{ "data": { "a": { "slug": "agent-browser", "name": "agent-browser", "vendor": "Vercel Labs", "vendorUrl": "https://agent-browser.dev", "kind": "mcp", "category": "browser", "summary": "agent-browser is an open-source command-line tool from Vercel Labs that lets AI agents drive Chrome through accessibility-tree snapshots and element refs. It runs locally as a Rust binary and includes a stdio MCP server.", "url": "https://www.anchorterminal.com/tools/agent-browser", "markdownUrl": "https://www.anchorterminal.com/tools/agent-browser.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agent-browser.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agent-browser.json", "repo": "https://github.com/vercel-labs/agent-browser", "license": "Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "agent-browser" } ], "auth": "none", "authNotes": "No account or key. The CLI and its daemon run on the owner's machine. Site logins are held in a local auth vault encrypted with AES-256-GCM, in saved state files (plaintext unless `AGENT_BROWSER_ENCRYPTION_KEY` is set) or in a reused Chrome profile. Cloud browser providers and the optional `chat` command need their own keys in environment variables.", "pricing": "free", "pricingNotes": "Free and open source under Apache-2.0, with nothing to buy and no hosted service. The optional `chat` command and dashboard chat bill the user's own Vercel AI Gateway key, and cloud browser providers bill separately (checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": 158, "popularity": { "githubStars": 43679, "npmWeekly": 2069828, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://agent-browser.dev", "llmsTxt": "https://agent-browser.dev/llms.txt", "capabilities": [ "browser.control", "browser.debug" ], "tags": [ "official", "local", "open-source", "browser", "cli", "mcp", "rust", "no-auth", "llms-txt" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 66.6, "grade": "B", "agentReady": false, "rank": 301, "ranked": true, "rankOf": 1076, "categoryRank": 12, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 70, "payments": 60, "reliability": 48, "schema": 84, "security": 67, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.", "bestFor": "Coding agents with a shell that want short commands and compact snapshots.", "strengths": [ "Accessibility-tree snapshots give each element a ref such as `@e2`, with `-i`, `-c`, `-d` and `--delta` to cut the output", "The stdio MCP server loads 29 tools by default and 158 with `--tools all`, each with a typed schema and `readOnlyHint`", "Domain allowlist, action policy, action confirmation and content boundary markers are documented with a threat model and known limitations", "19 tagged releases between 13 July and 1 October 2026, each with a changelog entry", "llms.txt and a Markdown copy of every docs page at agent-browser.dev, plus bundled skills served by `agent-browser skills get`" ], "weaknesses": [ "The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed", "Version 0.38.2 with a Vercel Labs badge and no stable release or deprecation policy", "All security controls are opt-in. By default there is no limit on navigation, actions or output", "crates.io holds 0.19.0 from 14 March 2026, although the README lists `cargo install agent-browser` as an install route", "No SECURITY.md in the repository, and 840 open issues and pull requests, with most of the newest issues unlabelled and unanswered" ], "agentNotes": [ "Run `agent-browser install` once after `npm install -g agent-browser`. It downloads Chrome for Testing", "Take a fresh `snapshot -i` after any navigation. Refs survive same-document changes only", "Pass `--json` for machine-readable results and `--max-output` to cap page text", "Set `--allowed-domains`, `--action-policy` and `--content-boundaries` for untrusted sites. None is on by default, and the allowlist rejects `--profile`, `--cdp` and `--restore`", "Start MCP with `agent-browser mcp`, and add profiles such as `--tools core,network` only when needed" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.6 } ], "editorialScores": { "ergonomics": 78, "maintenance": 70, "payments": 60, "reliability": 48, "schema": 84, "security": 67, "transparency": 68 }, "provenanceScore": 53 }, "connect": { "install": "npm install -g agent-browser \u0026\u0026 agent-browser install", "config": { "mcpServers": { "agent-browser": { "args": [ "mcp" ], "command": "agent-browser" } } } }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/agent-browser" }, "area": "developer", "provenance": { "legalEntity": "Vercel Inc.", "domain": "agent-browser.dev", "domainRegistered": "2026-01-13", "domainNote": "The LICENSE file reads Copyright 2025 Vercel Inc., and the repository sits in the vercel-labs organisation on GitHub. agent-browser.dev has no security.txt (HTTP 404). vercel.com's is valid until 28 September 2027 and names HackerOne.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/vercel-labs/agent-browser/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "No terms or privacy document governs this software beyond the Apache-2.0 licence, so `terms` and `privacy` are left out." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agent-browser.json", "live": { "slug": "agent-browser", "versions": [ { "registry": "github", "name": "vercel-labs/agent-browser", "version": "v0.39.1", "released": "2026-10-13", "seenAt": "2026-10-13T22:40:27.127147835Z" }, { "registry": "npm", "name": "agent-browser", "version": "0.39.1", "seenAt": "2026-10-13T22:40:26.891933061Z" } ], "githubStars": 43922, "npmWeekly": 1726779, "securityTxt": { "url": "https://agent-browser.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-13T15:45:11.848060277Z" }, "llmsTxt": { "url": "https://agent-browser.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-13T14:10:31.244993908Z" }, "domain": { "domain": "agent-browser.dev", "registered": "2026-01-13", "source": "https://pubapi.registry.google/rdap/domain/agent-browser.dev", "checkedAt": "2026-10-11T13:19:37.147391842Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/vercel-labs/agent-browser/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-13T20:24:17.780896373Z", "changedAt": "2026-10-13T20:24:17.780896373Z", "fingerprint": "5fa60a4e9997" } ], "updatedAt": "2026-10-13T22:40:27.127147835Z" } }, "answer": "Puppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth.", "b": { "slug": "puppeteer", "name": "Puppeteer", "vendor": "Google", "vendorUrl": "https://pptr.dev", "kind": "sdk", "category": "browser", "summary": "Puppeteer is Google's open-source Node.js library for controlling Chrome and Firefox over the DevTools Protocol and WebDriver BiDi. An agent writes and runs scripts that navigate, click, type, read pages and take screenshots.", "url": "https://www.anchorterminal.com/tools/puppeteer", "markdownUrl": "https://www.anchorterminal.com/tools/puppeteer.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/puppeteer.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/puppeteer.json", "repo": "https://github.com/puppeteer/puppeteer", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "npm", "name": "puppeteer" }, { "registry": "npm", "name": "puppeteer-core" } ], "auth": "none", "authNotes": "No account or key. The library runs on the owner's machine and launches or connects to a local browser. Site logins live in the browser profile or cookies the script sets. `puppeteer.connect()` to a remote browser uses whatever that endpoint requires.", "pricing": "free", "pricingNotes": "Free and open source under Apache-2.0, with nothing to buy and no hosted service from Google. `npm i puppeteer` downloads Chrome for Testing and chrome-headless-shell at install time (checked 2026-10-14).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs or the source (checked 2026-10-14).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 95689, "npmWeekly": 11547242, "pypiWeekly": null, "asOf": "2026-10-14" }, "docsUrl": "https://pptr.dev", "capabilities": [ "browser.control", "browser.debug" ], "tags": [ "official", "local", "open-source", "browser", "sdk", "typescript", "no-auth" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 70.6, "grade": "BB", "agentReady": true, "rank": 154, "ranked": true, "rankOf": 1076, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 89, "payments": 60, "reliability": 80, "schema": 81, "security": 52, "transparency": 70 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-14" }, "negative": 0, "verdict": "Puppeteer is a stable, Apache-2.0 library on 25.13.0, with ten releases since 27 July 2026, typed APIs, locators that wait and retry, and accessibility snapshots an agent can read. It has no MCP server or llms.txt of its own, and 10 of the 20 most recent CI runs on main failed between 7 and 13 October 2026.", "bestFor": "Agents that write and run Node.js scripts against Chrome or Firefox.", "strengths": [ "Ten releases from 25.4.0 on 27 July to 25.13.0 on 8 October 2026, each with a changelog generated by release-please", "TypeScript types for the whole API and a generated reference of 643 Markdown pages in the repository", "`page.accessibility.snapshot()` and the Locator API, which waits for elements and retries actions, suit scripted agent use", "Each release pins a tested Chrome for Testing and Firefox version, listed in a public support table", "Typed errors such as `TimeoutError`, `TargetCloseError` and `ConnectionClosedError` let a script tell timeouts from a closed browser" ], "weaknesses": [ "No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project", "10 of the 20 most recent CI runs on main, 7 to 13 October 2026, concluded in failure, the newest in Windows Chrome and Firefox jobs", "Page content reaches the agent unfiltered, and the docs have no prompt-injection or untrusted-content guidance", "JavaScript and TypeScript only, with Node.js 22.12 or later required since 25.0.0", "A stale workflow marks unconfirmed bug reports after 14 days and closes them 7 days later" ], "agentNotes": [ "Install with `npm i puppeteer`, which downloads a matching Chrome for Testing. Use `puppeteer-core` to bring your own browser", "Prefer `page.locator()` over `page.$()`. Locators wait for the element to be visible and stable before acting", "Read pages with `page.accessibility.snapshot({interestingOnly: true})` rather than full HTML to keep output short", "Catch `TimeoutError` separately from `TargetCloseError`. The first can be retried, the second needs a new page or browser", "Packages are ESM only since 25.0.0. Use `import puppeteer from 'puppeteer'` rather than `require`" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.6 } ], "editorialScores": { "ergonomics": 67, "maintenance": 89, "payments": 60, "reliability": 80, "schema": 81, "security": 52, "transparency": 72 }, "provenanceScore": 68 }, "connect": { "install": "npm i puppeteer" }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/puppeteer" }, "area": "developer", "provenance": { "legalEntity": "Google LLC", "domain": "pptr.dev", "domainRegistered": "2018-05-23", "domainNote": "pptr.dev is the documentation site for Puppeteer, with a footer reading Copyright 2026 Google, Inc. RDAP gives a registration date of 23 May 2018. The repository is in the puppeteer organisation on GitHub. pptr.dev answers 404 for /.well-known/security.txt.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/puppeteer/puppeteer/blob/main/packages/puppeteer-core/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-14", "notes": [ "No terms or privacy document governs this software beyond the Apache-2.0 licence, so `terms` and `privacy` are left out. The pptr.dev footer links Google's cookie policy for the site itself." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/puppeteer.json" }, "facts": [ { "a": "MCP server", "b": "SDK + MCP", "name": "Kind" }, { "a": "Vercel Labs", "b": "Google", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "stdio", "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", "b": "Apache-2.0", "name": "Licence" }, { "a": "158", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-01", "b": "2026-10-08", "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": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "44k stars, 2.1M npm/wk", "b": "96k stars, 11.5M npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "Puppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth.", "question": "Which is better for AI agents, agent-browser or Puppeteer?" }, { "answer": "agent-browser runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Puppeteer.", "question": "Can an agent call agent-browser and Puppeteer without installing anything?" }, { "answer": "Yes. agent-browser is open source (Apache-2.0). Puppeteer is open source (Apache-2.0).", "question": "Are agent-browser and Puppeteer open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 78 against 67", "Security \u0026 auth, 67 against 52" ], "also": [ "Runs on your own machine" ], "goodFor": "Coding agents with a shell that want short commands and compact snapshots.", "slug": "agent-browser", "watchFor": "The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed" }, { "aheadOn": [ "Reliability, 80 against 48", "Maintenance \u0026 community, 89 against 70", "Transparency \u0026 trust, 70 against 61" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Agents that write and run Node.js scripts against Chrome or Firefox.", "slug": "puppeteer", "watchFor": "No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project" } ], "job": { "capability": "browser.control", "name": "Browser automation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-airtop.json", "title": "agent-browser vs Airtop", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-airtop" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.json", "title": "agent-browser vs Anchor Browser", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.json", "title": "agent-browser vs Browser Use", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-browser-use" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-browserbase.json", "title": "agent-browser vs Browserbase", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-browserbase" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless.json", "title": "agent-browser vs Browserless", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp.json", "title": "agent-browser vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser.json", "title": "agent-browser vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-notte.json", "title": "agent-browser vs Notte", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.json", "title": "agent-browser vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.json", "title": "agent-browser vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium.json", "title": "agent-browser vs Selenium", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.json", "title": "agent-browser vs Skyvern", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-steel.json", "title": "agent-browser vs Steel", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish.json", "title": "agent-browser vs TinyFish", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/airtop-vs-puppeteer.json", "title": "Airtop vs Puppeteer", "url": "https://www.anchorterminal.com/compare/airtop-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer.json", "title": "Anchor Browser vs Puppeteer", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-puppeteer.json", "title": "Browser Use vs Puppeteer", "url": "https://www.anchorterminal.com/compare/browser-use-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/browserbase-vs-puppeteer.json", "title": "Browserbase vs Puppeteer", "url": "https://www.anchorterminal.com/compare/browserbase-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-puppeteer.json", "title": "Browserless vs Puppeteer", "url": "https://www.anchorterminal.com/compare/browserless-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-puppeteer.json", "title": "Chrome DevTools MCP vs Puppeteer", "url": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/hyperbrowser-vs-puppeteer.json", "title": "Hyperbrowser vs Puppeteer", "url": "https://www.anchorterminal.com/compare/hyperbrowser-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/notte-vs-puppeteer.json", "title": "Notte vs Puppeteer", "url": "https://www.anchorterminal.com/compare/notte-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.json", "title": "Playwright MCP vs Puppeteer", "url": "https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-vs-puppeteer-reference-server-archived.json", "title": "Puppeteer vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/puppeteer-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-vs-selenium.json", "title": "Puppeteer vs Selenium", "url": "https://www.anchorterminal.com/compare/puppeteer-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-vs-skyvern.json", "title": "Puppeteer vs Skyvern", "url": "https://www.anchorterminal.com/compare/puppeteer-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-vs-steel.json", "title": "Puppeteer vs Steel", "url": "https://www.anchorterminal.com/compare/puppeteer-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-vs-tinyfish.json", "title": "Puppeteer vs TinyFish", "url": "https://www.anchorterminal.com/compare/puppeteer-vs-tinyfish" } ], "scores": [ { "agent-browser": 48, "by": 32, "edge": "puppeteer", "key": "reliability", "name": "Reliability", "puppeteer": 80, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agent-browser": 84, "by": 3, "edge": "agent-browser", "key": "schema", "name": "Schema \u0026 documentation", "puppeteer": 81, "weight": 13 }, { "agent-browser": 78, "by": 11, "edge": "agent-browser", "key": "ergonomics", "name": "Agent ergonomics", "puppeteer": 67, "weight": 13 }, { "agent-browser": 67, "by": 15, "edge": "agent-browser", "key": "security", "name": "Security \u0026 auth", "puppeteer": 52, "weight": 14 }, { "agent-browser": 60, "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "puppeteer": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agent-browser": 70, "by": 19, "edge": "puppeteer", "key": "maintenance", "name": "Maintenance \u0026 community", "puppeteer": 89, "weight": 7 }, { "agent-browser": 61, "by": 9, "edge": "puppeteer", "key": "transparency", "name": "Transparency \u0026 trust", "puppeteer": 70, "weight": 7 } ], "summary": "Puppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth. Both do browser automation.", "verdicts": { "agent-browser": "Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.", "puppeteer": "Puppeteer is a stable, Apache-2.0 library on 25.13.0, with ten releases since 27 July 2026, typed APIs, locators that wait and retry, and accessibility snapshots an agent can read. It has no MCP server or llms.txt of its own, and 10 of the 20 most recent CI runs on main failed between 7 and 13 October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer", "json": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.md", "slim": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.min.md" }, "markdown": "Puppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth. Both do browser automation.\n\n- agent-browser: grade B, 66.6/100, rank #301 of 1076. Markdown https://www.anchorterminal.com/tools/agent-browser.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-browser.json\n- Puppeteer: grade BB, 70.6/100, rank #154 of 1076. Markdown https://www.anchorterminal.com/tools/puppeteer.md · JSON https://www.anchorterminal.com/api/v1/tools/puppeteer.json\n- Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md\n- All 120 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md\n\n## Which one, for what\n\n### agent-browser (B)\n\nGood for: Coding agents with a shell that want short commands and compact snapshots.\n\nAhead on:\n- Agent ergonomics, 78 against 67\n- Security \u0026 auth, 67 against 52\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed\n\n### Puppeteer (BB)\n\nGood for: Agents that write and run Node.js scripts against Chrome or Firefox.\n\nAhead on:\n- Reliability, 80 against 48\n- Maintenance \u0026 community, 89 against 70\n- Transparency \u0026 trust, 70 against 61\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project\n\n\n## Score by category\n\n| Category | Weight | agent-browser | Puppeteer | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 48 | 80 | Puppeteer +32 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 81 | agent-browser +3 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 67 | agent-browser +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 67 | 52 | agent-browser +15 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 70 | 89 | Puppeteer +19 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 70 | Puppeteer +9 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **66.6 · B** | **70.6 · BB** | |\n\n## Facts side by side\n\n| Fact | agent-browser | Puppeteer |\n| --- | --- | --- |\n| Kind | MCP server | SDK + MCP |\n| Vendor | Vercel Labs | Google |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Tools exposed | 158 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-01 | 2026-10-08 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 44k stars, 2.1M npm/wk | 96k stars, 11.5M npm/wk |\n\n## Verdicts\n\n**agent-browser.** Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.\n\n**Puppeteer.** Puppeteer is a stable, Apache-2.0 library on 25.13.0, with ten releases since 27 July 2026, typed APIs, locators that wait and retry, and accessibility snapshots an agent can read. It has no MCP server or llms.txt of its own, and 10 of the 20 most recent CI runs on main failed between 7 and 13 October 2026.\n\n## Before you call either\n\n### agent-browser\n\n1. Run `agent-browser install` once after `npm install -g agent-browser`. It downloads Chrome for Testing\n2. Take a fresh `snapshot -i` after any navigation. Refs survive same-document changes only\n3. Pass `--json` for machine-readable results and `--max-output` to cap page text\n4. Set `--allowed-domains`, `--action-policy` and `--content-boundaries` for untrusted sites. None is on by default, and the allowlist rejects `--profile`, `--cdp` and `--restore`\n5. Start MCP with `agent-browser mcp`, and add profiles such as `--tools core,network` only when needed\n\n### Puppeteer\n\n1. Install with `npm i puppeteer`, which downloads a matching Chrome for Testing. Use `puppeteer-core` to bring your own browser\n2. Prefer `page.locator()` over `page.$()`. Locators wait for the element to be visible and stable before acting\n3. Read pages with `page.accessibility.snapshot({interestingOnly: true})` rather than full HTML to keep output short\n4. Catch `TimeoutError` separately from `TargetCloseError`. The first can be retried, the second needs a new page or browser\n5. Packages are ESM only since 25.0.0. Use `import puppeteer from 'puppeteer'` rather than `require`\n\n## Questions\n\n### Which is better for AI agents, agent-browser or Puppeteer?\n\nPuppeteer scores 70.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 3 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth.\n\n### Can an agent call agent-browser and Puppeteer without installing anything?\n\nagent-browser runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Puppeteer.\n\n### Are agent-browser and Puppeteer open source?\n\nYes. agent-browser is open source (Apache-2.0). Puppeteer is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agent-browser\", \"b\": \"puppeteer\"}`. From a terminal: `anchor compare agent-browser puppeteer`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-browser.json and https://www.anchorterminal.com/api/v1/tools/puppeteer.json\n\n## Other comparisons with agent-browser or Puppeteer\n\n- [agent-browser vs Airtop](https://www.anchorterminal.com/compare/agent-browser-vs-airtop.md)\n- [agent-browser vs Anchor Browser](https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.md)\n- [agent-browser vs Browser Use](https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.md)\n- [agent-browser vs Browserbase](https://www.anchorterminal.com/compare/agent-browser-vs-browserbase.md)\n- [agent-browser vs Browserless](https://www.anchorterminal.com/compare/agent-browser-vs-browserless.md)\n- [agent-browser vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp.md)\n- [agent-browser vs Hyperbrowser](https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser.md)\n- [agent-browser vs Notte](https://www.anchorterminal.com/compare/agent-browser-vs-notte.md)\n- [agent-browser vs Playwright MCP](https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.md)\n- [agent-browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.md)\n- [agent-browser vs Selenium](https://www.anchorterminal.com/compare/agent-browser-vs-selenium.md)\n- [agent-browser vs Skyvern](https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.md)\n- [agent-browser vs Steel](https://www.anchorterminal.com/compare/agent-browser-vs-steel.md)\n- [agent-browser vs TinyFish](https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish.md)\n- [Airtop vs Puppeteer](https://www.anchorterminal.com/compare/airtop-vs-puppeteer.md)\n- [Anchor Browser vs Puppeteer](https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer.md)\n- [Browser Use vs Puppeteer](https://www.anchorterminal.com/compare/browser-use-vs-puppeteer.md)\n- [Browserbase vs Puppeteer](https://www.anchorterminal.com/compare/browserbase-vs-puppeteer.md)\n- [Browserless vs Puppeteer](https://www.anchorterminal.com/compare/browserless-vs-puppeteer.md)\n- [Chrome DevTools MCP vs Puppeteer](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-puppeteer.md)\n- [Hyperbrowser vs Puppeteer](https://www.anchorterminal.com/compare/hyperbrowser-vs-puppeteer.md)\n- [Notte vs Puppeteer](https://www.anchorterminal.com/compare/notte-vs-puppeteer.md)\n- [Playwright MCP vs Puppeteer](https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.md)\n- [Puppeteer vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/puppeteer-vs-puppeteer-reference-server-archived.md)\n- [Puppeteer vs Selenium](https://www.anchorterminal.com/compare/puppeteer-vs-selenium.md)\n- [Puppeteer vs Skyvern](https://www.anchorterminal.com/compare/puppeteer-vs-skyvern.md)\n- [Puppeteer vs Steel](https://www.anchorterminal.com/compare/puppeteer-vs-steel.md)\n- [Puppeteer vs TinyFish](https://www.anchorterminal.com/compare/puppeteer-vs-tinyfish.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-14", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "agent-browser vs Puppeteer", "url": "" } ], "description": "Puppeteer scores 70.6 (BB) to agent-browser's 66.6 (B) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "agent-browser B 66.6", "Puppeteer BB 70.6", "scores" ], "h1": "agent-browser vs Puppeteer", "image": "https://www.anchorterminal.com/assets/og/compare-agent-browser-vs-puppeteer.png", "path": "/compare/agent-browser-vs-puppeteer", "published": "2026-10-01", "section": "tools", "title": "agent-browser vs Puppeteer for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-14", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer" }, "tokens": { "markdown": 2500, "slim": 530 }, "version": 1 }