{ "data": { "a": { "slug": "antigravity-cli", "name": "Antigravity CLI", "vendor": "Google", "vendorUrl": "https://antigravity.google", "kind": "harness", "category": "agent-harnesses", "summary": "Google's terminal agent for coding tasks, distributed as a closed-source binary and installed as agy. It replaces Gemini CLI for consumer accounts.", "url": "https://www.anchorterminal.com/tools/antigravity-cli", "markdownUrl": "https://www.anchorterminal.com/tools/antigravity-cli.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/antigravity-cli.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/antigravity-cli.json", "repo": "https://github.com/google-antigravity/antigravity-cli", "license": "Proprietary. The repository holds the README, changelog and examples, with no source and no licence file. Use is under the Google Antigravity Additional Terms of Service, the Google Terms of Service and the Privacy Policy", "transports": [], "packages": [], "auth": "mixed", "authNotes": "Sign in with a Google account in the browser, which uses the operating system keyring, or pick the Business account option for Gemini Enterprise through Google Cloud sign-in, workforce identity federation or Application Default Credentials. Alternatively set modelProvider to gemini in ~/.gemini/antigravity-cli/settings.json and export GEMINI_API_KEY. The terms treat access through third-party software with Antigravity OAuth as a breach.", "pricing": "freemium", "pricingNotes": "Free to install. A $0 individual plan needs no subscription and has a weekly quota, with Gemini Flash and other models. Google AI Pro costs $20 a month and Ultra $100 or $200 a month (announced 19 May 2026). Enterprise Standard or Plus seats start at $30 a seat a month, or pay-as-you-go with no seat fee at consumption rates. Checked 10 October 2026.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs pages, the pricing page, the plans page, the README or the changelog (checked 2026-10-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-10" }, "docsUrl": "https://antigravity.google/docs/cli/overview", "llmsTxt": "https://antigravity.google/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "closed-source", "mcp", "llms-txt", "sandbox-default", "telemetry-opt-out", "subagents", "hooks", "plugins", "paid-plans", "gemini-models", "third-party-models" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 57.4, "grade": "C", "agentReady": false, "rank": 675, "ranked": true, "rankOf": 1135, "categoryRank": 19, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 68, "payments": 30, "reliability": 43, "schema": 78, "security": 53, "transparency": 51 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": 0, "verdict": "Google's terminal agent, shipped as a closed-source binary with a terminal sandbox on by default on macOS and Linux and documented headless JSON output. Interactions are used to improve Google products unless users opt out, and a headless run exits 0 when a tool is denied.", "bestFor": "Developers on Google AI plans or Gemini Enterprise who want a terminal agent with a sandbox on by default and access to several model families, depending on plan.", "strengths": [ "The sandbox is on under the Default preset on macOS and Linux, hides ~/.ssh and .env, and limits network access to approved domains", "Headless `agy -p` runs with `--output-format json` or `stream-json`, a status field with SUCCESS, ERROR and other terminal states, and token usage in the result event", "MCP clients for stdio, Streamable HTTP, SSE and WebSocket servers, with unconfigured MCP tools set to ask first and allow rules by server and tool", "Skills, subagents, PreToolUse and PostToolUse hooks, and plugins from an official marketplace that `/plugin` manages", "The installer verifies a SHA-512 checksum against a manifest on Google's release server before it installs" ], "weaknesses": [ "Closed source. The repository holds the README, changelog and examples, with no source and no licence file", "Interactions are used to improve Google and Alphabet products and models, and Google staff and contractors may review them, unless the user opts out", "The sandbox is labelled preview in the permissions docs, and Windows still uses the older permission model that the docs describe separately", "A headless run exits 0 when a tool that needs approval is refused, and the only sign is a notice on stderr", "The plans page gives no request counts for the weekly quota, which Google sets by available capacity" ], "agentNotes": [ "Read the `status` field from `--output-format json` and read stderr too. A tool refused for lack of approval still exits 0", "Pre-approve each shell command and tool a headless run needs with `action(target)` rules under `permissions.allow` in ~/.gemini/antigravity-cli/settings.json, because headless runs cannot ask", "Export `GEMINI_API_KEY` after setting modelProvider to gemini. The CLI won't start when the key is missing, and setting the variable alone has no effect", "Turn off Enable Telemetry in the Account settings before running on private repositories if Interactions should not be used for product improvement", "Set `--print-timeout` explicitly. The docs give a five-minute default, while `agy --help` shows 0s" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 68, "payments": 30, "reliability": 43, "schema": 78, "security": 53, "transparency": 52 }, "provenanceScore": 50 }, "connect": { "install": "curl -fsSL https://antigravity.google/cli/install.sh | bash", "headless": { "run": "agy -p \"fix the failing test\" --output-format json" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/antigravity-cli" }, "area": "frameworks", "provenance": { "legalEntity": "Google LLC", "domain": "antigravity.google", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://antigravity.google/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "", "changelog": "https://antigravity.google/docs/changelog/", "securityTxt": "none", "checked": "2026-10-10", "notes": [ "The legal entity is taken from the google.com check on the Gemini CLI listing. The Antigravity terms name Google without an entity.", "antigravity.google serves no security.txt (both /.well-known/security.txt and /security.txt answered 404 on 10 October 2026). google.com has a valid one, with reports to g.co/vulnz.", "No status page for the CLI was found in the docs, and the domain's registration date was not read." ], "score": 50 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/antigravity-cli.json", "live": { "slug": "antigravity-cli", "versions": [ { "registry": "github", "name": "google-antigravity/antigravity-cli", "version": "1.4.2", "released": "2026-10-18", "seenAt": "2026-10-18T02:32:14.473016389Z" } ], "githubStars": 2586, "securityTxt": { "url": "https://antigravity.google/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:53:48.773733488Z" }, "llmsTxt": { "url": "https://antigravity.google/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:24:16.35964951Z" }, "domain": { "domain": "antigravity.google", "registered": "2025-09-19", "source": "https://pubapi.registry.google/rdap/domain/antigravity.google", "checkedAt": "2026-10-18T13:33:59.674027856Z" }, "pages": [ { "url": "https://antigravity.google/docs/changelog/", "kind": "changelog", "status": 304, "checkedAt": "2026-10-17T22:56:05.174828357Z", "changedAt": "2026-10-17T22:44:44.718339453Z", "fingerprint": "c85bb2092d02" }, { "url": "https://policies.google.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-17T23:07:57.727753793Z", "changedAt": "2026-10-16T22:29:01.693232998Z", "fingerprint": "a7c8f2c3ee09" }, { "url": "https://antigravity.google/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-17T22:56:07.293037738Z", "changedAt": "2026-10-17T22:44:47.360698402Z", "fingerprint": "45cbf764cb98" } ], "updatedAt": "2026-10-18T15:53:48.773733488Z" } }, "answer": "Antigravity CLI scores 57.4 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing.", "b": { "slug": "harness2", "name": "Harness²", "vendor": "Google (Google Research)", "vendorUrl": "https://harness2.github.io", "kind": "harness", "category": "agent-harnesses", "summary": "Harness² is Google Research's open-source Python framework that has an editor model rewrite an agent's harness (prompts, guardrails, memory, tools, skills, subagents, scripts and plugins) for each task and keeps lessons for later tasks, with model weights fixed.", "url": "https://www.anchorterminal.com/tools/harness2", "markdownUrl": "https://www.anchorterminal.com/tools/harness2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness2.json", "repo": "https://github.com/google-research/harness2", "license": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "transports": [], "packages": [], "auth": "none", "authNotes": "No Harness² account or key. Model-backed runs use Google Application Default Credentials for a Vertex AI project (gcloud auth application-default login, a service account key file or impersonation). The optional Codex bridge generates its own local access key.", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with nothing to buy. Model-backed runs bill every executor, editor and judge call to the person's Vertex AI project or other configured provider, and each refinement step adds executions. The local demo needs no credentials.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, docs or source (checked 2026-10-18). The software has nothing to buy.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4200, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://github.com/google-research/harness2/tree/main/docs", "capabilities": [ "agent.harness" ], "tags": [ "open-source", "apache-2.0", "local", "self-hosted", "free", "python", "cli", "linux" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 41.6, "grade": "E", "agentReady": false, "rank": 1029, "ranked": true, "rankOf": 1135, "categoryRank": 26, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 44 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-18" }, "negative": 0, "verdict": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.", "bestFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "strengths": [ "Refining a harness needs no grader, rubric or answer key. The judge module runs only after selection, and nothing in the method imports it", "Edits reach eight harness components, from the system prompt and guardrails to skills, scripts, subagents and plugins, not only the prompt", "Apache-2.0, with upstream checkouts pinned by commit, a hash list for bundled files and each third-party runner's licence and provenance", "Rerunning a command resumes it, failed grades stay unscored rather than zero, and `--dry-run` previews task selection without model calls", "Each editor session's prompt, response, model and cost are written to an audit folder beside the run" ], "weaknesses": [ "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI", "The CLI accepts only JobBench, LAB and WorkBuddy-Bench, with no documented way to run it on your own tasks", "Executor network access is unrestricted, Codex runs with approvals and sandbox bypassed, and executors inherit the whole shell environment", "The quick start copies `.env.example`, which the repository doesn't contain, and no .gitignore keeps a filled-in .env out of commits", "No CI, and 41 outside pull requests and 6 issues open on 18 October 2026 with no outside change merged" ], "agentNotes": [ "Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only", "Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`", "Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched", "Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it", "Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 41.6 } ], "editorialScores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 48 }, "provenanceScore": 40 }, "connect": { "install": "git clone https://github.com/google-research/harness2.git \u0026\u0026 cd harness2 \u0026\u0026 uv venv --python 3.12 .venv \u0026\u0026 source .venv/bin/activate \u0026\u0026 uv pip install -e '.[render]' \u0026\u0026 harness2-demo --output runs/demo --k 2", "headless": { "command": "harness2-setup lab \u0026\u0026 harness2-check --bench lab \u0026\u0026 harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1", "env": { "GOOGLE_CLOUD_PROJECT": "\u003cyour-vertex-project\u003e", "HARNESS2_JUDGE_MODEL": "\u003cmodel-id\u003e", "HARNESS2_SOLVER_MODEL": "\u003cprovider/model\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/harness2" }, "area": "frameworks", "provenance": { "legalEntity": "Google LLC", "domain": "harness2.github.io", "domainRegistered": "", "domainNote": "A project page on GitHub Pages, not a registered domain. The code is in the google-research organisation on GitHub.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "LICENSE is Apache-2.0, and pyproject.toml and every source file name Google LLC. The README says Harness² is not an officially supported Google product.", "No terms or privacy policy govern the package or the project page. Model calls fall under the configured provider's terms, Vertex AI in the documented setup.", "The repository has no SECURITY.md, and harness2.github.io/.well-known/security.txt returns 404. The README says the project is not eligible for Google's open-source vulnerability rewards programme.", "No changelog, tags or GitHub releases. The version is 0.1.0 in pyproject.toml.", "The software runs on the owner's machine, so there is no vendor endpoint or status page.", "The project page has no robots.txt and carries a noindex, nofollow robots meta tag. It was read once as a public page." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harness2.json" }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google", "b": "Google (Google Research)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary. The repository holds the README, changelog and examples, with no source and no licence file. Use is under the Google Antigravity Additional Terms of Service, the Google Terms of Service and the Privacy Policy", "b": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-10-08", "name": "Last release" }, { "a": "no date given", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "4.2k stars", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Antigravity CLI scores 57.4 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Antigravity CLI or Harness²?" }, { "answer": "No open-source release is listed for Antigravity CLI. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).).", "question": "Are Antigravity CLI and Harness² open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 43 against 20", "Schema \u0026 documentation, 78 against 51", "Agent ergonomics, 78 against 59", "Security \u0026 auth, 53 against 44", "Maintenance \u0026 community, 68 against 36", "Transparency \u0026 trust, 51 against 44" ], "also": null, "goodFor": "Developers on Google AI plans or Gemini Enterprise who want a terminal agent with a sandbox on by default and access to several model families, depending on plan.", "slug": "antigravity-cli", "watchFor": "Closed source. The repository holds the README, changelog and examples, with no source and no licence file" }, { "aheadOn": [ "Payments \u0026 pricing, 40 against 30" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.", "slug": "harness2", "watchFor": "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI" } ], "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli.json", "title": "Agent Zero vs Antigravity CLI", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2.json", "title": "Agent Zero vs Harness²", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-antigravity-cli.json", "title": "Aider vs Antigravity CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-antigravity-cli" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-harness2.json", "title": "Aider vs Harness²", "url": "https://www.anchorterminal.com/compare/aider-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-antigravity-cli.json", "title": "Amp vs Antigravity CLI", "url": "https://www.anchorterminal.com/compare/amp-vs-antigravity-cli" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-harness2.json", "title": "Amp vs Harness²", "url": "https://www.anchorterminal.com/compare/amp-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code.json", "title": "Antigravity CLI vs Claude Code", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-cline.json", "title": "Antigravity CLI vs Cline", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-cline" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-cursor-cli.json", "title": "Antigravity CLI vs Cursor CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-cursor-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-devin.json", "title": "Antigravity CLI vs Devin", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-devin" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-droid-cli.json", "title": "Antigravity CLI vs Droid CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-droid-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi.json", "title": "Antigravity CLI vs Pi", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-gemini-cli.json", "title": "Antigravity CLI vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-github-copilot-cli.json", "title": "Antigravity CLI vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-goose.json", "title": "Antigravity CLI vs goose", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter.json", "title": "Antigravity CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-kilo-code-cli.json", "title": "Antigravity CLI vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-kiro-cli.json", "title": "Antigravity CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-muse-code.json", "title": "Antigravity CLI vs Muse Code", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-codex.json", "title": "Antigravity CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-opencode.json", "title": "Antigravity CLI vs OpenCode", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openhands.json", "title": "Antigravity CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-prime-agent.json", "title": "Antigravity CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-qwen-code.json", "title": "Antigravity CLI vs Qwen Code", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-reflection-mirror.json", "title": "Antigravity CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness2.json", "title": "Claude Code vs Harness²", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-harness2.json", "title": "Cline vs Harness²", "url": "https://www.anchorterminal.com/compare/cline-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.json", "title": "Cursor CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harness2.json", "title": "Devin vs Harness²", "url": "https://www.anchorterminal.com/compare/devin-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2.json", "title": "Droid CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json", "title": "Pi vs Harness²", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.json", "title": "Gemini CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.json", "title": "GitHub Copilot CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-harness2.json", "title": "goose vs Harness²", "url": "https://www.anchorterminal.com/compare/goose-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json", "title": "Harness² vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json", "title": "Harness² vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json", "title": "Harness² vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-muse-code.json", "title": "Harness² vs Muse Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex.json", "title": "Harness² vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-opencode.json", "title": "Harness² vs OpenCode", "url": "https://www.anchorterminal.com/compare/harness2-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openhands.json", "title": "Harness² vs OpenHands", "url": "https://www.anchorterminal.com/compare/harness2-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json", "title": "Harness² vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code.json", "title": "Harness² vs Qwen Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.json", "title": "Harness² vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-cli-manager.json", "title": "Antigravity CLI vs CLI Manager", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-cli-manager" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous.json", "title": "Antigravity CLI vs Harness", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-paperclip.json", "title": "Antigravity CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-parallax-agents.json", "title": "Antigravity CLI vs Parallax", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-parallax-agents" } ], "scores": [ { "antigravity-cli": 43, "by": 23, "edge": "antigravity-cli", "harness2": 20, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "antigravity-cli": 78, "by": 27, "edge": "antigravity-cli", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "antigravity-cli": 78, "by": 19, "edge": "antigravity-cli", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "antigravity-cli": 53, "by": 9, "edge": "antigravity-cli", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "antigravity-cli": 30, "by": 10, "edge": "harness2", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "antigravity-cli": 68, "by": 32, "edge": "antigravity-cli", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "antigravity-cli": 51, "by": 7, "edge": "antigravity-cli", "harness2": 44, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Antigravity CLI scores 57.4 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing. Both do agent harnesses.", "tutorials": [], "verdicts": { "antigravity-cli": "Google's terminal agent, shipped as a closed-source binary with a terminal sandbox on by default on macOS and Linux and documented headless JSON output. Interactions are used to improve Google products unless users opt out, and a headless run exits 0 when a tool is denied.", "harness2": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2", "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.min.md" }, "markdown": "Antigravity CLI scores 57.4 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing. Both do agent harnesses.\n\n- Antigravity CLI: grade C, 57.4/100, rank #675 of 1135. Markdown https://www.anchorterminal.com/tools/antigravity-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/antigravity-cli.json\n- Harness²: grade E, 41.6/100, rank #1029 of 1135. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 354 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Antigravity CLI (C)\n\nGood for: Developers on Google AI plans or Gemini Enterprise who want a terminal agent with a sandbox on by default and access to several model families, depending on plan.\n\nAhead on:\n- Reliability, 43 against 20\n- Schema \u0026 documentation, 78 against 51\n- Agent ergonomics, 78 against 59\n- Security \u0026 auth, 53 against 44\n- Maintenance \u0026 community, 68 against 36\n- Transparency \u0026 trust, 51 against 44\n\nWatch for: Closed source. The repository holds the README, changelog and examples, with no source and no licence file\n\n### Harness² (E)\n\nGood for: Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.\n\nAhead on:\n- Payments \u0026 pricing, 40 against 30\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI\n\n\n## Score by category\n\n| Category | Weight | Antigravity CLI | Harness² | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 43 | 20 | Antigravity CLI +23 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 78 | 51 | Antigravity CLI +27 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 59 | Antigravity CLI +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 53 | 44 | Antigravity CLI +9 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 40 | Harness² +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 68 | 36 | Antigravity CLI +32 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 51 | 44 | Antigravity CLI +7 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **57.4 · C** | **41.6 · E** | |\n\n## Facts side by side\n\n| Fact | Antigravity CLI | Harness² |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google | Google (Google Research) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Proprietary. The repository holds the README, changelog and examples, with no source and no licence file. Use is under the Google Antigravity Additional Terms of Service, the Google Terms of Service and the Privacy Policy | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-08 | 2026-10-08 |\n| Terms last updated | no date given | no document linked |\n| Privacy policy last updated | 2026-10-01 | no document linked |\n| Customer content may train models | yes, with an opt-out | |\n| Terms restrict automated access | not found in the text | |\n| Terms restrict benchmarking | not found in the text | |\n| Terms or service can change without notice | not found in the text | |\n| Arbitration or class-action waiver | not found in the text | |\n| Popularity | none | 4.2k stars |\n| Agent reviews | none | 2.5/5 (4) |\n\n## Verdicts\n\n**Antigravity CLI.** Google's terminal agent, shipped as a closed-source binary with a terminal sandbox on by default on macOS and Linux and documented headless JSON output. Interactions are used to improve Google products unless users opt out, and a headless run exits 0 when a tool is denied.\n\n**Harness².** Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.\n\n## Before you call either\n\n### Antigravity CLI\n\n1. Read the `status` field from `--output-format json` and read stderr too. A tool refused for lack of approval still exits 0\n2. Pre-approve each shell command and tool a headless run needs with `action(target)` rules under `permissions.allow` in ~/.gemini/antigravity-cli/settings.json, because headless runs cannot ask\n3. Export `GEMINI_API_KEY` after setting modelProvider to gemini. The CLI won't start when the key is missing, and setting the variable alone has no effect\n4. Turn off Enable Telemetry in the Account settings before running on private repositories if Interactions should not be used for product improvement\n5. Set `--print-timeout` explicitly. The docs give a five-minute default, while `agy --help` shows 0s\n\n### Harness²\n\n1. Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only\n2. Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`\n3. Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched\n4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it\n5. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up\n\n## Questions\n\n### Which is better for AI agents, Antigravity CLI or Harness²?\n\nAntigravity CLI scores 57.4 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments \u0026 pricing.\n\n### Are Antigravity CLI and Harness² open source?\n\nNo open-source release is listed for Antigravity CLI. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"antigravity-cli\", \"b\": \"harness2\"}`. From a terminal: `anchor compare antigravity-cli harness2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/antigravity-cli.json and https://www.anchorterminal.com/api/v1/tools/harness2.json\n\n## Other comparisons with Antigravity CLI or Harness²\n\n- [Agent Zero vs Antigravity CLI](https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Aider vs Antigravity CLI](https://www.anchorterminal.com/compare/aider-vs-antigravity-cli.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Amp vs Antigravity CLI](https://www.anchorterminal.com/compare/amp-vs-antigravity-cli.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Antigravity CLI vs Claude Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-claude-code.md)\n- [Antigravity CLI vs Cline](https://www.anchorterminal.com/compare/antigravity-cli-vs-cline.md)\n- [Antigravity CLI vs Cursor CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-cursor-cli.md)\n- [Antigravity CLI vs Devin](https://www.anchorterminal.com/compare/antigravity-cli-vs-devin.md)\n- [Antigravity CLI vs Droid CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-droid-cli.md)\n- [Antigravity CLI vs Pi](https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi.md)\n- [Antigravity CLI vs Gemini CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-gemini-cli.md)\n- [Antigravity CLI vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-github-copilot-cli.md)\n- [Antigravity CLI vs goose](https://www.anchorterminal.com/compare/antigravity-cli-vs-goose.md)\n- [Antigravity CLI vs HarnessRouter](https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter.md)\n- [Antigravity CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-kilo-code-cli.md)\n- [Antigravity CLI vs Kiro CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-kiro-cli.md)\n- [Antigravity CLI vs Muse Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-muse-code.md)\n- [Antigravity CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-codex.md)\n- [Antigravity CLI vs OpenCode](https://www.anchorterminal.com/compare/antigravity-cli-vs-opencode.md)\n- [Antigravity CLI vs OpenHands](https://www.anchorterminal.com/compare/antigravity-cli-vs-openhands.md)\n- [Antigravity CLI vs Prime Agent](https://www.anchorterminal.com/compare/antigravity-cli-vs-prime-agent.md)\n- [Antigravity CLI vs Qwen Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-qwen-code.md)\n- [Antigravity CLI vs Mirror CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-reflection-mirror.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)\n- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)\n- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)\n- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)\n- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)\n- [Harness² vs OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.md)\n- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)\n- [Harness² vs Qwen Code](https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md)\n- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)\n- [Antigravity CLI vs CLI Manager](https://www.anchorterminal.com/compare/antigravity-cli-vs-cli-manager.md)\n- [Antigravity CLI vs Harness](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous.md)\n- [Antigravity CLI vs Paperclip](https://www.anchorterminal.com/compare/antigravity-cli-vs-paperclip.md)\n- [Antigravity CLI vs Parallax](https://www.anchorterminal.com/compare/antigravity-cli-vs-parallax-agents.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Antigravity CLI vs Harness²", "url": "" } ], "description": "Antigravity CLI scores 57.4 (C) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Antigravity CLI C 57.4", "Harness² E 41.6", "scores" ], "h1": "Antigravity CLI vs Harness²", "image": "https://www.anchorterminal.com/assets/og/compare-antigravity-cli-vs-harness2.png", "path": "/compare/antigravity-cli-vs-harness2", "published": "2026-10-01", "section": "tools", "title": "Antigravity CLI vs Harness² for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2" }, "tokens": { "markdown": 3250, "slim": 780 }, "version": 1 }