{ "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": "Sculptor scores 53.1 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on schema \u0026 documentation and agent ergonomics.", "b": { "slug": "sculptor", "name": "Sculptor", "vendor": "Imbue, Inc.", "vendorUrl": "https://imbue.com", "kind": "harness", "category": "agent-harnesses", "summary": "Sculptor is Imbue's open-source desktop app for running coding agents in parallel, each in an isolated copy of your code, with built-in skills for agentic development. It's labelled an experimental research preview.", "url": "https://www.anchorterminal.com/tools/sculptor", "markdownUrl": "https://www.anchorterminal.com/tools/sculptor.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/sculptor.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/sculptor.json", "dns": "sculptor.grade.anchorterminal.com", "repo": "https://github.com/imbue-ai/sculptor", "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://github.com/imbue-ai/sculptor#readme", "capabilities": [ "agent.harness", "agent.multi-agent" ], "tags": [ "open-source", "mit", "desktop-app", "new" ], "lastRelease": "2026-11-06", "graded": true, "anchor": { "graded": true, "score": 53.1, "grade": "D", "agentReady": false, "rank": 966, "ranked": true, "rankOf": 1510, "categoryRank": 37, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 50, "maintenance": 75, "payments": 60, "reliability": 43, "schema": 45, "security": 57, "transparency": 57 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-07" }, "negative": 0, "verdict": "Imbue's open-source app for parallel coding agents in isolated workspaces, with telemetry off until you choose otherwise. It's an experimental research preview that warns of bugs and drastic changes, Mac and Linux only, with no changelog.", "bestFor": "Developers who want parallel coding agents in isolated workspaces and are fine with a research preview.", "strengths": [ "Each workspace is an isolated copy of the code, reviewed and merged back", "Analytics, error reporting and session recording default to off, with consent at first run", "Built-in skills for agentic development", "MIT from Imbue, with CI on pull requests" ], "weaknesses": [ "Labelled an experimental research preview that may change drastically", "Mac (Apple Silicon) and Linux only", "No changelog file", "Few outside contributions accepted for now" ], "agentNotes": [ "Download from the README's links, connect a repository and create a workspace before prompting", "Review the diff before merging a workspace back to main" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.1 } ], "editorialScores": { "ergonomics": 50, "maintenance": 75, "payments": 60, "reliability": 43, "schema": 45, "security": 57, "transparency": 73 }, "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 for Mac (Apple Silicon) or Linux from the README" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/sculptor" }, "area": "frameworks", "provenance": { "legalEntity": "Imbue, Inc.", "domain": "imbue.com", "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 Imbue, Inc.. The repository is github.com/imbue-ai/sculptor." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/sculptor.json", "live": { "slug": "sculptor", "securityTxt": { "url": "https://imbue.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:32.925074454Z" }, "updatedAt": "2026-11-07T16:01:32.925074454Z" } }, "edges": [ { "by": 39, "category": "maintenance", "leads": "sculptor", "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": "Commits on 6 November 2026 and frequent tagged versions (30). More than three 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; the README says Imbue can't take many outside contributions yet (0). Current official downloads (15). CI on pull requests (10). 30 + 20 + 0 + 15 + 10 = 75." }, "scores": { "a": 36, "b": 75 } }, { "by": 23, "category": "reliability", "leads": "sculptor", "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 downloads for Mac (Apple Silicon), Linux and Linux ARM64 (20). checks.yml and a PR gate run on the repository; 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). sculptor-v tags up to v0.49.0, no changelog file (8). 0.x and labelled a research preview (0). 20 + 15 + 0 + 8 + 0 = 43." }, "scores": { "a": 20, "b": 43 } }, { "by": 20, "category": "payments", "leads": "sculptor", "name": "Payments \u0026 pricing", "reasons": { "a": "No payment protocol (0). Read with the self-hosted rule, as for the other harnesses. Free under Apache-2.0 with nothing to buy (20). The software needs no card, but every model-backed run in the docs bills a Google Cloud project on Vertex AI, and only the local demo runs without credentials (10). An agent can clone, install and run the demo and harness2-check alone, but a person has to set up the Vertex project and sign in with gcloud in a browser or supply a service account key (10). 40 in all.", "b": "Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60." }, "scores": { "a": 40, "b": 60 } }, { "by": 13, "category": "security", "leads": "sculptor", "name": "Security \u0026 auth", "reasons": { "a": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Against that, executors inherit the whole shell environment (the editor channel drops only five Anthropic variables), and no .gitignore keeps a filled-in .env out of commits (20). Codex runs with `--dangerously-bypass-approvals-and-sandbox`, the Claude CLI editor channel with `--dangerously-skip-permissions`, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 44 in all.", "b": "Harness reading. Product analytics, error reporting and session recording default to off in the user config, and the app asks for a telemetry level and privacy consent at first run; PostHog runs on the front end only for now (25 of 30). Each workspace is an isolated copy of the code (14 of 20). No prompt-injection guidance (5). No audit log (5). SECURITY.md (8). 25 + 14 + 5 + 5 + 8 = 57." }, "scores": { "a": 44, "b": 57 } }, { "by": 9, "category": "ergonomics", "leads": "harness2", "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. Workspaces as isolated copies, review and merge back, and built-in skills (50)." }, "scores": { "a": 59, "b": 50 } }, { "by": 8, "category": "transparency", "leads": "sculptor", "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). Consent-based telemetry documented in the repository (18 of 30). The README warns of drastic changes during the research preview, with no deprecation policy (5). Opt-in telemetry (20). 30 + 18 + 5 + 20 = 73." }, "scores": { "a": 49, "b": 57 } } ], "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Imbue, 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": "Sculptor scores 53.1 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Harness² or Sculptor?" }, { "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).). Sculptor is open source (MIT).", "question": "Are Harness² and Sculptor open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 51 against 45", "Agent ergonomics, 59 against 50" ], "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, 43 against 20", "Security \u0026 auth, 57 against 44", "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 75 against 36", "Transparency \u0026 trust, 57 against 49" ], "also": null, "goodFor": "Developers who want parallel coding agents in isolated workspaces and are fine with a research preview.", "slug": "sculptor", "watchFor": "Labelled an experimental research preview that may change drastically" } ], "history": { "harness2": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.4, "from": 41.6, "fromGrade": "E", "to": 42, "toGrade": "E" } ], "sculptor": 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-sculptor.json", "title": "Agent Zero vs Sculptor", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-sculptor" }, { "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-sculptor.json", "title": "Aider vs Sculptor", "url": "https://www.anchorterminal.com/compare/aider-vs-sculptor" }, { "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-sculptor.json", "title": "Amp vs Sculptor", "url": "https://www.anchorterminal.com/compare/amp-vs-sculptor" }, { "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-sculptor.json", "title": "Antigravity CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-sculptor" }, { "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-sculptor.json", "title": "Auggie CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/auggie-vs-sculptor" }, { "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-sculptor.json", "title": "AXLR vs Sculptor", "url": "https://www.anchorterminal.com/compare/axlr-vs-sculptor" }, { "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-sculptor.json", "title": "Claude Code vs Sculptor", "url": "https://www.anchorterminal.com/compare/claude-code-vs-sculptor" }, { "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-sculptor.json", "title": "Cline vs Sculptor", "url": "https://www.anchorterminal.com/compare/cline-vs-sculptor" }, { "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-sculptor.json", "title": "Conductor vs Sculptor", "url": "https://www.anchorterminal.com/compare/conductor-vs-sculptor" }, { "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-sculptor.json", "title": "Crush vs Sculptor", "url": "https://www.anchorterminal.com/compare/crush-vs-sculptor" }, { "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-sculptor.json", "title": "Cursor CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-sculptor" }, { "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-sculptor.json", "title": "DeepSeek Harness (dsh) vs Sculptor", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-sculptor" }, { "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-sculptor.json", "title": "dsh-superagent (DeepSeek) vs Sculptor", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-sculptor" }, { "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-sculptor.json", "title": "Devin vs Sculptor", "url": "https://www.anchorterminal.com/compare/devin-vs-sculptor" }, { "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-sculptor.json", "title": "Droid CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-sculptor" }, { "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-sculptor.json", "title": "Pi vs Sculptor", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-sculptor" }, { "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-sculptor.json", "title": "Emdash vs Sculptor", "url": "https://www.anchorterminal.com/compare/emdash-vs-sculptor" }, { "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-sculptor.json", "title": "Gemini CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-sculptor" }, { "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-sculptor.json", "title": "GitHub Copilot CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-sculptor" }, { "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-sculptor.json", "title": "goose vs Sculptor", "url": "https://www.anchorterminal.com/compare/goose-vs-sculptor" }, { "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-orca.json", "title": "Harness² vs Orca", "url": "https://www.anchorterminal.com/compare/harness2-vs-orca" }, { "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-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-sculptor.json", "title": "HarnessRouter vs Sculptor", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-sculptor.json", "title": "Jules vs Sculptor", "url": "https://www.anchorterminal.com/compare/jules-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-sculptor.json", "title": "Junie CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/junie-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-sculptor.json", "title": "Kilo Code CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-sculptor.json", "title": "Kimi Code CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-sculptor.json", "title": "Kiro CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/letta-vs-sculptor.json", "title": "Letta vs Sculptor", "url": "https://www.anchorterminal.com/compare/letta-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor.json", "title": "mini-swe-agent vs Sculptor", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-sculptor.json", "title": "MiniMax Code vs Sculptor", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor.json", "title": "Mistral Vibe CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-sculptor.json", "title": "Muse Code vs Sculptor", "url": "https://www.anchorterminal.com/compare/muse-code-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-sculptor.json", "title": "OpenAI Agents API vs Sculptor", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-sculptor.json", "title": "OpenAI Codex vs Sculptor", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-sculptor.json", "title": "OpenCode vs Sculptor", "url": "https://www.anchorterminal.com/compare/opencode-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-sculptor.json", "title": "OpenHands vs Sculptor", "url": "https://www.anchorterminal.com/compare/openhands-vs-sculptor" }, { "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/paseo-vs-sculptor.json", "title": "Paseo vs Sculptor", "url": "https://www.anchorterminal.com/compare/paseo-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/prime-agent-vs-sculptor.json", "title": "Prime Agent vs Sculptor", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/qoder-cli-vs-sculptor.json", "title": "Qoder CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/qoder-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/qwen-code-vs-sculptor.json", "title": "Qwen Code vs Sculptor", "url": "https://www.anchorterminal.com/compare/qwen-code-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/reflection-mirror-vs-sculptor.json", "title": "Mirror CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/reflection-mirror-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-sculptor.json", "title": "Rovo Dev CLI vs Sculptor", "url": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-t3-code.json", "title": "Sculptor vs T3 Code", "url": "https://www.anchorterminal.com/compare/sculptor-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-traycer.json", "title": "Sculptor vs Traycer", "url": "https://www.anchorterminal.com/compare/sculptor-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-unstoppable.json", "title": "Sculptor vs Unstoppable", "url": "https://www.anchorterminal.com/compare/sculptor-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-verdent.json", "title": "Sculptor vs Verdent", "url": "https://www.anchorterminal.com/compare/sculptor-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-vibe-trading.json", "title": "Sculptor vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/sculptor-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-warp.json", "title": "Sculptor vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/sculptor-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-sculptor.json", "title": "Clawboo vs Sculptor", "url": "https://www.anchorterminal.com/compare/clawboo-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-sculptor.json", "title": "CLI Manager vs Sculptor", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-sculptor.json", "title": "Harness vs Sculptor", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/openmausbot-vs-sculptor.json", "title": "OpenMausBot vs Sculptor", "url": "https://www.anchorterminal.com/compare/openmausbot-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/paperclip-vs-sculptor.json", "title": "Paperclip vs Sculptor", "url": "https://www.anchorterminal.com/compare/paperclip-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/parallax-agents-vs-sculptor.json", "title": "Parallax vs Sculptor", "url": "https://www.anchorterminal.com/compare/parallax-agents-vs-sculptor" } ], "panel": null, "scores": [ { "by": 23, "edge": "sculptor", "harness2": 20, "key": "reliability", "name": "Reliability", "sculptor": 43, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 6, "edge": "harness2", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "sculptor": 45, "weight": 13 }, { "by": 9, "edge": "harness2", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "sculptor": 50, "weight": 13 }, { "by": 13, "edge": "sculptor", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "sculptor": 57, "weight": 14 }, { "by": 20, "edge": "sculptor", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "sculptor": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 39, "edge": "sculptor", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "sculptor": 75, "weight": 7 }, { "by": 8, "edge": "sculptor", "harness2": 49, "key": "transparency", "name": "Transparency \u0026 trust", "sculptor": 57, "weight": 7 } ], "summary": "Sculptor scores 53.1 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on schema \u0026 documentation and agent ergonomics. 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.", "sculptor": "Imbue's open-source app for parallel coding agents in isolated workspaces, with telemetry off until you choose otherwise. It's an experimental research preview that warns of bugs and drastic changes, Mac and Linux only, with no changelog." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-sculptor", "json": "https://www.anchorterminal.com/compare/harness2-vs-sculptor.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-sculptor.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-sculptor.min.md" }, "markdown": "Sculptor scores 53.1 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on schema \u0026 documentation and agent ergonomics. 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- Sculptor: grade D, 53.1/100, rank #966 of 1510. Markdown https://www.anchorterminal.com/tools/sculptor.md · JSON https://www.anchorterminal.com/api/v1/tools/sculptor.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\nAhead on:\n- Schema \u0026 documentation, 51 against 45\n- Agent ergonomics, 59 against 50\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### Sculptor (D)\n\nGood for: Developers who want parallel coding agents in isolated workspaces and are fine with a research preview.\n\nAhead on:\n- Reliability, 43 against 20\n- Security \u0026 auth, 57 against 44\n- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 75 against 36\n- Transparency \u0026 trust, 57 against 49\n\nWatch for: Labelled an experimental research preview that may change drastically\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Sculptor +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- Sculptor (75): Commits on 6 November 2026 and frequent tagged versions (30). More than three 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; the README says Imbue can't take many outside contributions yet (0). Current official downloads (15). CI on pull requests (10). 30 + 20 + 0 + 15 + 10 = 75.\n\n### Reliability: Sculptor +23\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- Sculptor (43): Local software. Desktop downloads for Mac (Apple Silicon), Linux and Linux ARM64 (20). checks.yml and a PR gate run on the repository; 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). sculptor-v tags up to v0.49.0, no changelog file (8). 0.x and labelled a research preview (0). 20 + 15 + 0 + 8 + 0 = 43.\n\n### Payments \u0026 pricing: Sculptor +20\n\n- Harness² (40): No payment protocol (0). Read with the self-hosted rule, as for the other harnesses. Free under Apache-2.0 with nothing to buy (20). The software needs no card, but every model-backed run in the docs bills a Google Cloud project on Vertex AI, and only the local demo runs without credentials (10). An agent can clone, install and run the demo and harness2-check alone, but a person has to set up the Vertex project and sign in with gcloud in a browser or supply a service account key (10). 40 in all.\n- Sculptor (60): Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60.\n\n### Security \u0026 auth: Sculptor +13\n\n- Harness² (44): Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Against that, executors inherit the whole shell environment (the editor channel drops only five Anthropic variables), and no .gitignore keeps a filled-in .env out of commits (20). Codex runs with `--dangerously-bypass-approvals-and-sandbox`, the Claude CLI editor channel with `--dangerously-skip-permissions`, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 44 in all.\n- Sculptor (57): Harness reading. Product analytics, error reporting and session recording default to off in the user config, and the app asks for a telemetry level and privacy consent at first run; PostHog runs on the front end only for now (25 of 30). Each workspace is an isolated copy of the code (14 of 20). No prompt-injection guidance (5). No audit log (5). SECURITY.md (8). 25 + 14 + 5 + 5 + 8 = 57.\n\n### Agent ergonomics: Harness² +9\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- Sculptor (50): Harness reading. Workspaces as isolated copies, review and merge back, and built-in skills (50).\n\n### Transparency \u0026 trust: Sculptor +8\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- Sculptor (57): MIT (30). Consent-based telemetry documented in the repository (18 of 30). The README warns of drastic changes during the research preview, with no deprecation policy (5). Opt-in telemetry (20). 30 + 18 + 5 + 20 = 73.\n\n## Score by category\n\n| Category | Weight | Harness² | Sculptor | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 43 | Sculptor +23 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 45 | Harness² +6 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 50 | Harness² +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 57 | Sculptor +13 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | Sculptor +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 75 | Sculptor +39 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 49 | 57 | Sculptor +8 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **42 · E** | **53.1 · D** | |\n\n## Facts side by side\n\n| Fact | Harness² | Sculptor |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Imbue, 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### Sculptor\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**Sculptor.** Imbue's open-source app for parallel coding agents in isolated workspaces, with telemetry off until you choose otherwise. It's an experimental research preview that warns of bugs and drastic changes, Mac and Linux only, with no changelog.\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### Sculptor\n\n1. Download from the README's links, connect a repository and create a workspace before prompting\n2. Review the diff before merging a workspace back to main\n\n## Questions\n\n### Which is better for AI agents, Harness² or Sculptor?\n\nSculptor scores 53.1 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on schema \u0026 documentation and agent ergonomics.\n\n### Are Harness² and Sculptor 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).). Sculptor is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-sculptor.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-sculptor.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"sculptor\"}`. From a terminal: `anchor compare harness2 sculptor`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/sculptor.json\n\n## Other comparisons with Harness² or Sculptor\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Sculptor](https://www.anchorterminal.com/compare/agent-zero-vs-sculptor.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Sculptor](https://www.anchorterminal.com/compare/aider-vs-sculptor.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Sculptor](https://www.anchorterminal.com/compare/amp-vs-sculptor.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Sculptor](https://www.anchorterminal.com/compare/antigravity-cli-vs-sculptor.md)\n- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)\n- [Auggie CLI vs Sculptor](https://www.anchorterminal.com/compare/auggie-vs-sculptor.md)\n- [AXLR vs Harness²](https://www.anchorterminal.com/compare/axlr-vs-harness2.md)\n- [AXLR vs Sculptor](https://www.anchorterminal.com/compare/axlr-vs-sculptor.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Sculptor](https://www.anchorterminal.com/compare/claude-code-vs-sculptor.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Sculptor](https://www.anchorterminal.com/compare/cline-vs-sculptor.md)\n- [Conductor vs Harness²](https://www.anchorterminal.com/compare/conductor-vs-harness2.md)\n- [Conductor vs Sculptor](https://www.anchorterminal.com/compare/conductor-vs-sculptor.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Crush vs Sculptor](https://www.anchorterminal.com/compare/crush-vs-sculptor.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Sculptor](https://www.anchorterminal.com/compare/cursor-cli-vs-sculptor.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs Sculptor](https://www.anchorterminal.com/compare/deepseek-harness-vs-sculptor.md)\n- [dsh-superagent (DeepSeek) vs Harness²](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.md)\n- [dsh-superagent (DeepSeek) vs Sculptor](https://www.anchorterminal.com/compare/deepseek-superagent-vs-sculptor.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Sculptor](https://www.anchorterminal.com/compare/devin-vs-sculptor.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Sculptor](https://www.anchorterminal.com/compare/droid-cli-vs-sculptor.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Sculptor](https://www.anchorterminal.com/compare/earendil-pi-vs-sculptor.md)\n- [Emdash vs Harness²](https://www.anchorterminal.com/compare/emdash-vs-harness2.md)\n- [Emdash vs Sculptor](https://www.anchorterminal.com/compare/emdash-vs-sculptor.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Sculptor](https://www.anchorterminal.com/compare/gemini-cli-vs-sculptor.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Sculptor](https://www.anchorterminal.com/compare/github-copilot-cli-vs-sculptor.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Sculptor](https://www.anchorterminal.com/compare/goose-vs-sculptor.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 Orca](https://www.anchorterminal.com/compare/harness2-vs-orca.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 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 Sculptor](https://www.anchorterminal.com/compare/harnessrouter-vs-sculptor.md)\n- [Jules vs Sculptor](https://www.anchorterminal.com/compare/jules-vs-sculptor.md)\n- [Junie CLI vs Sculptor](https://www.anchorterminal.com/compare/junie-vs-sculptor.md)\n- [Kilo Code CLI vs Sculptor](https://www.anchorterminal.com/compare/kilo-code-cli-vs-sculptor.md)\n- [Kimi Code CLI vs Sculptor](https://www.anchorterminal.com/compare/kimi-code-cli-vs-sculptor.md)\n- [Kiro CLI vs Sculptor](https://www.anchorterminal.com/compare/kiro-cli-vs-sculptor.md)\n- [Letta vs Sculptor](https://www.anchorterminal.com/compare/letta-vs-sculptor.md)\n- [mini-swe-agent vs Sculptor](https://www.anchorterminal.com/compare/mini-swe-agent-vs-sculptor.md)\n- [MiniMax Code vs Sculptor](https://www.anchorterminal.com/compare/minimax-code-vs-sculptor.md)\n- [Mistral Vibe CLI vs Sculptor](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-sculptor.md)\n- [Muse Code vs Sculptor](https://www.anchorterminal.com/compare/muse-code-vs-sculptor.md)\n- [OpenAI Agents API vs Sculptor](https://www.anchorterminal.com/compare/openai-agents-api-vs-sculptor.md)\n- [OpenAI Codex vs Sculptor](https://www.anchorterminal.com/compare/openai-codex-vs-sculptor.md)\n- [OpenCode vs Sculptor](https://www.anchorterminal.com/compare/opencode-vs-sculptor.md)\n- [OpenHands vs Sculptor](https://www.anchorterminal.com/compare/openhands-vs-sculptor.md)\n- [Orca vs Sculptor](https://www.anchorterminal.com/compare/orca-vs-sculptor.md)\n- [Paseo vs Sculptor](https://www.anchorterminal.com/compare/paseo-vs-sculptor.md)\n- [Prime Agent vs Sculptor](https://www.anchorterminal.com/compare/prime-agent-vs-sculptor.md)\n- [Qoder CLI vs Sculptor](https://www.anchorterminal.com/compare/qoder-cli-vs-sculptor.md)\n- [Qwen Code vs Sculptor](https://www.anchorterminal.com/compare/qwen-code-vs-sculptor.md)\n- [Mirror CLI vs Sculptor](https://www.anchorterminal.com/compare/reflection-mirror-vs-sculptor.md)\n- [Rovo Dev CLI vs Sculptor](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-sculptor.md)\n- [Sculptor vs T3 Code](https://www.anchorterminal.com/compare/sculptor-vs-t3-code.md)\n- [Sculptor vs Traycer](https://www.anchorterminal.com/compare/sculptor-vs-traycer.md)\n- [Sculptor vs Unstoppable](https://www.anchorterminal.com/compare/sculptor-vs-unstoppable.md)\n- [Sculptor vs Verdent](https://www.anchorterminal.com/compare/sculptor-vs-verdent.md)\n- [Sculptor vs Vibe-Trading](https://www.anchorterminal.com/compare/sculptor-vs-vibe-trading.md)\n- [Sculptor vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/sculptor-vs-warp.md)\n- [Clawboo vs Sculptor](https://www.anchorterminal.com/compare/clawboo-vs-sculptor.md)\n- [CLI Manager vs Sculptor](https://www.anchorterminal.com/compare/cli-manager-vs-sculptor.md)\n- [Harness vs Sculptor](https://www.anchorterminal.com/compare/harness-autonomous-vs-sculptor.md)\n- [OpenMausBot vs Sculptor](https://www.anchorterminal.com/compare/openmausbot-vs-sculptor.md)\n- [Paperclip vs Sculptor](https://www.anchorterminal.com/compare/paperclip-vs-sculptor.md)\n- [Parallax vs Sculptor](https://www.anchorterminal.com/compare/parallax-agents-vs-sculptor.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 Sculptor", "url": "" } ], "description": "Sculptor scores 53.1 (D) to Harness²'s 42 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 42", "Sculptor D 53.1", "scores" ], "h1": "Harness² vs Sculptor", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/harness2-vs-sculptor", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Sculptor for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/harness2-vs-sculptor" }, "tokens": { "markdown": 5900, "slim": 2330 }, "version": 1 }