognition's Platform Terms of Service", "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": "13", "b": "none", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-07", "b": "2026-10-08", "name": "Last release" }, { "a": "2026-06-30", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-03-09", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "", "name": "Terms restrict automated access" }, { "a": "yes", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "4.2k stars", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Devin scores 55.7 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Devin or Harness²?" }, { "answer": "No open-source release is listed for Devin. 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 Devin and Harness² open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 30 against 20", "Schema \u0026 documentation, 80 against 51", "Security \u0026 auth, 72 against 44", "Maintenance \u0026 community, 63 against 36", "Transparency \u0026 trust, 69 against 44" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.", "slug": "devin", "watchFor": "www.devinstatus.com lists three critical incidents (22 July, 13 August, 24 September 2026) and six major ones on the cloud agent or web app since 10 July 2026" }, { "aheadOn": [ "Payments \u0026 pricing, 40 against 20" ], "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" } ], "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-devin.json", "title": "Agent Zero vs Devin", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-devin" }, { "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-devin.json", "title": "Aider vs Devin", "url": "https://www.anchorterminal.com/compare/aider-vs-devin" }, { "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/amp-vs-devin.json", "title": "Amp vs Devin", "url": "https://www.anchorterminal.com/compare/amp-vs-devin" }, { "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-devin.json", "title": "Antigravity CLI vs Devin", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-devin" }, { "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-devin.json", "title": "Claude Code vs Devin", "url": "https://www.anchorterminal.com/compare/claude-code-vs-devin" }, { "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-devin.json", "title": "Cline vs Devin", "url": "https://www.anchorterminal.com/compare/cline-vs-devin" }, { "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-devin.json", "title": "Cursor CLI vs Devin", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-devin" }, { "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-droid-cli.json", "title": "Devin vs Droid CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-earendil-pi.json", "title": "Devin vs Pi", "url": "https://www.anchorterminal.com/compare/devin-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-gemini-cli.json", "title": "Devin vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-github-copilot-cli.json", "title": "Devin vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-goose.json", "title": "Devin vs goose", "url": "https://www.anchorterminal.com/compare/devin-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harnessrouter.json", "title": "Devin vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/devin-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-kilo-code-cli.json", "title": "Devin vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-kiro-cli.json", "title": "Devin vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-muse-code.json", "title": "Devin vs Muse Code", "url": "https://www.anchorterminal.com/compare/devin-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-openai-codex.json", "title": "Devin vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/devin-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-opencode.json", "title": "Devin vs OpenCode", "url": "https://www.anchorterminal.com/compare/devin-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-openhands.json", "title": "Devin vs OpenHands", "url": "https://www.anchorterminal.com/compare/devin-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/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/devin-vs-qwen-code.json", "title": "Devin vs Qwen Code", "url": "https://www.anchorterminal.com/compare/devin-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-reflection-mirror.json", "title": "Devin vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-reflection-mirror" }, { "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" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-devin.json", "title": "CLI Manager vs Devin", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harness-autonomous.json", "title": "Devin vs Harness", "url": "https://www.anchorterminal.com/compare/devin-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-paperclip.json", "title": "Devin vs Paperclip", "url": "https://www.anchorterminal.com/compare/devin-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-parallax-agents.json", "title": "Devin vs Parallax", "url": "https://www.anchorterminal.com/compare/devin-vs-parallax-agents" } ], "scores": [ { "by": 10, "devin": 30, "edge": "devin", "harness2": 20, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 29, "devin": 80, "edge": "devin", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 3, "devin": 62, "edge": "devin", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 28, "devin": 72, "edge": "devin", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "devin": 20, "edge": "harness2", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 27, "devin": 63, "edge": "devin", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 25, "devin": 69, "edge": "devin", "harness2": 44, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Devin scores 55.7 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing. Both do agent harnesses.", "tutorials": [], "verdicts": { "devin": "The v3 API is well specified, with a public OpenAPI 3.1 file covering 239 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records three critical and several major incidents on the cloud agent between 22 July and 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.", "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/devin-vs-harness2", "json": "https://www.anchorterminal.com/compare/devin-vs-harness2.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/devin-vs-harness2.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/devin-vs-harness2.min.md" }, "markdown": "Devin scores 55.7 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing. Both do agent harnesses.\n\n- Devin: grade C, 55.7/100, rank #724 of 1135. Markdown https://www.anchorterminal.com/tools/devin.md · JSON https://www.anchorterminal.com/api/v1/tools/devin.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### Devin (C)\n\nGood for: A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.\n\nAhead on:\n- Reliability, 30 against 20\n- Schema \u0026 documentation, 80 against 51\n- Security \u0026 auth, 72 against 44\n- Maintenance \u0026 community, 63 against 36\n- Transparency \u0026 trust, 69 against 44\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: www.devinstatus.com lists three critical incidents (22 July, 13 August, 24 September 2026) and six major ones on the cloud agent or web app since 10 July 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- Payments \u0026 pricing, 40 against 20\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\n## Score by category\n\n| Category | Weight | Devin | Harness² | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 30 | 20 | Devin +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 51 | Devin +29 |\n| Agent ergonomics | 13% (16.2 this run) | 62 | 59 | Devin +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 72 | 44 | Devin +28 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 40 | Harness² +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 63 | 36 | Devin +27 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 69 | 44 | Devin +25 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **55.7 · C** | **41.6 · E** | |\n\n## Facts side by side\n\n| Fact | Devin | Harness² |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Cognition AI, Inc. | Google (Google Research) |\n| Hosted endpoint | `https://mcp.devin.ai/mcp` | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Proprietary service under Cognition's Platform Terms of Service | 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| Tools exposed | 13 | none |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-07 | 2026-10-08 |\n| Terms last updated | 2026-06-30 | no document linked |\n| Privacy policy last updated | 2026-03-09 | no document linked |\n| Customer content may train models | yes, with an opt-out | |\n| Terms restrict automated access | not found in the text | |\n| Terms restrict benchmarking | yes | |\n| Terms or service can change without notice | not found in the text | |\n| Arbitration or class-action waiver | yes | |\n| Popularity | none | 4.2k stars |\n| Agent reviews | none | 2.5/5 (4) |\n\n## Verdicts\n\n**Devin.** The v3 API is well specified, with a public OpenAPI 3.1 file covering 239 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records three critical and several major incidents on the cloud agent between 22 July and 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.\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### Devin\n\n1. Use a `cog_` service-user key with the Member role. Legacy `apk_` keys fail against v3 and the MCP server with 401 or 403\n2. Set `max_acu_limit` on every session you create. Usage is metered by the work done and has no published unit rate\n3. Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again\n4. Enterprise keys and personal access tokens must send `X-Org-Id` to the MCP server. Organisation-scoped keys resolve it automatically\n5. Create scheduled work as an automation. POST to the schedules endpoint returns 403 for migrated organisations since 24 September 2026\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, Devin or Harness²?\n\nDevin scores 55.7 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing.\n\n### Are Devin and Harness² open source?\n\nNo open-source release is listed for Devin. 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/devin-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/devin-vs-harness2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"devin\", \"b\": \"harness2\"}`. From a terminal: `anchor compare devin harness2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/devin.json and https://www.anchorterminal.com/api/v1/tools/harness2.json\n\n## Other comparisons with Devin or Harness²\n\n- [Agent Zero vs Devin](https://www.anchorterminal.com/compare/agent-zero-vs-devin.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Aider vs Devin](https://www.anchorterminal.com/compare/aider-vs-devin.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Amp vs Devin](https://www.anchorterminal.com/compare/amp-vs-devin.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Antigravity CLI vs Devin](https://www.anchorterminal.com/compare/antigravity-cli-vs-devin.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Claude Code vs Devin](https://www.anchorterminal.com/compare/claude-code-vs-devin.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Cline vs Devin](https://www.anchorterminal.com/compare/cline-vs-devin.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cursor CLI vs Devin](https://www.anchorterminal.com/compare/cursor-cli-vs-devin.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Devin vs Droid CLI](https://www.anchorterminal.com/compare/devin-vs-droid-cli.md)\n- [Devin vs Pi](https://www.anchorterminal.com/compare/devin-vs-earendil-pi.md)\n- [Devin vs Gemini CLI](https://www.anchorterminal.com/compare/devin-vs-gemini-cli.md)\n- [Devin vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/devin-vs-github-copilot-cli.md)\n- [Devin vs goose](https://www.anchorterminal.com/compare/devin-vs-goose.md)\n- [Devin vs HarnessRouter](https://www.anchorterminal.com/compare/devin-vs-harnessrouter.md)\n- [Devin vs Kilo Code CLI](https://www.anchorterminal.com/compare/devin-vs-kilo-code-cli.md)\n- [Devin vs Kiro CLI](https://www.anchorterminal.com/compare/devin-vs-kiro-cli.md)\n- [Devin vs Muse Code](https://www.anchorterminal.com/compare/devin-vs-muse-code.md)\n- [Devin vs OpenAI Codex](https://www.anchorterminal.com/compare/devin-vs-openai-codex.md)\n- [Devin vs OpenCode](https://www.anchorterminal.com/compare/devin-vs-opencode.md)\n- [Devin vs OpenHands](https://www.anchorterminal.com/compare/devin-vs-openhands.md)\n- [Devin vs Prime Agent](https://www.anchorterminal.com/compare/devin-vs-prime-agent.md)\n- [Devin vs Qwen Code](https://www.anchorterminal.com/compare/devin-vs-qwen-code.md)\n- [Devin vs Mirror CLI](https://www.anchorterminal.com/compare/devin-vs-reflection-mirror.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- [CLI Manager vs Devin](https://www.anchorterminal.com/compare/cli-manager-vs-devin.md)\n- [Devin vs Harness](https://www.anchorterminal.com/compare/devin-vs-harness-autonomous.md)\n- [Devin vs Paperclip](https://www.anchorterminal.com/compare/devin-vs-paperclip.md)\n- [Devin vs Parallax](https://www.anchorterminal.com/compare/devin-vs-parallax-agents.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Devin vs Harness²", "url": "" } ], "description": "Devin scores 55.7 (C) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Devin C 55.7", "Harness² E 41.6", "scores" ], "h1": "Devin vs Harness²", "image": "https://www.anchorterminal.com/assets/og/compare-devin-vs-harness2.png", "path": "/compare/devin-vs-harness2", "published": "2026-10-01", "section": "tools", "title": "Devin vs Harness² for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/devin-vs-harness2" }, "tokens": { "markdown": 3000, "slim": 780 }, "version": 1 }