{ "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", "dns": "harness2.grade.anchorterminal.com", "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": 42, "grade": "E", "agentReady": false, "rank": 1290, "ranked": true, "rankOf": 1510, "categoryRank": 51, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 49 }, "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": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 42 } ], "editorialScores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 48 }, "provenanceScore": 50, "checked": { "categories": { "ergonomics": "2026-10-18", "maintenance": "2026-10-18", "payments": "2026-10-18", "reliability": "2026-10-18", "schema": "2026-10-18", "security": "2026-10-18", "transparency": "2026-10-18" }, "last": "2026-10-18", "lastMoved": "2026-10-27", "oldest": "2026-10-18", "stale": false, "staleAfterDays": 90 } }, "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": 50 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harness2.json", "live": { "slug": "harness2", "githubStars": 22938, "securityTxt": { "url": "https://harness2.github.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:54.53290748Z" }, "domain": { "domain": "github.io", "checkedAt": "2026-11-01T14:18:40.30630652Z" }, "github": { "repo": "google-research/harness2", "checkedAt": "2026-11-02T08:51:52.491406601Z", "stars": 21980, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T02:17:27Z", "openIssues": 36, "openPRs": 103, "issuesOpened90d": 41, "issuesClosed90d": 5, "prsMerged90d": 17, "replies": { "sampled": 25, "unanswered": 23, "medianDays": 12.1 } }, "updatedAt": "2026-11-07T15:59:54.53290748Z" } }, "answer": "Orca scores 57.4 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories.", "b": { "slug": "orca", "name": "Orca", "vendor": "Lovecast Inc.", "vendorUrl": "https://www.onorca.dev", "kind": "harness", "category": "agent-harnesses", "summary": "Orca is an open-source app that runs Claude Code, Codex and other coding agents in parallel, each in its own worktree, in chat or terminal, on a laptop or in the cloud, with an orchestrator that splits tasks across workers.", "url": "https://www.anchorterminal.com/tools/orca", "markdownUrl": "https://www.anchorterminal.com/tools/orca.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/orca.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/orca.json", "dns": "orca.grade.anchorterminal.com", "repo": "https://github.com/stablyai/orca", "license": "MIT", "transports": [], "packages": [], "auth": "none", "pricing": "free", "pricingNotes": "Free and open source. You pay for the coding agents it runs, through your own subscriptions or API keys (checked 2026-11-07).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol in the repository or README (checked 2026-11-07).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-07" }, "docsUrl": "https://www.onorca.dev/docs", "capabilities": [ "agent.harness", "agent.multi-agent" ], "tags": [ "open-source", "mit", "desktop-app", "mobile", "cli", "telemetry", "new" ], "lastRelease": "2026-11-06", "graded": true, "anchor": { "graded": true, "score": 57.4, "grade": "C", "agentReady": false, "rank": 795, "ranked": true, "rankOf": 1510, "categoryRank": 25, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 75, "payments": 40, "reliability": 58, "schema": 65, "security": 43, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-07" }, "negative": 0, "verdict": "An open-source orchestrator for coding agents with worker agents in their own worktrees, chat and terminal views, a browser and a CLI, on desktop and mobile, with heavy test automation. It collects anonymous usage data by default, and the cloud option's pricing wasn't found.", "bestFor": "Developers who want an orchestrator agent to split work across parallel coding agents, on desktop or mobile.", "strengths": [ "An orchestrator agent splits a task across worker agents in their own workspaces", "Chat UI or the raw CLI, switching without losing context", "Desktop and mobile apps and a CLI", "MIT, with extensive unit and end-to-end CI" ], "weaknesses": [ "Anonymous usage data collected by default, with an opt-out", "Cloud pricing not found on the pages read", "No changelog file" ], "agentNotes": [ "See the telemetry docs on onorca.dev to opt out of anonymous usage data", "Use the orchestration CLI to hand a large task to one agent that starts workers" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.4 } ], "editorialScores": { "ergonomics": 70, "maintenance": 75, "payments": 40, "reliability": 58, "schema": 65, "security": 43, "transparency": 68 }, "provenanceScore": 40, "checked": { "categories": { "ergonomics": "2026-11-07", "maintenance": "2026-11-07", "payments": "2026-11-07", "reliability": "2026-11-07", "schema": "2026-11-07", "security": "2026-11-07", "transparency": "2026-11-07" }, "last": "2026-11-07", "oldest": "2026-11-07", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "Download from the releases page or Homebrew (Casks in the repository)" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/orca" }, "area": "frameworks", "provenance": { "legalEntity": "Lovecast Inc.", "domain": "onorca.dev", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-07", "notes": [ "The licence names Lovecast Inc.. The repository is github.com/stablyai/orca." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/orca.json", "live": { "slug": "orca", "securityTxt": { "url": "https://onorca.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:18.358018303Z" }, "updatedAt": "2026-11-07T16:01:18.358018303Z" } }, "edges": [ { "by": 39, "category": "maintenance", "leads": "orca", "name": "Maintenance \u0026 community", "reasons": { "a": "0.1.0, first committed on 8 October 2026, with a README fix on 13 October (30). No tags, releases or dated changelog entries (0). 42 pull requests (41 from outside contributors, one from Dependabot) and 6 issues open on 18 October, against one pull request and no issues closed. No outside change is on main, which has three commits by the authors, and reply times couldn't be read (3 of 25). Not on PyPI and no SDK (0). No CI. Dependencies are pinned by version and upstream checkouts by commit, a ruff configuration is in pyproject.toml, and Dependabot's litellm bump of 8 October is still open (3 of 10). 36 in all.", "b": "Tags to v1.4.251 and commits on 6 November 2026 (30). Many releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current builds (15). Extensive CI (10). 30 + 20 + 0 + 15 + 10 = 75." }, "scores": { "a": 36, "b": 75 } }, { "by": 38, "category": "reliability", "leads": "orca", "name": "Reliability", "reasons": { "a": "Local-package reading. Not on PyPI (the release feed for harness2 answers 404). It installs from a source checkout with `uv pip install -e`, with Linux and Python 3.12 stated (the package allows 3.13), plus Node.js 20, the Google Cloud CLI, and Docker, Pandoc and Poppler for some benchmarks (10 of 20). No CI workflow in the repository. tests/test_workflow.py holds five unit tests over the deterministic demo, which needs no credentials (5 of 25). Six issues and 42 pull requests were open on 18 October, the pull requests mostly fixes by their titles, such as the missing .env.example, report failures, seeds lost between refinement and grading, and resume. None is merged and no issue is closed. Issue text and replies couldn't be read (5 of 25). No tags or changelog (0). Version 0.1.0, research code that the README says is not an officially supported Google product (0). 20 in all.", "b": "Local software. Desktop and mobile builds and a Homebrew cask (20). Unit, end-to-end and platform test workflows; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Tags to v1.4.251, no changelog file (8). Version 1.4 (15). 20 + 15 + 0 + 8 + 15 = 58." }, "scores": { "a": 20, "b": 58 } }, { "by": 14, "category": "schema", "leads": "orca", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, but the quick start's `cp .env.example .env` fails because the file isn't shipped (8 of 15). Version 0.1.0 with no changelog (3 of 15). 51 in all.", "b": "Harness reading. A docs site with CLI orchestration and native chat pages (65)." }, "scores": { "a": 51, "b": 65 } }, { "by": 11, "category": "ergonomics", "leads": "orca", "name": "Agent ergonomics", "reasons": { "a": "Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all.", "b": "Harness reading. An orchestrator agent that splits work across workers in their own workspaces, chat or raw CLI, a browser and a CLI in one app (70)." }, "scores": { "a": 59, "b": 70 } }, { "by": 5, "category": "transparency", "leads": "orca", "name": "Transparency \u0026 trust", "reasons": { "a": "Apache-2.0 under Google LLC, with each bundled runner's licence and provenance file and a hash list. The WorkBuddy runners carry Tencent's custom licence, which has an EU territorial limitation (26 of 30). The docs list every host setup contacts and say credentials, generated configuration and run artefacts are not release assets. No privacy statement covers the package, and task data goes to the configured model provider (12 of 30). No deprecation policy or notices for the 0.1.0 research release (0). No telemetry found in the source, and the docs don't say either way. OpenCode's telemetry is turned off only in the WorkBuddy configs (10 of 20). 48 in all.", "b": "MIT (30). Privacy and telemetry docs on the site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68." }, "scores": { "a": 49, "b": 54 } } ], "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Lovecast Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-11-06", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "4.2k stars", "b": "none", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Orca scores 57.4 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Harness² or Orca?" }, { "answer": "Yes. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).). Orca is open source (MIT).", "question": "Are Harness² and Orca open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "slug": "harness2", "watchFor": "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI" }, { "aheadOn": [ "Reliability, 58 against 20", "Schema \u0026 documentation, 65 against 51", "Agent ergonomics, 70 against 59", "Maintenance \u0026 community, 75 against 36", "Transparency \u0026 trust, 54 against 49" ], "also": null, "goodFor": "Developers who want an orchestrator agent to split work across parallel coding agents, on desktop or mobile.", "slug": "orca", "watchFor": "Anonymous usage data collected by default, with an opt-out" } ], "history": { "harness2": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.4, "from": 41.6, "fromGrade": "E", "to": 42, "toGrade": "E" } ], "orca": null }, "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-orca.json", "title": "Agent Zero vs Orca", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-orca" }, { "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-orca.json", "title": "Aider vs Orca", "url": "https://www.anchorterminal.com/compare/aider-vs-orca" }, { "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-orca.json", "title": "Amp vs Orca", "url": "https://www.anchorterminal.com/compare/amp-vs-orca" }, { "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-orca.json", "title": "Antigravity CLI vs Orca", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-orca" }, { "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-orca.json", "title": "Auggie CLI vs Orca", "url": "https://www.anchorterminal.com/compare/auggie-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-harness2.json", "title": "AXLR vs Harness²", "url": "https://www.anchorterminal.com/compare/axlr-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-orca.json", "title": "AXLR vs Orca", "url": "https://www.anchorterminal.com/compare/axlr-vs-orca" }, { "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-orca.json", "title": "Claude Code vs Orca", "url": "https://www.anchorterminal.com/compare/claude-code-vs-orca" }, { "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-orca.json", "title": "Cline vs Orca", "url": "https://www.anchorterminal.com/compare/cline-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-harness2.json", "title": "Conductor vs Harness²", "url": "https://www.anchorterminal.com/compare/conductor-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-orca.json", "title": "Conductor vs Orca", "url": "https://www.anchorterminal.com/compare/conductor-vs-orca" }, { "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-orca.json", "title": "Crush vs Orca", "url": "https://www.anchorterminal.com/compare/crush-vs-orca" }, { "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-orca.json", "title": "Cursor CLI vs Orca", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-orca" }, { "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-orca.json", "title": "DeepSeek Harness (dsh) vs Orca", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.json", "title": "dsh-superagent (DeepSeek) vs Harness²", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-orca.json", "title": "dsh-superagent (DeepSeek) vs Orca", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-orca" }, { "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-orca.json", "title": "Devin vs Orca", "url": "https://www.anchorterminal.com/compare/devin-vs-orca" }, { "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-orca.json", "title": "Droid CLI vs Orca", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-orca" }, { "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-orca.json", "title": "Pi vs Orca", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-harness2.json", "title": "Emdash vs Harness²", "url": "https://www.anchorterminal.com/compare/emdash-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-orca.json", "title": "Emdash vs Orca", "url": "https://www.anchorterminal.com/compare/emdash-vs-orca" }, { "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-orca.json", "title": "Gemini CLI vs Orca", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-orca" }, { "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-orca.json", "title": "GitHub Copilot CLI vs Orca", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-orca" }, { "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-orca.json", "title": "goose vs Orca", "url": "https://www.anchorterminal.com/compare/goose-vs-orca" }, { "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-jules.json", "title": "Harness² vs Jules", "url": "https://www.anchorterminal.com/compare/harness2-vs-jules" }, { "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-letta.json", "title": "Harness² vs Letta", "url": "https://www.anchorterminal.com/compare/harness2-vs-letta" }, { "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-minimax-code.json", "title": "Harness² vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-minimax-code" }, { "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-agents-api.json", "title": "Harness² vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api" }, { "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-openmausbot.json", "title": "Harness² vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/harness2-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-paseo.json", "title": "Harness² vs Paseo", "url": "https://www.anchorterminal.com/compare/harness2-vs-paseo" }, { "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-sculptor.json", "title": "Harness² vs Sculptor", "url": "https://www.anchorterminal.com/compare/harness2-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-t3-code.json", "title": "Harness² vs T3 Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-traycer.json", "title": "Harness² vs Traycer", "url": "https://www.anchorterminal.com/compare/harness2-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-unstoppable.json", "title": "Harness² vs Unstoppable", "url": "https://www.anchorterminal.com/compare/harness2-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-verdent.json", "title": "Harness² vs Verdent", "url": "https://www.anchorterminal.com/compare/harness2-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.json", "title": "Harness² vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/harness2-vs-vibe-trading" }, { "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-orca.json", "title": "HarnessRouter vs Orca", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-orca.json", "title": "Jules vs Orca", "url": "https://www.anchorterminal.com/compare/jules-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-orca.json", "title": "Junie CLI vs Orca", "url": "https://www.anchorterminal.com/compare/junie-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-orca.json", "title": "Kilo Code CLI vs Orca", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-orca.json", "title": "Kimi Code CLI vs Orca", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-orca.json", "title": "Kiro CLI vs Orca", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/letta-vs-orca.json", "title": "Letta vs Orca", "url": "https://www.anchorterminal.com/compare/letta-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-orca.json", "title": "mini-swe-agent vs Orca", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-orca.json", "title": "MiniMax Code vs Orca", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-orca.json", "title": "Mistral Vibe CLI vs Orca", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-orca.json", "title": "Muse Code vs Orca", "url": "https://www.anchorterminal.com/compare/muse-code-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-orca.json", "title": "OpenAI Agents API vs Orca", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-orca.json", "title": "OpenAI Codex vs Orca", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-orca.json", "title": "OpenCode vs Orca", "url": "https://www.anchorterminal.com/compare/opencode-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-orca.json", "title": "OpenHands vs Orca", "url": "https://www.anchorterminal.com/compare/openhands-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-paseo.json", "title": "Orca vs Paseo", "url": "https://www.anchorterminal.com/compare/orca-vs-paseo" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-prime-agent.json", "title": "Orca vs Prime Agent", "url": "https://www.anchorterminal.com/compare/orca-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-qoder-cli.json", "title": "Orca vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/orca-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-qwen-code.json", "title": "Orca vs Qwen Code", "url": "https://www.anchorterminal.com/compare/orca-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-reflection-mirror.json", "title": "Orca vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/orca-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-rovo-dev-cli.json", "title": "Orca vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/orca-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-sculptor.json", "title": "Orca vs Sculptor", "url": "https://www.anchorterminal.com/compare/orca-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-t3-code.json", "title": "Orca vs T3 Code", "url": "https://www.anchorterminal.com/compare/orca-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-traycer.json", "title": "Orca vs Traycer", "url": "https://www.anchorterminal.com/compare/orca-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-unstoppable.json", "title": "Orca vs Unstoppable", "url": "https://www.anchorterminal.com/compare/orca-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-verdent.json", "title": "Orca vs Verdent", "url": "https://www.anchorterminal.com/compare/orca-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-vibe-trading.json", "title": "Orca vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/orca-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-warp.json", "title": "Orca vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/orca-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-orca.json", "title": "Clawboo vs Orca", "url": "https://www.anchorterminal.com/compare/clawboo-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-orca.json", "title": "CLI Manager vs Orca", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-orca.json", "title": "Harness vs Orca", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/openmausbot-vs-orca.json", "title": "OpenMausBot vs Orca", "url": "https://www.anchorterminal.com/compare/openmausbot-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-paperclip.json", "title": "Orca vs Paperclip", "url": "https://www.anchorterminal.com/compare/orca-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-parallax-agents.json", "title": "Orca vs Parallax", "url": "https://www.anchorterminal.com/compare/orca-vs-parallax-agents" } ], "panel": null, "scores": [ { "by": 38, "edge": "orca", "harness2": 20, "key": "reliability", "name": "Reliability", "orca": 58, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "edge": "orca", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "orca": 65, "weight": 13 }, { "by": 11, "edge": "orca", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "orca": 70, "weight": 13 }, { "by": 1, "edge": "harness2", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "orca": 43, "weight": 14 }, { "by": 0, "edge": "", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "orca": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 39, "edge": "orca", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "orca": 75, "weight": 7 }, { "by": 5, "edge": "orca", "harness2": 49, "key": "transparency", "name": "Transparency \u0026 trust", "orca": 54, "weight": 7 } ], "summary": "Orca scores 57.4 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Both do agent harnesses.", "tasks": null, "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.", "orca": "An open-source orchestrator for coding agents with worker agents in their own worktrees, chat and terminal views, a browser and a CLI, on desktop and mobile, with heavy test automation. It collects anonymous usage data by default, and the cloud option's pricing wasn't found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-orca", "json": "https://www.anchorterminal.com/compare/harness2-vs-orca.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-orca.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-orca.min.md" }, "markdown": "Orca scores 57.4 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Both do agent harnesses.\n\n- Harness²: grade E, 42/100, rank #1290 of 1510. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json\n- Orca: grade C, 57.4/100, rank #795 of 1510. Markdown https://www.anchorterminal.com/tools/orca.md · JSON https://www.anchorterminal.com/api/v1/tools/orca.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1500 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\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### Orca (C)\n\nGood for: Developers who want an orchestrator agent to split work across parallel coding agents, on desktop or mobile.\n\nAhead on:\n- Reliability, 58 against 20\n- Schema \u0026 documentation, 65 against 51\n- Agent ergonomics, 70 against 59\n- Maintenance \u0026 community, 75 against 36\n- Transparency \u0026 trust, 54 against 49\n\nWatch for: Anonymous usage data collected by default, with an opt-out\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Orca +39\n\n- Harness² (36): 0.1.0, first committed on 8 October 2026, with a README fix on 13 October (30). No tags, releases or dated changelog entries (0). 42 pull requests (41 from outside contributors, one from Dependabot) and 6 issues open on 18 October, against one pull request and no issues closed. No outside change is on main, which has three commits by the authors, and reply times couldn't be read (3 of 25). Not on PyPI and no SDK (0). No CI. Dependencies are pinned by version and upstream checkouts by commit, a ruff configuration is in pyproject.toml, and Dependabot's litellm bump of 8 October is still open (3 of 10). 36 in all.\n- Orca (75): Tags to v1.4.251 and commits on 6 November 2026 (30). Many releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current builds (15). Extensive CI (10). 30 + 20 + 0 + 15 + 10 = 75.\n\n### Reliability: Orca +38\n\n- Harness² (20): Local-package reading. Not on PyPI (the release feed for harness2 answers 404). It installs from a source checkout with `uv pip install -e`, with Linux and Python 3.12 stated (the package allows 3.13), plus Node.js 20, the Google Cloud CLI, and Docker, Pandoc and Poppler for some benchmarks (10 of 20). No CI workflow in the repository. tests/test_workflow.py holds five unit tests over the deterministic demo, which needs no credentials (5 of 25). Six issues and 42 pull requests were open on 18 October, the pull requests mostly fixes by their titles, such as the missing .env.example, report failures, seeds lost between refinement and grading, and resume. None is merged and no issue is closed. Issue text and replies couldn't be read (5 of 25). No tags or changelog (0). Version 0.1.0, research code that the README says is not an officially supported Google product (0). 20 in all.\n- Orca (58): Local software. Desktop and mobile builds and a Homebrew cask (20). Unit, end-to-end and platform test workflows; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Tags to v1.4.251, no changelog file (8). Version 1.4 (15). 20 + 15 + 0 + 8 + 15 = 58.\n\n### Schema \u0026 documentation: Orca +14\n\n- Harness² (51): Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, but the quick start's `cp .env.example .env` fails because the file isn't shipped (8 of 15). Version 0.1.0 with no changelog (3 of 15). 51 in all.\n- Orca (65): Harness reading. A docs site with CLI orchestration and native chat pages (65).\n\n### Agent ergonomics: Orca +11\n\n- Harness² (59): Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all.\n- Orca (70): Harness reading. An orchestrator agent that splits work across workers in their own workspaces, chat or raw CLI, a browser and a CLI in one app (70).\n\n### Transparency \u0026 trust: Orca +5\n\n- Harness² (49): Apache-2.0 under Google LLC, with each bundled runner's licence and provenance file and a hash list. The WorkBuddy runners carry Tencent's custom licence, which has an EU territorial limitation (26 of 30). The docs list every host setup contacts and say credentials, generated configuration and run artefacts are not release assets. No privacy statement covers the package, and task data goes to the configured model provider (12 of 30). No deprecation policy or notices for the 0.1.0 research release (0). No telemetry found in the source, and the docs don't say either way. OpenCode's telemetry is turned off only in the WorkBuddy configs (10 of 20). 48 in all.\n- Orca (54): MIT (30). Privacy and telemetry docs on the site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68.\n\n## Score by category\n\n| Category | Weight | Harness² | Orca | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 58 | Orca +38 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 65 | Orca +14 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 70 | Orca +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 43 | Harness² +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 75 | Orca +39 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 49 | 54 | Orca +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **42 · E** | **57.4 · C** | |\n\n## Facts side by side\n\n| Fact | Harness² | Orca |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Lovecast Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-08 | 2026-11-06 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Popularity | 4.2k stars | none |\n| Agent reviews | 2.5/5 (4) | none |\n\n## How the scores have moved\n\n### Harness²\n\n- +0.4 on 27 October 2026: checklist\n\n### Orca\n\nNo score change since it was listed.\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**Orca.** An open-source orchestrator for coding agents with worker agents in their own worktrees, chat and terminal views, a browser and a CLI, on desktop and mobile, with heavy test automation. It collects anonymous usage data by default, and the cloud option's pricing wasn't found.\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### Orca\n\n1. See the telemetry docs on onorca.dev to opt out of anonymous usage data\n2. Use the orchestration CLI to hand a large task to one agent that starts workers\n\n## Questions\n\n### Which is better for AI agents, Harness² or Orca?\n\nOrca scores 57.4 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories.\n\n### Are Harness² and Orca open source?\n\nYes. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).). Orca is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-orca.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-orca.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"orca\"}`. From a terminal: `anchor compare harness2 orca`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/orca.json\n\n## Other comparisons with Harness² or Orca\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Orca](https://www.anchorterminal.com/compare/agent-zero-vs-orca.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Orca](https://www.anchorterminal.com/compare/aider-vs-orca.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Orca](https://www.anchorterminal.com/compare/amp-vs-orca.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Orca](https://www.anchorterminal.com/compare/antigravity-cli-vs-orca.md)\n- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)\n- [Auggie CLI vs Orca](https://www.anchorterminal.com/compare/auggie-vs-orca.md)\n- [AXLR vs Harness²](https://www.anchorterminal.com/compare/axlr-vs-harness2.md)\n- [AXLR vs Orca](https://www.anchorterminal.com/compare/axlr-vs-orca.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Orca](https://www.anchorterminal.com/compare/claude-code-vs-orca.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Orca](https://www.anchorterminal.com/compare/cline-vs-orca.md)\n- [Conductor vs Harness²](https://www.anchorterminal.com/compare/conductor-vs-harness2.md)\n- [Conductor vs Orca](https://www.anchorterminal.com/compare/conductor-vs-orca.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Crush vs Orca](https://www.anchorterminal.com/compare/crush-vs-orca.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Orca](https://www.anchorterminal.com/compare/cursor-cli-vs-orca.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs Orca](https://www.anchorterminal.com/compare/deepseek-harness-vs-orca.md)\n- [dsh-superagent (DeepSeek) vs Harness²](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.md)\n- [dsh-superagent (DeepSeek) vs Orca](https://www.anchorterminal.com/compare/deepseek-superagent-vs-orca.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Orca](https://www.anchorterminal.com/compare/devin-vs-orca.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Orca](https://www.anchorterminal.com/compare/droid-cli-vs-orca.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Orca](https://www.anchorterminal.com/compare/earendil-pi-vs-orca.md)\n- [Emdash vs Harness²](https://www.anchorterminal.com/compare/emdash-vs-harness2.md)\n- [Emdash vs Orca](https://www.anchorterminal.com/compare/emdash-vs-orca.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Orca](https://www.anchorterminal.com/compare/gemini-cli-vs-orca.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Orca](https://www.anchorterminal.com/compare/github-copilot-cli-vs-orca.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Orca](https://www.anchorterminal.com/compare/goose-vs-orca.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Jules](https://www.anchorterminal.com/compare/harness2-vs-jules.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 Letta](https://www.anchorterminal.com/compare/harness2-vs-letta.md)\n- [Harness² vs mini-swe-agent](https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md)\n- [Harness² vs MiniMax Code](https://www.anchorterminal.com/compare/harness2-vs-minimax-code.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 Agents API](https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.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 OpenMausBot](https://www.anchorterminal.com/compare/harness2-vs-openmausbot.md)\n- [Harness² vs Paseo](https://www.anchorterminal.com/compare/harness2-vs-paseo.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 Sculptor](https://www.anchorterminal.com/compare/harness2-vs-sculptor.md)\n- [Harness² vs T3 Code](https://www.anchorterminal.com/compare/harness2-vs-t3-code.md)\n- [Harness² vs Traycer](https://www.anchorterminal.com/compare/harness2-vs-traycer.md)\n- [Harness² vs Unstoppable](https://www.anchorterminal.com/compare/harness2-vs-unstoppable.md)\n- [Harness² vs Verdent](https://www.anchorterminal.com/compare/harness2-vs-verdent.md)\n- [Harness² vs Vibe-Trading](https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.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 Orca](https://www.anchorterminal.com/compare/harnessrouter-vs-orca.md)\n- [Jules vs Orca](https://www.anchorterminal.com/compare/jules-vs-orca.md)\n- [Junie CLI vs Orca](https://www.anchorterminal.com/compare/junie-vs-orca.md)\n- [Kilo Code CLI vs Orca](https://www.anchorterminal.com/compare/kilo-code-cli-vs-orca.md)\n- [Kimi Code CLI vs Orca](https://www.anchorterminal.com/compare/kimi-code-cli-vs-orca.md)\n- [Kiro CLI vs Orca](https://www.anchorterminal.com/compare/kiro-cli-vs-orca.md)\n- [Letta vs Orca](https://www.anchorterminal.com/compare/letta-vs-orca.md)\n- [mini-swe-agent vs Orca](https://www.anchorterminal.com/compare/mini-swe-agent-vs-orca.md)\n- [MiniMax Code vs Orca](https://www.anchorterminal.com/compare/minimax-code-vs-orca.md)\n- [Mistral Vibe CLI vs Orca](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-orca.md)\n- [Muse Code vs Orca](https://www.anchorterminal.com/compare/muse-code-vs-orca.md)\n- [OpenAI Agents API vs Orca](https://www.anchorterminal.com/compare/openai-agents-api-vs-orca.md)\n- [OpenAI Codex vs Orca](https://www.anchorterminal.com/compare/openai-codex-vs-orca.md)\n- [OpenCode vs Orca](https://www.anchorterminal.com/compare/opencode-vs-orca.md)\n- [OpenHands vs Orca](https://www.anchorterminal.com/compare/openhands-vs-orca.md)\n- [Orca vs Paseo](https://www.anchorterminal.com/compare/orca-vs-paseo.md)\n- [Orca vs Prime Agent](https://www.anchorterminal.com/compare/orca-vs-prime-agent.md)\n- [Orca vs Qoder CLI](https://www.anchorterminal.com/compare/orca-vs-qoder-cli.md)\n- [Orca vs Qwen Code](https://www.anchorterminal.com/compare/orca-vs-qwen-code.md)\n- [Orca vs Mirror CLI](https://www.anchorterminal.com/compare/orca-vs-reflection-mirror.md)\n- [Orca vs Rovo Dev CLI](https://www.anchorterminal.com/compare/orca-vs-rovo-dev-cli.md)\n- [Orca vs Sculptor](https://www.anchorterminal.com/compare/orca-vs-sculptor.md)\n- [Orca vs T3 Code](https://www.anchorterminal.com/compare/orca-vs-t3-code.md)\n- [Orca vs Traycer](https://www.anchorterminal.com/compare/orca-vs-traycer.md)\n- [Orca vs Unstoppable](https://www.anchorterminal.com/compare/orca-vs-unstoppable.md)\n- [Orca vs Verdent](https://www.anchorterminal.com/compare/orca-vs-verdent.md)\n- [Orca vs Vibe-Trading](https://www.anchorterminal.com/compare/orca-vs-vibe-trading.md)\n- [Orca vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/orca-vs-warp.md)\n- [Clawboo vs Orca](https://www.anchorterminal.com/compare/clawboo-vs-orca.md)\n- [CLI Manager vs Orca](https://www.anchorterminal.com/compare/cli-manager-vs-orca.md)\n- [Harness vs Orca](https://www.anchorterminal.com/compare/harness-autonomous-vs-orca.md)\n- [OpenMausBot vs Orca](https://www.anchorterminal.com/compare/openmausbot-vs-orca.md)\n- [Orca vs Paperclip](https://www.anchorterminal.com/compare/orca-vs-paperclip.md)\n- [Orca vs Parallax](https://www.anchorterminal.com/compare/orca-vs-parallax-agents.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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 Orca", "url": "" } ], "description": "Orca scores 57.4 (C) to Harness²'s 42 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 42", "Orca C 57.4", "scores" ], "h1": "Harness² vs Orca", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/harness2-vs-orca", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Orca for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/harness2-vs-orca" }, "tokens": { "markdown": 5250, "slim": 1830 }, "version": 1 }