{ "data": { "a": { "slug": "autocua", "name": "AutoCua", "vendor": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)", "vendorUrl": "https://github.com/ComputerUseAgent/AutoCua", "kind": "framework", "category": "desktop-automation", "summary": "AutoCua is an open-source Python agent that operates a computer the way a person does, desktop apps, a terminal, your own Chrome and iOS or Android phones, with any of 60 models from ten providers.", "url": "https://www.anchorterminal.com/tools/autocua", "markdownUrl": "https://www.anchorterminal.com/tools/autocua.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/autocua.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/autocua.json", "dns": "autocua.grade.anchorterminal.com", "repo": "https://github.com/ComputerUseAgent/AutoCua", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "AutoCua" } ], "auth": "none", "authNotes": "No account. You bring an API key for the model provider you choose, kept with chats, Chrome profiles and a credential vault in a local AutoCua_data folder.", "pricing": "free", "pricingNotes": "Free and MIT-licensed. You pay your model provider for tokens. Nothing to buy from the project (checked 2026-11-06).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "A local package with nothing to buy and no payment protocol (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://github.com/ComputerUseAgent/AutoCua#readme", "capabilities": [ "browser.control", "agent.run" ], "tags": [ "open-source", "mit", "python", "computer-use", "local", "new" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 44.3, "grade": "E", "agentReady": false, "rank": 1100, "ranked": true, "rankOf": 1354, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 65, "payments": 60, "reliability": 25, "schema": 42, "security": 38, "transparency": 42 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-06" }, "negative": 0, "verdict": "A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.", "bestFor": "Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.", "strengths": [ "One run_agent call drives the desktop, a terminal, your Chrome, or an iOS or Android device", "Element picking from accessibility trees and OCR instead of pixel coordinates", "Credentials typed from a vault so the model never sees them, in the browser and phone agents", "No telemetry, and nothing downloaded without a yes on the terminal", "MIT licence, a pip wheel per OS and architecture, and 60 models across ten providers" ], "weaknesses": [ "Two weeks old at version 0.1.9, with no changelog file", "No CI running the tests; the only workflow labels issues", "On Windows the model answers UAC elevation prompts itself through a kernel input driver", "Keeps API keys and logged-in Chrome profiles in a local folder next to the checkout", "No API reference beyond the README" ], "agentNotes": [ "pip install AutoCua, then call run_agent with a mode such as \"web use\" or \"computer use\", a provider, a model and a task", "Run it on a machine or account you can afford to lose; it drives real input and keeps logged-in browser profiles", "On Windows, don't install the Interception driver unless you accept the model deciding UAC prompts", "Set AutoCua_DATA_DIR to keep keys and profiles somewhere private", "Phones go over USB from a script; Wi-Fi only through the desktop app" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.3 } ], "editorialScores": { "ergonomics": 55, "maintenance": 65, "payments": 60, "reliability": 25, "schema": 42, "security": 38, "transparency": 70 }, "provenanceScore": 13, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install AutoCua\n# then, in Python:\n# from AutoCua.agent_launcher import run_agent\n# run_agent(mode=\"web use\", provider=\"openrouter\", model=\"gemini-3.8-flash\", task=\"Open wikipedia.org and summarise today's featured article.\")" }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/autocua" }, "area": "developer", "provenance": { "legalEntity": "", "domain": "github.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The licence names Ashish Yadav as copyright holder; most commits are from the GitHub user FunctionFreak. No company, site or terms were found.", "github.com/AutoCua/AutoCua and github.com/ComputerUseAgent/AutoCua serve the same main branch, so one is a rename or mirror of the other." ], "score": 13 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/autocua.json" }, "answer": "Browser Use scores 80.3 (A) on agent readiness against AutoCua's 44.3 (E), and leads in every scored category.", "b": { "slug": "browser-use", "name": "Browser Use", "vendor": "Browser Use", "vendorUrl": "https://browser-use.com", "kind": "http-api", "category": "browser", "summary": "Browser Use runs AI agents that operate a web browser. It has an MIT Python library and CLI, and a hosted cloud with an agent API, managed browsers over CDP and an MCP server.", "url": "https://www.anchorterminal.com/tools/browser-use", "markdownUrl": "https://www.anchorterminal.com/tools/browser-use.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/browser-use.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/browser-use.json", "dns": "browser-use.grade.anchorterminal.com", "repo": "https://github.com/browser-use/browser-use", "license": "MIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of service", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.browser-use.com/api/v4", "packages": [ { "registry": "pypi", "name": "browser-use-sdk" }, { "registry": "npm", "name": "browser-use-sdk" }, { "registry": "pypi", "name": "browser-use" } ], "auth": "api-key", "authNotes": "Self-serve API key from cloud.browser-use.com, sent as the `X-Browser-Use-API-Key` header with no Bearer prefix on the REST API. The hosted MCP server takes `Authorization: Bearer` and still accepts the old header. Keys start with `bu_`, belong to one project and share its credits and concurrency. A key can be full access or restricted at creation to Read or Write per V4 resource (scopes such as `v4:runs:create`), and scopes can't be changed later. A key can carry a monthly spending cap, which is a soft limit. EU keys are separate and work only on api.eu.browser-use.com. The x402 host authenticates by wallet signature with no key.", "pricing": "usage", "pricingNotes": "Pay as you go from prepaid credits, minimum top-up $5, no subscription and no expiry. Browsers $0.02 an hour, rounded up to whole minutes, plus traffic at $5 a GB through the managed residential proxy (on by default) or $0.20 a GB direct or through your own proxy. Hosted agents cost model tokens plus a 20 per cent fee, plus browser time and traffic. $1 of free credit once for eligible Google, GitHub or Microsoft signups, no card. An agent with a wallet can start without an account by x402 (https://browser-use.com/pricing, https://docs.browser-use.com/cloud/guides/x402.md).", "priceSummary": "$0.02 / browser-hr", "where": "both", "x402": { "level": "yes", "evidence": "x402 on https://x402.api.browser-use.com for the V2 and V3 APIs, with an x402 challenge in place of API key auth. The x402 guide says it doesn't support API V4 yet. USDC on Base mainnet, no account or API key. Payments are credit top-ups to a project tied to the wallet, $1 by default or any amount from $0.01 to $100 with an `upto` client, not per-call fees (https://docs.browser-use.com/cloud/guides/x402.md, https://docs.browser-use.com/cloud/guides/x402-agent-wallets.md, checked 2026-10-17).", "endpoints": [ { "url": "https://x402.api.browser-use.com/api/v3/sessions", "priceUsd": null, "network": "eip155:8453" } ] }, "toolCount": 7, "popularity": { "githubStars": 117448, "npmWeekly": 106854, "pypiWeekly": 2090278, "asOf": "2026-10-08" }, "docsUrl": "https://docs.browser-use.com", "llmsTxt": "https://docs.browser-use.com/llms.txt", "openapi": "https://docs.browser-use.com/cloud/openapi/v4.json", "registryName": "com.browser-use/browser-use", "capabilities": [ "browser.control", "browser.hosted", "web.extract" ], "tags": [ "official", "hosted", "open-source", "usage", "no-card", "x402", "openapi", "llms-txt", "mcp", "python", "typescript", "status-page", "soc2" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 80.3, "grade": "A", "agentReady": true, "rank": 9, "ranked": true, "rankOf": 1354, "categoryRank": 1, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 82, "payments": 90, "reliability": 87, "schema": 86, "security": 69, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "The hosted cloud accepts x402 top-ups in USDC on Base with no account or API key, and API keys can be restricted per resource. x402 doesn't cover API V4, the API the docs recommend, the privacy policy says inputs are used to train Browser Use's models, and no prompt-injection guidance was found in the docs.", "bestFor": "An agent that wants to hand a whole browser task to a hosted agent and get a result back, or that needs a low-cost cloud browser over CDP, and for unattended agents that can pay by x402.", "strengths": [ "x402 host at x402.api.browser-use.com takes USDC on Base with no account or API key, and wallet top-ups start at $0.01", "Public prices without login, $0.02 a browser-hour, proxy traffic $5 a GB, model tokens plus a 20 per cent fee", "Restricted API keys take Read or Write per V4 resource, and a call outside them returns 403 naming the missing scope", "The docs let a US project owner turn on zero data retention in the dashboard, though browser-use.com's zero data retention page still describes it as part of an enterprise agreement", "Secret bindings limit each credential to at most 20 named hostnames, and a run takes a `maxCostUsd` cap" ], "weaknesses": [ "The privacy policy says inputs are used to train Browser Use's AI models. Self-service zero data retention covers US projects only and doesn't say what model providers keep", "x402 doesn't support API V4 yet, so a keyless agent is limited to the V2 and V3 APIs", "No prompt-injection guidance found in the cloud docs, though agents read untrusted pages", "No idempotency key on `POST /runs`, and a client timeout leaves the billable run active", "The terms allow the service to be changed or discontinued with or without notice, and no deprecation policy was found" ], "agentNotes": [ "Send the key as `X-Browser-Use-API-Key` with no Bearer prefix on the REST API, where a Bearer header returns 401. The MCP server takes `Authorization: Bearer`", "Stop browsers with `PATCH /api/v4/browsers/{id}` and `{\"action\":\"stop\"}`. Closing CDP or the SDK client leaves the browser billing", "Poll `GET /runs/{id}/status`, not the full run, and wait for the returned Retry-After on 429, which can be 300 seconds at the edge", "Before resubmitting after a timeout, read the existing run's status. The server keeps running and may already have submitted a form", "With a wallet and no key, call x402.api.browser-use.com on `/api/v2` or `/api/v3` routes, since x402 doesn't take V4 yet. A task stops with INSUFFICIENT_CREDITS if credit runs out" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "A", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 80.3 } ], "editorialScores": { "ergonomics": 78, "maintenance": 82, "payments": 90, "reliability": 87, "schema": 86, "security": 69, "transparency": 51 }, "provenanceScore": 81, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-10-27", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install --upgrade browser-use-sdk", "http": "curl https://api.browser-use.com/api/v4/runs -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"task\":\"Find the top Hacker News story\"}'", "claudeCode": "claude mcp add -t http -H \"Authorization: Bearer YOUR_API_KEY\" browser-use https://api.browser-use.com/v3/mcp", "config": { "mcpServers": { "browser-use": { "headers": { "Authorization": "Bearer YOUR_API_KEY" }, "url": "https://api.browser-use.com/v3/mcp" } } }, "x402": "pip install \"browser-use-sdk[x402]\"\n# set BROWSER_USE_X402_PRIVATE_KEY, then use AsyncBrowserUse from browser_use_sdk.v3, or POST https://x402.api.browser-use.com/api/v3/sessions with an x402 client (USDC on eip155:8453)" }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/browser-use" }, "area": "developer", "unitPrices": [ { "item": "Cloud browser", "unit": "browser-hour", "usd": 0.02, "note": "rounded up to whole minutes, one-minute minimum" }, { "item": "Residential proxy traffic", "unit": "gb", "usd": 5, "note": "managed proxy, on by default" }, { "item": "Direct or own-proxy traffic", "unit": "gb", "usd": 0.2 }, { "item": "Agent service fee on model tokens", "unit": "pct", "usd": 20, "note": "added to model cost, plus browser time and traffic" }, { "item": "GPT-5.6 Luna input, fee included", "unit": "1m-tokens", "usd": 0.24, "note": "output $1.44, cached input $0.024" }, { "item": "Claude Sonnet 5 input, fee included", "unit": "1m-tokens", "usd": 2.4, "note": "output $12.00, cached input $0.24" }, { "item": "Claude Opus 5 input, fee included", "unit": "1m-tokens", "usd": 6, "note": "output $30.00, cached input $0.60" }, { "item": "BU 2.0 model API input", "unit": "1m-tokens", "usd": 0.6, "note": "output $3.50, cached input $0.06" } ], "provenance": { "legalEntity": "Browser Use, Inc.", "domain": "browser-use.com", "domainRegistered": "2024-11-11", "endpointOnVendorDomain": true, "terms": "https://browser-use.com/legal/terms-of-service", "privacy": "https://browser-use.com/privacy", "statusPage": "https://status.browser-use.com", "changelog": "https://browser-use.com/changelog", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "The privacy policy names Browser Use, Inc. as the responsible entity. The terms of service, last revised 15 October 2026, name Browser Use Inc. and say it is headquartered in the United States.", "browser-use.com/.well-known/security.txt gives security@browser-use.com and the SOC 2 page as contact and policy, with a Canonical line and no Expires field, which RFC 9116 requires, re-read on 2026-11-01.", "RDAP for browser-use.com gives a registration date of 2024-11-11, per the 8 October check.", "The API, the x402 host, the EU API and the MCP server all answer on browser-use.com subdomains.", "The DPA of 30 July 2026 links the sub-processor list in a Vanta trust centre, which we didn't read." ], "score": 81 }, "requirements": { "agentAlone": true, "card": "unknown", "freeTier": true, "minutes": 4, "credential": "mixed", "hosting": [ "US", "EU" ], "euResidency": "yes", "trainsOnData": "unknown", "zeroRetention": "enterprise", "certifications": [ "SOC 2 Type II", "GDPR" ], "dpa": true, "selfHost": "no" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/browser-use.json", "live": { "slug": "browser-use", "probe": { "target": "https://api.browser-use.com/api/v4", "method": "get", "lastAt": "2026-11-06T09:47:22.013867664Z", "lastOk": true, "lastStatus": 404, "lastMs": 386, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 389, "p95ms24h": 504, "samples24h": 221, "samples30d": 7137, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 248, "ok": 248 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 102, "ok": 102 } ] }, "vendorStatus": { "page": "https://status.browser-use.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-06T05:41:11.189359002Z" }, "versions": [ { "registry": "github", "name": "browser-use/browser-use", "version": "0.13.14", "released": "2026-10-26", "seenAt": "2026-11-05T21:18:26.146408801Z" }, { "registry": "mcp-registry", "name": "com.browser-use/browser-use", "version": "0.13.11", "seenAt": "2026-11-05T17:32:31.346782632Z" }, { "registry": "npm", "name": "browser-use-sdk", "version": "3.12.1", "seenAt": "2026-11-05T21:18:24.305982265Z" }, { "registry": "pypi", "name": "browser-use", "version": "0.13.14", "released": "2026-10-26", "seenAt": "2026-11-05T21:18:25.125828116Z" }, { "registry": "pypi", "name": "browser-use-sdk", "version": "3.12.1", "released": "2026-10-17", "seenAt": "2026-11-05T21:18:24.1099521Z" } ], "githubStars": 120124, "npmWeekly": 221896, "pypiWeekly": 1409040, "securityTxt": { "url": "https://browser-use.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-11-05T15:56:10.976618065Z" }, "llmsTxt": { "url": "https://docs.browser-use.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:25:21.589630821Z" }, "domain": { "domain": "browser-use.com", "registered": "2024-11-11", "source": "https://rdap.verisign.com/com/v1/domain/browser-use.com", "checkedAt": "2026-11-01T14:23:51.368429125Z" }, "pages": [ { "url": "https://browser-use.com/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-11-05T12:47:24.018280105Z", "changedAt": "2026-11-01T06:36:56.630899737Z", "fingerprint": "3edb7b63e32b" }, { "url": "https://browser-use.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-11-05T12:47:28.213358453Z", "changedAt": "2026-11-01T06:37:00.836346534Z", "fingerprint": "42fee43ea928" }, { "url": "https://browser-use.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-05T12:47:30.294956521Z", "changedAt": "2026-10-25T02:40:59.44641638Z", "fingerprint": "dc1066805bf0" }, { "url": "https://browser-use.com/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-11-05T12:47:26.26891771Z", "changedAt": "2026-10-25T02:40:55.729696033Z", "fingerprint": "456c258dfb4e" } ], "github": { "repo": "browser-use/browser-use", "checkedAt": "2026-11-02T08:36:46.678007672Z", "stars": 119798, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T01:31:56Z", "openIssues": 178, "openPRs": 439, "issuesOpened90d": 146, "issuesClosed90d": 59, "prsMerged90d": 118, "ci": { "branch": "main", "runs": 50, "success": 45, "failure": 0, "other": 5, "latest": "success", "latestAt": "2026-10-30T04:30:00Z" }, "advisories": [ { "ghsa": "GHSA-x39x-9qw5-ghrf", "cve": "CVE-2025-47241", "severity": "critical", "published": "2025-05-04T06:30:46Z" } ], "replies": { "sampled": 25, "unanswered": 22, "medianDays": 4.5 } }, "updatedAt": "2026-11-06T09:47:22.013867664Z" } }, "edges": [ { "by": 62, "category": "reliability", "leads": "browser-use", "name": "Reliability", "reasons": { "a": "Local package. Installs from PyPI as AutoCua with Python 3.10 or later and the supported platforms stated (20). No CI runs the tests; the only workflow, use_case_label.yml, labels issues (0). GitHub issues weren't read, so the open-issue line is scored absent (0). Four tags in a week with no changelog file (5). Version 0.1.9 (0). 20 + 0 + 0 + 5 + 0 = 25.", "b": "Graded as a hosted service, on Browser Use Cloud. status.browser-use.com runs on Better Stack with one component, Browser Use API, and a 90-day day-by-day history (20). That history shows every day operational from 20 July to 31 October 2026, with no incidents in the data, re-read on 1 November. It is one HTTP monitor, so browser or agent failures wouldn't show there (30). Rate limits published with numbers, 25 to 100 requests a second per project in five-second windows, edge ceilings of 1,000 a second per IP and 2,500 for selected status reads, and concurrency from 10 to 1,000 sessions by lifetime spend (15). 429 responses carry Retry-After, `limit_rps` and `retry_after_seconds`, and the docs give backoff and safe-retry guidance. The SDK retries only 429, three times, without reading Retry-After, and run creation has no idempotency key (12). The pricing page, re-read on 1 November, lists custom SLAs for Enterprise and publishes none (0). API V4 is the current API. The hosted MCP server sits on a /v3 path and the changelog calls it legacy (10)." }, "scores": { "a": 25, "b": 87 } }, { "by": 44, "category": "schema", "leads": "browser-use", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading. No API reference or typed interface beyond run_agent's documented arguments (5 of 25). No llms.txt (0). The README says what each mode drives and where it runs, and agent_capabilities.md lists what it can do (16 of 20). Modes and device are documented strings (6 of 15). Many examples, no documented errors (10 of 15). Tags without a changelog (5 of 15). 5 + 0 + 16 + 6 + 10 + 5 = 42.", "b": "OpenAPI 3.1.0 documents for API v2, v3 and v4, the v4 one with 50 operations on 33 paths and 73 schemas on 17 October (25). llms.txt, a full-text bundle and a Markdown copy of every docs page (10). The guides say which product and API version to pick and when not to. In the v4 document four operations have no description, Create Run among them, and request fields such as `task`, `sessionId` and `maxCostUsd` have none. The seven MCP tools have one-line descriptions (13). Required fields are marked and there are 12 enums, but `modelParams` is free-form and six schemas allow any extra properties, per the 8 October check (10). Python, TypeScript and curl examples throughout, named error schemas for 402, 404 and 429, and a troubleshooting table by status code. 36 of the 50 operations document an error beyond 422, 404 on 32 and 403 on 24, though only three document 429. The 8 October note said most documented only 422, which the 8 October copy of the spec in the vendor's docs repository doesn't bear out either (13). Versioned paths /api/v2, /api/v3 and /api/v4 and a dated public changelog, newest entry 24 August 2026 (15)." }, "scores": { "a": 42, "b": 86 } }, { "by": 31, "category": "security", "leads": "browser-use", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading (telemetry, approvals, guardrails, sandboxing). Provider keys stored in a local folder with Chrome profiles (10 of 30). The worker tools are an allow-list with no write tool, unseen ids are refused, downloads need a yes, but on Windows the model answers UAC elevation prompts itself through a kernel driver, with no person asked (6 of 20). The scraping ruleset has a prompt-injection instruction to log page text that gives instructions (10 of 15). Runs are logged in the app, with no audit log (7 of 15). No security policy, disclosure route or advisories found (5 of 20, for the vault and certificate handling). 10 + 6 + 10 + 7 + 5 = 38.", "b": "API keys in a header, several per project, each with an optional monthly spending cap that the docs call a soft limit. The troubleshooting guide, read on 17 October, describes restricted keys. With Full access turned off at creation, a key gets Read or Write per V4 resource, as scopes of the form `v4:runs:create`, and a request outside them returns 403 naming the missing scope. Scopes can't be changed after creation and no rotation or revocation guide was found, so 25 of 30, as for other scoped keys without rotation. The x402 host authenticates by wallet signature (25). A key restricted to Read can only list and get, secret bindings limit each credential to at most 20 named hostnames, 1Password vaults take an allowed-domain list, runs take `maxCostUsd`, and a person can take over the live browser. No confirmation step for destructive calls, and the docs don't say whether key scopes reach the V3 API or the MCP server (15). Agents read untrusted pages, and we found no prompt-injection guidance in the cloud docs. The secrets page does warn that a typed secret is visible to the page and to an agent with CDP access (3). Ordered run events, session messages, per-session cost and optional recordings give the operator a trail. No audit log of key or account changes found (12). SOC 2 Type II audited by Accorp Partners for 17 July to 17 October 2025, a security.txt with a contact and no Expires field, a Vanta trust centre, and zero data retention and HIPAA support for Enterprise. No bug bounty or public advisories found (14)." }, "scores": { "a": 38, "b": 69 } }, { "by": 30, "category": "payments", "leads": "browser-use", "name": "Payments \u0026 pricing", "reasons": { "a": "Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.", "b": "x402 on x402.api.browser-use.com for the V2 and V3 APIs, in USDC on Base. Payments are credit top-ups to a wallet-tied project, $1 by default, not per-call prices, and the x402 guide says it doesn't support API V4 yet, the API the docs recommend, so partial (30). Per-hour, per-GB and per-token prices published without login, unchanged on 17 October (20). $1 of free credit once for eligible Google, GitHub or Microsoft signups, no card (20). An agent with a funded wallet gets access with no account or API key. The separate agent signup endpoints are off and return 403, per the 8 October check (20)." }, "scores": { "a": 60, "b": 90 } }, { "by": 24, "category": "transparency", "leads": "browser-use", "name": "Transparency \u0026 trust", "reasons": { "a": "MIT (30). Says it sends data only to the chosen model provider and keeps everything else locally, and the source agrees (20 of 30). No deprecation policy (0). States no telemetry, and none was found (20). 30 + 20 + 0 + 20 = 70.", "b": "The cloud is closed with published terms, last revised 15 October 2026. The library and the SDK are MIT (20). The privacy policy, which carries no date in the text we read, says 'We use Inputs to train our AI models in order to improve the Services' and keeps data as long as necessary with no periods, re-read on 1 November. The DPA of 30 July 2026 bars use of customer personal data beyond the service, which doesn't sit easily with that. The docs' zero data retention page, last modified 24 October per the docs sitemap, says a project owner can turn it on in Cloud settings with no enterprise contract, covering US session data, with cleanup every 15 minutes, V4 results to be saved within 15 minutes, and no recordings or session history. It doesn't say what model providers keep. The zero data retention page on browser-use.com still says it 'is part of an enterprise agreement' and to email sales, re-read on 1 November. API recording is off by default. With the privacy policy's training sentence and the two zero data retention pages at odds, the statements still don't agree, so 14 stands (14). No deprecation policy found, and the terms, re-read on 1 November, still allow the service to be changed or discontinued with or without notice. The docs mark V2 as legacy and Box, Bux and Skills as retired, without dates (5). The EU page names Frankfurt AWS, Datadog EU and an OpenRouter EU route. The sub-processor list is in a Vanta trust centre we didn't read, and the DPA promises 10 days' notice of new sub-processors (12)." }, "scores": { "a": 42, "b": 66 } }, { "by": 23, "category": "ergonomics", "leads": "browser-use", "name": "Agent ergonomics", "reasons": { "a": "Framework reading. One call with a mode, provider, model and task runs a whole agent (20 of 25). A separate compression agent splices handoff summaries in, and runs are capped and stoppable (15 of 20). Permission and blocked-input errors are reported specifically, with no error reference (8 of 20). No resume or retry semantics described (2 of 20). Sensible defaults (simulators unless device is set), Python only (10 of 15). 20 + 15 + 8 + 2 + 10 = 55.", "b": "The hosted MCP server has seven compact tools. The API has a minimal status endpoint for polling, and run events take `limit`, an `after` cursor and `include_output` (22). Cursor and limit on runs, sessions, files and downloads, and page number and size on browsers, profiles and extensions, so two pagination styles, with status, session and metadata filters (17). Errors carry codes an agent can act on, such as `api_key_monthly_spend_limit_reached` with `cap` and `spent`, `rate_limited` with `limit_rps`, and `domain_not_allowed` with the origin. Other errors are a bare `detail` string (16). Cancel, session delete and workspace delete are documented as idempotent. `POST /runs` has no idempotency key, and the docs tell callers to check the earlier run before resubmitting. We didn't read the MCP tools' annotations (8). Only `task` is required to create a run, with a default model, and official SDKs cover Python and TypeScript (15)." }, "scores": { "a": 55, "b": 78 } } ], "facts": [ { "a": "Agent framework", "b": "HTTP API", "name": "Kind" }, { "a": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)", "b": "Browser Use", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.browser-use.com/api/v4", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, Streamable HTTP, stdio", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "yes", "name": "x402" }, { "a": "MIT", "b": "MIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of service", "name": "Licence" }, { "a": "none", "b": "7", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "com.browser-use/browser-use", "name": "MCP registry" }, { "a": "2026-11-04", "b": "2026-10-30", "name": "Last release" }, { "a": "no document linked", "b": "2026-07-15", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "yes", "name": "Customer content may train models" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "117k stars, 107k npm/wk, 2.1M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Browser Use scores 80.3 (A) on agent readiness against AutoCua's 44.3 (E), and leads in every scored category.", "question": "Which is better for AI agents, AutoCua or Browser Use?" }, { "answer": "No hosted endpoint is listed for AutoCua. Browser Use has a hosted endpoint at https://api.browser-use.com/api/v4.", "question": "Can an agent call AutoCua and Browser Use without installing anything?" }, { "answer": "Yes. AutoCua is open source (MIT). Browser Use is open source (MIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of service).", "question": "Are AutoCua and Browser Use open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "No key needed to call it" ], "goodFor": "Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.", "slug": "autocua", "watchFor": "Two weeks old at version 0.1.9, with no changelog file" }, { "aheadOn": [ "Reliability, 87 against 25", "Schema \u0026 documentation, 86 against 42", "Agent ergonomics, 78 against 55", "Security \u0026 auth, 69 against 38", "Payments \u0026 pricing, 90 against 60", "Maintenance \u0026 community, 82 against 65", "Transparency \u0026 trust, 66 against 42" ], "also": [ "Agent-ready, a grade of BB or better", "An agent can pay per call over x402, with no account", "A hosted endpoint, with nothing to install", "Runs on your own machine", "Free to start without a card" ], "goodFor": "An agent that wants to hand a whole browser task to a hosted agent and get a result back, or that needs a low-cost cloud browser over CDP, and for unattended agents that can pay by x402.", "slug": "browser-use", "watchFor": "The privacy policy says inputs are used to train Browser Use's AI models. Self-service zero data retention covers US projects only and doesn't say what model providers keep" } ], "history": { "autocua": null, "browser-use": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 80.2, "fromGrade": "A", "to": 80.3, "toGrade": "A" }, { "causes": [ "product", "correction" ], "date": "2026-10-17", "delta": 2.3, "from": 77.9, "fromGrade": "BB", "to": 80.2, "toGrade": "A" } ] }, "job": { "capability": "browser.control", "name": "Browser automation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-autocua.json", "title": "agent-browser vs AutoCua", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-autocua" }, { "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/airtop-vs-autocua.json", "title": "Airtop vs AutoCua", "url": "https://www.anchorterminal.com/compare/airtop-vs-autocua" }, { "json": "https://www.anchorterminal.com/compare/airtop-vs-browser-use.json", "title": "Airtop vs Browser Use", "url": "https://www.anchorterminal.com/compare/airtop-vs-browser-use" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.json", "title": "Anchor Browser vs AutoCua", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-browser-use.json", "title": "Anchor Browser vs Browser Use", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-browser-use" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-browserless.json", "title": "AutoCua vs Browserless", "url": "https://www.anchorterminal.com/compare/autocua-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-bx-playwright.json", "title": "AutoCua vs BxPlaywright", "url": "https://www.anchorterminal.com/compare/autocua-vs-bx-playwright" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp.json", "title": "AutoCua vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.json", "title": "AutoCua vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser.json", "title": "AutoCua vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-kane-cli.json", "title": "AutoCua vs Kane CLI", "url": "https://www.anchorterminal.com/compare/autocua-vs-kane-cli" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-lightpanda.json", "title": "AutoCua vs Lightpanda", "url": "https://www.anchorterminal.com/compare/autocua-vs-lightpanda" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-notte.json", "title": "AutoCua vs Notte", "url": "https://www.anchorterminal.com/compare/autocua-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.json", "title": "AutoCua vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-pomerado.json", "title": "AutoCua vs Pomerado", "url": "https://www.anchorterminal.com/compare/autocua-vs-pomerado" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer.json", "title": "AutoCua vs Puppeteer", "url": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived.json", "title": "AutoCua vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-robocorp.json", "title": "AutoCua vs Robocorp", "url": "https://www.anchorterminal.com/compare/autocua-vs-robocorp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-selenium.json", "title": "AutoCua vs Selenium", "url": "https://www.anchorterminal.com/compare/autocua-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-skyvern.json", "title": "AutoCua vs Skyvern", "url": "https://www.anchorterminal.com/compare/autocua-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-steel.json", "title": "AutoCua vs Steel", "url": "https://www.anchorterminal.com/compare/autocua-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-tinyfish.json", "title": "AutoCua vs TinyFish", "url": "https://www.anchorterminal.com/compare/autocua-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-browserbase.json", "title": "Browser Use vs Browserbase", "url": "https://www.anchorterminal.com/compare/browser-use-vs-browserbase" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-browserless.json", "title": "Browser Use vs Browserless", "url": "https://www.anchorterminal.com/compare/browser-use-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-bx-playwright.json", "title": "Browser Use vs BxPlaywright", "url": "https://www.anchorterminal.com/compare/browser-use-vs-bx-playwright" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-chrome-devtools-mcp.json", "title": "Browser Use vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/browser-use-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp.json", "title": "Browser Use vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-hyperbrowser.json", "title": "Browser Use vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/browser-use-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-kane-cli.json", "title": "Browser Use vs Kane CLI", "url": "https://www.anchorterminal.com/compare/browser-use-vs-kane-cli" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-lightpanda.json", "title": "Browser Use vs Lightpanda", "url": "https://www.anchorterminal.com/compare/browser-use-vs-lightpanda" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-notte.json", "title": "Browser Use vs Notte", "url": "https://www.anchorterminal.com/compare/browser-use-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-playwright-mcp.json", "title": "Browser Use vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/browser-use-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-pomerado.json", "title": "Browser Use vs Pomerado", "url": "https://www.anchorterminal.com/compare/browser-use-vs-pomerado" }, { "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/browser-use-vs-puppeteer-reference-server-archived.json", "title": "Browser Use vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/browser-use-vs-puppeteer-reference-server-archived" }, { "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/browser-use-vs-skyvern.json", "title": "Browser Use vs Skyvern", "url": "https://www.anchorterminal.com/compare/browser-use-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-steel.json", "title": "Browser Use vs Steel", "url": "https://www.anchorterminal.com/compare/browser-use-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-tinyfish.json", "title": "Browser Use vs TinyFish", "url": "https://www.anchorterminal.com/compare/browser-use-vs-tinyfish" } ], "panel": null, "scores": [ { "autocua": 25, "browser-use": 87, "by": 62, "edge": "browser-use", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "autocua": 42, "browser-use": 86, "by": 44, "edge": "browser-use", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "autocua": 55, "browser-use": 78, "by": 23, "edge": "browser-use", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "autocua": 38, "browser-use": 69, "by": 31, "edge": "browser-use", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "autocua": 60, "browser-use": 90, "by": 30, "edge": "browser-use", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "autocua": 65, "browser-use": 82, "by": 17, "edge": "browser-use", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "autocua": 42, "browser-use": 66, "by": 24, "edge": "browser-use", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Browser Use scores 80.3 (A) on agent readiness against AutoCua's 44.3 (E), and leads in every scored category. Both do browser automation. Browser Use accepts x402. AutoCua doesn't.", "tasks": null, "tutorials": [], "verdicts": { "autocua": "A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.", "browser-use": "The hosted cloud accepts x402 top-ups in USDC on Base with no account or API key, and API keys can be restricted per resource. x402 doesn't cover API V4, the API the docs recommend, the privacy policy says inputs are used to train Browser Use's models, and no prompt-injection guidance was found in the docs." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/autocua-vs-browser-use", "json": "https://www.anchorterminal.com/compare/autocua-vs-browser-use.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/autocua-vs-browser-use.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/autocua-vs-browser-use.min.md" }, "markdown": "Browser Use scores 80.3 (A) on agent readiness against AutoCua's 44.3 (E), and leads in every scored category. Both do browser automation. Browser Use accepts x402. AutoCua doesn't.\n\n- AutoCua: grade E, 44.3/100, rank #1100 of 1354. Markdown https://www.anchorterminal.com/tools/autocua.md · JSON https://www.anchorterminal.com/api/v1/tools/autocua.json\n- Browser Use: grade A, 80.3/100, rank #9 of 1354. Markdown https://www.anchorterminal.com/tools/browser-use.md · JSON https://www.anchorterminal.com/api/v1/tools/browser-use.json\n- Best desktop and mobile app automation for AI agents: https://www.anchorterminal.com/best/desktop-automation/index.md\n- All 48 desktop comparisons: https://www.anchorterminal.com/compare/desktop-automation/index.md\n- Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md\n- All 230 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md\n\n## Which one, for what\n\n### AutoCua (E)\n\nGood for: Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: Two weeks old at version 0.1.9, with no changelog file\n\n### Browser Use (A)\n\nGood for: An agent that wants to hand a whole browser task to a hosted agent and get a result back, or that needs a low-cost cloud browser over CDP, and for unattended agents that can pay by x402.\n\nAhead on:\n- Reliability, 87 against 25\n- Schema \u0026 documentation, 86 against 42\n- Agent ergonomics, 78 against 55\n- Security \u0026 auth, 69 against 38\n- Payments \u0026 pricing, 90 against 60\n- Maintenance \u0026 community, 82 against 65\n- Transparency \u0026 trust, 66 against 42\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- An agent can pay per call over x402, with no account\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: The privacy policy says inputs are used to train Browser Use's AI models. Self-service zero data retention covers US projects only and doesn't say what model providers keep\n\n\n## Why the edge\n\n### Reliability: Browser Use +62\n\n- AutoCua (25): Local package. Installs from PyPI as AutoCua with Python 3.10 or later and the supported platforms stated (20). No CI runs the tests; the only workflow, use_case_label.yml, labels issues (0). GitHub issues weren't read, so the open-issue line is scored absent (0). Four tags in a week with no changelog file (5). Version 0.1.9 (0). 20 + 0 + 0 + 5 + 0 = 25.\n- Browser Use (87): Graded as a hosted service, on Browser Use Cloud. status.browser-use.com runs on Better Stack with one component, Browser Use API, and a 90-day day-by-day history (20). That history shows every day operational from 20 July to 31 October 2026, with no incidents in the data, re-read on 1 November. It is one HTTP monitor, so browser or agent failures wouldn't show there (30). Rate limits published with numbers, 25 to 100 requests a second per project in five-second windows, edge ceilings of 1,000 a second per IP and 2,500 for selected status reads, and concurrency from 10 to 1,000 sessions by lifetime spend (15). 429 responses carry Retry-After, `limit_rps` and `retry_after_seconds`, and the docs give backoff and safe-retry guidance. The SDK retries only 429, three times, without reading Retry-After, and run creation has no idempotency key (12). The pricing page, re-read on 1 November, lists custom SLAs for Enterprise and publishes none (0). API V4 is the current API. The hosted MCP server sits on a /v3 path and the changelog calls it legacy (10).\n\n### Schema \u0026 documentation: Browser Use +44\n\n- AutoCua (42): Framework reading. No API reference or typed interface beyond run_agent's documented arguments (5 of 25). No llms.txt (0). The README says what each mode drives and where it runs, and agent_capabilities.md lists what it can do (16 of 20). Modes and device are documented strings (6 of 15). Many examples, no documented errors (10 of 15). Tags without a changelog (5 of 15). 5 + 0 + 16 + 6 + 10 + 5 = 42.\n- Browser Use (86): OpenAPI 3.1.0 documents for API v2, v3 and v4, the v4 one with 50 operations on 33 paths and 73 schemas on 17 October (25). llms.txt, a full-text bundle and a Markdown copy of every docs page (10). The guides say which product and API version to pick and when not to. In the v4 document four operations have no description, Create Run among them, and request fields such as `task`, `sessionId` and `maxCostUsd` have none. The seven MCP tools have one-line descriptions (13). Required fields are marked and there are 12 enums, but `modelParams` is free-form and six schemas allow any extra properties, per the 8 October check (10). Python, TypeScript and curl examples throughout, named error schemas for 402, 404 and 429, and a troubleshooting table by status code. 36 of the 50 operations document an error beyond 422, 404 on 32 and 403 on 24, though only three document 429. The 8 October note said most documented only 422, which the 8 October copy of the spec in the vendor's docs repository doesn't bear out either (13). Versioned paths /api/v2, /api/v3 and /api/v4 and a dated public changelog, newest entry 24 August 2026 (15).\n\n### Security \u0026 auth: Browser Use +31\n\n- AutoCua (38): Framework reading (telemetry, approvals, guardrails, sandboxing). Provider keys stored in a local folder with Chrome profiles (10 of 30). The worker tools are an allow-list with no write tool, unseen ids are refused, downloads need a yes, but on Windows the model answers UAC elevation prompts itself through a kernel driver, with no person asked (6 of 20). The scraping ruleset has a prompt-injection instruction to log page text that gives instructions (10 of 15). Runs are logged in the app, with no audit log (7 of 15). No security policy, disclosure route or advisories found (5 of 20, for the vault and certificate handling). 10 + 6 + 10 + 7 + 5 = 38.\n- Browser Use (69): API keys in a header, several per project, each with an optional monthly spending cap that the docs call a soft limit. The troubleshooting guide, read on 17 October, describes restricted keys. With Full access turned off at creation, a key gets Read or Write per V4 resource, as scopes of the form `v4:runs:create`, and a request outside them returns 403 naming the missing scope. Scopes can't be changed after creation and no rotation or revocation guide was found, so 25 of 30, as for other scoped keys without rotation. The x402 host authenticates by wallet signature (25). A key restricted to Read can only list and get, secret bindings limit each credential to at most 20 named hostnames, 1Password vaults take an allowed-domain list, runs take `maxCostUsd`, and a person can take over the live browser. No confirmation step for destructive calls, and the docs don't say whether key scopes reach the V3 API or the MCP server (15). Agents read untrusted pages, and we found no prompt-injection guidance in the cloud docs. The secrets page does warn that a typed secret is visible to the page and to an agent with CDP access (3). Ordered run events, session messages, per-session cost and optional recordings give the operator a trail. No audit log of key or account changes found (12). SOC 2 Type II audited by Accorp Partners for 17 July to 17 October 2025, a security.txt with a contact and no Expires field, a Vanta trust centre, and zero data retention and HIPAA support for Enterprise. No bug bounty or public advisories found (14).\n\n### Payments \u0026 pricing: Browser Use +30\n\n- AutoCua (60): Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.\n- Browser Use (90): x402 on x402.api.browser-use.com for the V2 and V3 APIs, in USDC on Base. Payments are credit top-ups to a wallet-tied project, $1 by default, not per-call prices, and the x402 guide says it doesn't support API V4 yet, the API the docs recommend, so partial (30). Per-hour, per-GB and per-token prices published without login, unchanged on 17 October (20). $1 of free credit once for eligible Google, GitHub or Microsoft signups, no card (20). An agent with a funded wallet gets access with no account or API key. The separate agent signup endpoints are off and return 403, per the 8 October check (20).\n\n### Transparency \u0026 trust: Browser Use +24\n\n- AutoCua (42): MIT (30). Says it sends data only to the chosen model provider and keeps everything else locally, and the source agrees (20 of 30). No deprecation policy (0). States no telemetry, and none was found (20). 30 + 20 + 0 + 20 = 70.\n- Browser Use (66): The cloud is closed with published terms, last revised 15 October 2026. The library and the SDK are MIT (20). The privacy policy, which carries no date in the text we read, says 'We use Inputs to train our AI models in order to improve the Services' and keeps data as long as necessary with no periods, re-read on 1 November. The DPA of 30 July 2026 bars use of customer personal data beyond the service, which doesn't sit easily with that. The docs' zero data retention page, last modified 24 October per the docs sitemap, says a project owner can turn it on in Cloud settings with no enterprise contract, covering US session data, with cleanup every 15 minutes, V4 results to be saved within 15 minutes, and no recordings or session history. It doesn't say what model providers keep. The zero data retention page on browser-use.com still says it 'is part of an enterprise agreement' and to email sales, re-read on 1 November. API recording is off by default. With the privacy policy's training sentence and the two zero data retention pages at odds, the statements still don't agree, so 14 stands (14). No deprecation policy found, and the terms, re-read on 1 November, still allow the service to be changed or discontinued with or without notice. The docs mark V2 as legacy and Box, Bux and Skills as retired, without dates (5). The EU page names Frankfurt AWS, Datadog EU and an OpenRouter EU route. The sub-processor list is in a Vanta trust centre we didn't read, and the DPA promises 10 days' notice of new sub-processors (12).\n\n### Agent ergonomics: Browser Use +23\n\n- AutoCua (55): Framework reading. One call with a mode, provider, model and task runs a whole agent (20 of 25). A separate compression agent splices handoff summaries in, and runs are capped and stoppable (15 of 20). Permission and blocked-input errors are reported specifically, with no error reference (8 of 20). No resume or retry semantics described (2 of 20). Sensible defaults (simulators unless device is set), Python only (10 of 15). 20 + 15 + 8 + 2 + 10 = 55.\n- Browser Use (78): The hosted MCP server has seven compact tools. The API has a minimal status endpoint for polling, and run events take `limit`, an `after` cursor and `include_output` (22). Cursor and limit on runs, sessions, files and downloads, and page number and size on browsers, profiles and extensions, so two pagination styles, with status, session and metadata filters (17). Errors carry codes an agent can act on, such as `api_key_monthly_spend_limit_reached` with `cap` and `spent`, `rate_limited` with `limit_rps`, and `domain_not_allowed` with the origin. Other errors are a bare `detail` string (16). Cancel, session delete and workspace delete are documented as idempotent. `POST /runs` has no idempotency key, and the docs tell callers to check the earlier run before resubmitting. We didn't read the MCP tools' annotations (8). Only `task` is required to create a run, with a default model, and official SDKs cover Python and TypeScript (15).\n\n## Score by category\n\n| Category | Weight | AutoCua | Browser Use | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 87 | Browser Use +62 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 42 | 86 | Browser Use +44 |\n| Agent ergonomics | 13% (16.2 this run) | 55 | 78 | Browser Use +23 |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 69 | Browser Use +31 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 90 | Browser Use +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 82 | Browser Use +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 42 | 66 | Browser Use +24 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **44.3 · E** | **80.3 · A** | |\n\n## Facts side by side\n\n| Fact | AutoCua | Browser Use |\n| --- | --- | --- |\n| Kind | Agent framework | HTTP API |\n| Vendor | Ashish Yadav and contributors (ComputerUseAgent on GitHub) | Browser Use |\n| Hosted endpoint | no (local only) | `https://api.browser-use.com/api/v4` |\n| Transports | | HTTP, Streamable HTTP, stdio |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | yes |\n| Licence | MIT | MIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of service |\n| Tools exposed | none | 7 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `com.browser-use/browser-use` |\n| Last release | 2026-11-04 | 2026-10-30 |\n| Terms last updated | no document linked | 2026-07-15 |\n| Privacy policy last updated | no document linked | no date given |\n| Customer content may train models | not read yet | yes |\n| Terms restrict automated access | not read yet | yes |\n| Terms restrict benchmarking | not read yet | yes |\n| Terms or service can change without notice | not read yet | yes |\n| Arbitration or class-action waiver | not read yet | yes |\n| Popularity | none | 117k stars, 107k npm/wk, 2.1M PyPI/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### AutoCua\n\nNo score change since it was listed.\n\n### Browser Use\n\n- +0.1 on 27 October 2026: checklist\n- +2.3 on 17 October 2026 (BB to A): product, correction\n\n## Verdicts\n\n**AutoCua.** A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.\n\n**Browser Use.** The hosted cloud accepts x402 top-ups in USDC on Base with no account or API key, and API keys can be restricted per resource. x402 doesn't cover API V4, the API the docs recommend, the privacy policy says inputs are used to train Browser Use's models, and no prompt-injection guidance was found in the docs.\n\n## Before you call either\n\n### AutoCua\n\n1. pip install AutoCua, then call run_agent with a mode such as \"web use\" or \"computer use\", a provider, a model and a task\n2. Run it on a machine or account you can afford to lose; it drives real input and keeps logged-in browser profiles\n3. On Windows, don't install the Interception driver unless you accept the model deciding UAC prompts\n4. Set AutoCua_DATA_DIR to keep keys and profiles somewhere private\n5. Phones go over USB from a script; Wi-Fi only through the desktop app\n\n### Browser Use\n\n1. Send the key as `X-Browser-Use-API-Key` with no Bearer prefix on the REST API, where a Bearer header returns 401. The MCP server takes `Authorization: Bearer`\n2. Stop browsers with `PATCH /api/v4/browsers/{id}` and `{\"action\":\"stop\"}`. Closing CDP or the SDK client leaves the browser billing\n3. Poll `GET /runs/{id}/status`, not the full run, and wait for the returned Retry-After on 429, which can be 300 seconds at the edge\n4. Before resubmitting after a timeout, read the existing run's status. The server keeps running and may already have submitted a form\n5. With a wallet and no key, call x402.api.browser-use.com on `/api/v2` or `/api/v3` routes, since x402 doesn't take V4 yet. A task stops with INSUFFICIENT_CREDITS if credit runs out\n\n## Questions\n\n### Which is better for AI agents, AutoCua or Browser Use?\n\nBrowser Use scores 80.3 (A) on agent readiness against AutoCua's 44.3 (E), and leads in every scored category.\n\n### Can an agent call AutoCua and Browser Use without installing anything?\n\nNo hosted endpoint is listed for AutoCua. Browser Use has a hosted endpoint at https://api.browser-use.com/api/v4.\n\n### Are AutoCua and Browser Use open source?\n\nYes. AutoCua is open source (MIT). Browser Use is open source (MIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of service).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/autocua-vs-browser-use.json, and with the fewest tokens: https://www.anchorterminal.com/compare/autocua-vs-browser-use.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"autocua\", \"b\": \"browser-use\"}`. From a terminal: `anchor compare autocua browser-use`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/autocua.json and https://www.anchorterminal.com/api/v1/tools/browser-use.json\n\n## Other comparisons with AutoCua or Browser Use\n\n- [agent-browser vs AutoCua](https://www.anchorterminal.com/compare/agent-browser-vs-autocua.md)\n- [agent-browser vs Browser Use](https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.md)\n- [Airtop vs AutoCua](https://www.anchorterminal.com/compare/airtop-vs-autocua.md)\n- [Airtop vs Browser Use](https://www.anchorterminal.com/compare/airtop-vs-browser-use.md)\n- [Anchor Browser vs AutoCua](https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.md)\n- [Anchor Browser vs Browser Use](https://www.anchorterminal.com/compare/anchor-browser-vs-browser-use.md)\n- [AutoCua vs Browserless](https://www.anchorterminal.com/compare/autocua-vs-browserless.md)\n- [AutoCua vs BxPlaywright](https://www.anchorterminal.com/compare/autocua-vs-bx-playwright.md)\n- [AutoCua vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp.md)\n- [AutoCua vs Functionize MCP server](https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.md)\n- [AutoCua vs Hyperbrowser](https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser.md)\n- [AutoCua vs Kane CLI](https://www.anchorterminal.com/compare/autocua-vs-kane-cli.md)\n- [AutoCua vs Lightpanda](https://www.anchorterminal.com/compare/autocua-vs-lightpanda.md)\n- [AutoCua vs Notte](https://www.anchorterminal.com/compare/autocua-vs-notte.md)\n- [AutoCua vs Playwright MCP](https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.md)\n- [AutoCua vs Pomerado](https://www.anchorterminal.com/compare/autocua-vs-pomerado.md)\n- [AutoCua vs Puppeteer](https://www.anchorterminal.com/compare/autocua-vs-puppeteer.md)\n- [AutoCua vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived.md)\n- [AutoCua vs Robocorp](https://www.anchorterminal.com/compare/autocua-vs-robocorp.md)\n- [AutoCua vs Selenium](https://www.anchorterminal.com/compare/autocua-vs-selenium.md)\n- [AutoCua vs Skyvern](https://www.anchorterminal.com/compare/autocua-vs-skyvern.md)\n- [AutoCua vs Steel](https://www.anchorterminal.com/compare/autocua-vs-steel.md)\n- [AutoCua vs TinyFish](https://www.anchorterminal.com/compare/autocua-vs-tinyfish.md)\n- [Browser Use vs Browserbase](https://www.anchorterminal.com/compare/browser-use-vs-browserbase.md)\n- [Browser Use vs Browserless](https://www.anchorterminal.com/compare/browser-use-vs-browserless.md)\n- [Browser Use vs BxPlaywright](https://www.anchorterminal.com/compare/browser-use-vs-bx-playwright.md)\n- [Browser Use vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/browser-use-vs-chrome-devtools-mcp.md)\n- [Browser Use vs Functionize MCP server](https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp.md)\n- [Browser Use vs Hyperbrowser](https://www.anchorterminal.com/compare/browser-use-vs-hyperbrowser.md)\n- [Browser Use vs Kane CLI](https://www.anchorterminal.com/compare/browser-use-vs-kane-cli.md)\n- [Browser Use vs Lightpanda](https://www.anchorterminal.com/compare/browser-use-vs-lightpanda.md)\n- [Browser Use vs Notte](https://www.anchorterminal.com/compare/browser-use-vs-notte.md)\n- [Browser Use vs Playwright MCP](https://www.anchorterminal.com/compare/browser-use-vs-playwright-mcp.md)\n- [Browser Use vs Pomerado](https://www.anchorterminal.com/compare/browser-use-vs-pomerado.md)\n- [Browser Use vs Puppeteer](https://www.anchorterminal.com/compare/browser-use-vs-puppeteer.md)\n- [Browser Use vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/browser-use-vs-puppeteer-reference-server-archived.md)\n- [Browser Use vs Selenium](https://www.anchorterminal.com/compare/browser-use-vs-selenium.md)\n- [Browser Use vs Skyvern](https://www.anchorterminal.com/compare/browser-use-vs-skyvern.md)\n- [Browser Use vs Steel](https://www.anchorterminal.com/compare/browser-use-vs-steel.md)\n- [Browser Use vs TinyFish](https://www.anchorterminal.com/compare/browser-use-vs-tinyfish.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-06", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "AutoCua vs Browser Use", "url": "" } ], "description": "Browser Use scores 80.3 (A) to AutoCua's 44.3 (E) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "AutoCua E 44.3", "Browser Use A 80.3", "scores" ], "h1": "AutoCua vs Browser Use", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/autocua-vs-browser-use", "published": "2026-10-01", "section": "tools", "title": "AutoCua vs Browser Use for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/autocua-vs-browser-use" }, "tokens": { "markdown": 5400, "slim": 3180 }, "version": 1 }