{ "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": "Selenium scores 73.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth.", "b": { "slug": "selenium", "name": "Selenium", "vendor": "Selenium project (Software Freedom Conservancy)", "vendorUrl": "https://www.selenium.dev", "kind": "sdk", "category": "browser", "summary": "Selenium is the open-source browser automation project behind the W3C WebDriver standard, with official bindings for Java, Python, C#, Ruby and JavaScript and a self-hosted Grid server that runs browsers on other machines.", "url": "https://www.anchorterminal.com/tools/selenium", "markdownUrl": "https://www.anchorterminal.com/tools/selenium.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/selenium.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/selenium.json", "repo": "https://github.com/SeleniumHQ/selenium", "license": "Apache-2.0", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "selenium" }, { "registry": "npm", "name": "selenium-webdriver" }, { "registry": "maven", "name": "org.seleniumhq.selenium:selenium-java" }, { "registry": "nuget", "name": "Selenium.WebDriver" }, { "registry": "rubygems", "name": "selenium-webdriver" } ], "auth": "none", "authNotes": "No account or key for the bindings, which run on the owner's machine. Grid accepts sessions without authentication unless both `--username` and `--password` are set, and Nodes register with a shared `--registration-secret` when one is configured. Site logins live in the browser profile or cookies the script sets.", "pricing": "free", "pricingNotes": "Free and open source under Apache-2.0, with nothing to buy and no hosted service from the project. Grid is self-hosted. Commercial clouds that run Selenium sessions are separate companies (checked 2026-10-14).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms.txt or the source (checked 2026-10-14).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 34542, "npmWeekly": 1807038, "pypiWeekly": 6884385, "asOf": "2026-10-14" }, "docsUrl": "https://www.selenium.dev/documentation/", "llmsTxt": "https://www.selenium.dev/llms.txt", "capabilities": [ "browser.control", "browser.debug" ], "tags": [ "official", "local", "open-source", "browser", "sdk", "python", "java", "javascript", "dotnet", "ruby", "llms-txt", "no-auth", "webdriver" ], "lastRelease": "2026-10-09", "graded": true, "anchor": { "graded": true, "score": 73.6, "grade": "BB", "agentReady": true, "rank": 90, "ranked": true, "rankOf": 1076, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 94, "payments": 60, "reliability": 90, "schema": 89, "security": 43, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-14" }, "negative": 0, "verdict": "Selenium is stable, Apache-2.0 software on 4.51.0 with bindings in five languages, CI passing on trunk, an llms.txt and an agent guide added in September 2026. It has no MCP server of its own, Selenium Manager sends usage statistics by default, and Grid accepts unauthenticated sessions unless a username and password are set.", "bestFor": "Agents that write test or automation scripts in any of five languages, and teams with a Grid.", "strengths": [ "Official bindings for Java, Python, C#, Ruby and JavaScript, released together, 4.51.0 on 9 October 2026", "llms.txt and a page on using AI coding agents with Selenium, last changed 28 September 2026", "Code samples in the docs are run in CI against current releases", "An error page per common exception, such as `StaleElementReferenceException`, gives causes and fixes", "The 15 most recent CI runs on trunk, 13 October 2026, all succeeded or were cancelled" ], "weaknesses": [ "No MCP server from the project. The docs point to community servers and say they are third-party", "Selenium Manager sends anonymised usage statistics to Plausible once a day by default, until `SE_AVOID_STATS=true` is set", "Grid has no authentication unless `--username` and `--password` are both set", "The project says it does not follow semantic versioning, and removes deprecated APIs in minor releases", "No accessibility snapshot call, so agents read page source or query elements one by one" ], "agentNotes": [ "Install with `pip install selenium` (Python 3.10 or later) and let Selenium Manager fetch drivers. Do not set driver paths", "Use `WebDriverWait` with expected conditions, never fixed sleeps, and do not mix implicit and explicit waits", "Set `SE_AVOID_STATS=true` to stop Selenium Manager sending usage statistics", "Point coding agents at https://www.selenium.dev/llms.txt. Most Selenium 2 and 3 era examples use removed APIs", "Set `--username` and `--password` before exposing a Grid beyond localhost. Check `http://localhost:4444/status` before creating sessions" ], "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": 73.6 } ], "editorialScores": { "ergonomics": 70, "maintenance": 94, "payments": 60, "reliability": 90, "schema": 89, "security": 43, "transparency": 80 }, "provenanceScore": 68 }, "connect": { "install": "pip install selenium", "http": "curl http://localhost:4444/status" }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/selenium" }, "area": "developer", "provenance": { "legalEntity": "Software Freedom Conservancy", "domain": "selenium.dev", "domainRegistered": "2019-02-22", "domainNote": "NOTICE reads Copyright 2011-2026 Software Freedom Conservancy, which holds the project. RDAP gives selenium.dev a registration date of 22 February 2019. selenium.dev answers 404 for /.well-known/security.txt. Security reports go to security@seleniumhq.org.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/SeleniumHQ/selenium/blob/trunk/py/CHANGES", "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. selenium.dev has no privacy page (/privacy/ answers 404). Selenium Manager's data collection is described in its documentation page.", "Each binding keeps its own changelog. The Python one is linked, and the downloads page links the others.", "selenium.dev's robots.txt names all user agents with no Disallow lines, so every page was read." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/selenium.json" }, "facts": [ { "a": "MCP server", "b": "SDK + MCP", "name": "Kind" }, { "a": "Vercel Labs", "b": "Selenium project (Software Freedom Conservancy)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "stdio", "b": "HTTP", "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": "yes", "name": "llms.txt" }, { "a": "2026-10-01", "b": "2026-10-09", "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": "35k stars, 1.8M npm/wk, 6.9M PyPI/wk", "name": "Popularity" } ], "faq": [ { "answer": "Selenium scores 73.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth.", "question": "Which is better for AI agents, agent-browser or Selenium?" }, { "answer": "agent-browser runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Selenium.", "question": "Can an agent call agent-browser and Selenium without installing anything?" }, { "answer": "Yes. agent-browser is open source (Apache-2.0). Selenium is open source (Apache-2.0).", "question": "Are agent-browser and Selenium open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 78 against 70", "Security \u0026 auth, 67 against 43" ], "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, 90 against 48", "Schema \u0026 documentation, 89 against 84", "Maintenance \u0026 community, 94 against 70", "Transparency \u0026 trust, 74 against 61" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Agents that write test or automation scripts in any of five languages, and teams with a Grid.", "slug": "selenium", "watchFor": "No MCP server from the project. The docs point to community servers and say they are third-party" } ], "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.json", "title": "agent-browser vs Puppeteer", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer" }, { "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-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-selenium.json", "title": "Airtop vs Selenium", "url": "https://www.anchorterminal.com/compare/airtop-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-selenium.json", "title": "Anchor Browser vs Selenium", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-selenium.json", "title": "Browser Use vs Selenium", "url": "https://www.anchorterminal.com/compare/browser-use-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/browserbase-vs-selenium.json", "title": "Browserbase vs Selenium", "url": "https://www.anchorterminal.com/compare/browserbase-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-selenium.json", "title": "Browserless vs Selenium", "url": "https://www.anchorterminal.com/compare/browserless-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-selenium.json", "title": "Chrome DevTools MCP vs Selenium", "url": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/hyperbrowser-vs-selenium.json", "title": "Hyperbrowser vs Selenium", "url": "https://www.anchorterminal.com/compare/hyperbrowser-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/notte-vs-selenium.json", "title": "Notte vs Selenium", "url": "https://www.anchorterminal.com/compare/notte-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.json", "title": "Playwright MCP vs Selenium", "url": "https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium.json", "title": "Puppeteer (archived MCP reference server) vs Selenium", "url": "https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium" }, { "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/selenium-vs-skyvern.json", "title": "Selenium vs Skyvern", "url": "https://www.anchorterminal.com/compare/selenium-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/selenium-vs-steel.json", "title": "Selenium vs Steel", "url": "https://www.anchorterminal.com/compare/selenium-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/selenium-vs-tinyfish.json", "title": "Selenium vs TinyFish", "url": "https://www.anchorterminal.com/compare/selenium-vs-tinyfish" } ], "scores": [ { "agent-browser": 48, "by": 42, "edge": "selenium", "key": "reliability", "name": "Reliability", "selenium": 90, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agent-browser": 84, "by": 5, "edge": "selenium", "key": "schema", "name": "Schema \u0026 documentation", "selenium": 89, "weight": 13 }, { "agent-browser": 78, "by": 8, "edge": "agent-browser", "key": "ergonomics", "name": "Agent ergonomics", "selenium": 70, "weight": 13 }, { "agent-browser": 67, "by": 24, "edge": "agent-browser", "key": "security", "name": "Security \u0026 auth", "selenium": 43, "weight": 14 }, { "agent-browser": 60, "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "selenium": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agent-browser": 70, "by": 24, "edge": "selenium", "key": "maintenance", "name": "Maintenance \u0026 community", "selenium": 94, "weight": 7 }, { "agent-browser": 61, "by": 13, "edge": "selenium", "key": "transparency", "name": "Transparency \u0026 trust", "selenium": 74, "weight": 7 } ], "summary": "Selenium scores 73.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 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.", "selenium": "Selenium is stable, Apache-2.0 software on 4.51.0 with bindings in five languages, CI passing on trunk, an llms.txt and an agent guide added in September 2026. It has no MCP server of its own, Selenium Manager sends usage statistics by default, and Grid accepts unauthenticated sessions unless a username and password are set." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium", "json": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium.md", "slim": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium.min.md" }, "markdown": "Selenium scores 73.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 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- Selenium: grade BB, 73.6/100, rank #90 of 1076. Markdown https://www.anchorterminal.com/tools/selenium.md · JSON https://www.anchorterminal.com/api/v1/tools/selenium.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 70\n- Security \u0026 auth, 67 against 43\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### Selenium (BB)\n\nGood for: Agents that write test or automation scripts in any of five languages, and teams with a Grid.\n\nAhead on:\n- Reliability, 90 against 48\n- Schema \u0026 documentation, 89 against 84\n- Maintenance \u0026 community, 94 against 70\n- Transparency \u0026 trust, 74 against 61\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: No MCP server from the project. The docs point to community servers and say they are third-party\n\n\n## Score by category\n\n| Category | Weight | agent-browser | Selenium | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 48 | 90 | Selenium +42 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 89 | Selenium +5 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 70 | agent-browser +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 67 | 43 | agent-browser +24 |\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 | 94 | Selenium +24 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 74 | Selenium +13 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **66.6 · B** | **73.6 · BB** | |\n\n## Facts side by side\n\n| Fact | agent-browser | Selenium |\n| --- | --- | --- |\n| Kind | MCP server | SDK + MCP |\n| Vendor | Vercel Labs | Selenium project (Software Freedom Conservancy) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio | HTTP |\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 | yes |\n| Last release | 2026-10-01 | 2026-10-09 |\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 | 35k stars, 1.8M npm/wk, 6.9M PyPI/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**Selenium.** Selenium is stable, Apache-2.0 software on 4.51.0 with bindings in five languages, CI passing on trunk, an llms.txt and an agent guide added in September 2026. It has no MCP server of its own, Selenium Manager sends usage statistics by default, and Grid accepts unauthenticated sessions unless a username and password are set.\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### Selenium\n\n1. Install with `pip install selenium` (Python 3.10 or later) and let Selenium Manager fetch drivers. Do not set driver paths\n2. Use `WebDriverWait` with expected conditions, never fixed sleeps, and do not mix implicit and explicit waits\n3. Set `SE_AVOID_STATS=true` to stop Selenium Manager sending usage statistics\n4. Point coding agents at https://www.selenium.dev/llms.txt. Most Selenium 2 and 3 era examples use removed APIs\n5. Set `--username` and `--password` before exposing a Grid beyond localhost. Check `http://localhost:4444/status` before creating sessions\n\n## Questions\n\n### Which is better for AI agents, agent-browser or Selenium?\n\nSelenium scores 73.6 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on agent ergonomics and security \u0026 auth.\n\n### Can an agent call agent-browser and Selenium without installing anything?\n\nagent-browser runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Selenium.\n\n### Are agent-browser and Selenium open source?\n\nYes. agent-browser is open source (Apache-2.0). Selenium 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-selenium.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-browser-vs-selenium.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agent-browser\", \"b\": \"selenium\"}`. From a terminal: `anchor compare agent-browser selenium`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-browser.json and https://www.anchorterminal.com/api/v1/tools/selenium.json\n\n## Other comparisons with agent-browser or Selenium\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](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.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 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 Selenium](https://www.anchorterminal.com/compare/airtop-vs-selenium.md)\n- [Anchor Browser vs Selenium](https://www.anchorterminal.com/compare/anchor-browser-vs-selenium.md)\n- [Browser Use vs Selenium](https://www.anchorterminal.com/compare/browser-use-vs-selenium.md)\n- [Browserbase vs Selenium](https://www.anchorterminal.com/compare/browserbase-vs-selenium.md)\n- [Browserless vs Selenium](https://www.anchorterminal.com/compare/browserless-vs-selenium.md)\n- [Chrome DevTools MCP vs Selenium](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-selenium.md)\n- [Hyperbrowser vs Selenium](https://www.anchorterminal.com/compare/hyperbrowser-vs-selenium.md)\n- [Notte vs Selenium](https://www.anchorterminal.com/compare/notte-vs-selenium.md)\n- [Playwright MCP vs Selenium](https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.md)\n- [Puppeteer (archived MCP reference server) vs Selenium](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium.md)\n- [Puppeteer vs Selenium](https://www.anchorterminal.com/compare/puppeteer-vs-selenium.md)\n- [Selenium vs Skyvern](https://www.anchorterminal.com/compare/selenium-vs-skyvern.md)\n- [Selenium vs Steel](https://www.anchorterminal.com/compare/selenium-vs-steel.md)\n- [Selenium vs TinyFish](https://www.anchorterminal.com/compare/selenium-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 Selenium", "url": "" } ], "description": "Selenium scores 73.6 (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", "Selenium BB 73.6", "scores" ], "h1": "agent-browser vs Selenium", "image": "https://www.anchorterminal.com/assets/og/compare-agent-browser-vs-selenium.png", "path": "/compare/agent-browser-vs-selenium", "published": "2026-10-01", "section": "tools", "title": "agent-browser vs Selenium for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-14", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-selenium" }, "tokens": { "markdown": 2500, "slim": 530 }, "version": 1 }