{ "data": { "a": { "slug": "anchor-browser", "name": "Anchor Browser", "vendor": "Anchor Forge Inc.", "vendorUrl": "https://anchorbrowser.io", "kind": "http-api", "category": "browser", "summary": "Anchor Browser runs cloud browser sessions for AI agents, controlled through a REST API, a CDP WebSocket, TypeScript and Python SDKs and hosted MCP servers. It adds managed logins with MFA, profiles, proxies, CAPTCHA solving and recordings.", "url": "https://www.anchorterminal.com/tools/anchor-browser", "markdownUrl": "https://www.anchorterminal.com/tools/anchor-browser.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/anchor-browser.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/anchor-browser.json", "dns": "anchor-browser.grade.anchorterminal.com", "repo": "https://github.com/anchorbrowser/AnchorBrowser-SDK-Typescript", "license": "Proprietary cloud service. No service agreement was found, only a website terms of use. The TypeScript and Python SDKs and the self-hosted MCP server are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.anchorbrowser.io", "packages": [ { "registry": "npm", "name": "anchorbrowser" }, { "registry": "pypi", "name": "anchorbrowser" } ], "auth": "mixed", "authNotes": "API key in the `anchor-api-key` header, created in the dashboard at app.anchorbrowser.io or issued by Agent Access, an unauthenticated puzzle flow that needs no account. The hosted MCP servers also accept OAuth sign-in through signin.anchorbrowser.io, with `mcp:tools` and `mcp:admin` scopes in the resource metadata. CDP connections pass the key as the `apiKey` query parameter on `wss://connect.anchorbrowser.io`. No key scopes, expiry or rotation guidance were found. Teams that enforce Agent Access identity also send `anchor-identity-token`.", "pricing": "freemium", "pricingNotes": "The Free plan has $5 of credits a month. Usage is $0.01 a browser created, $0.05 a browser-hour counted to the minute, $8 a GB through Anchor's proxy and $0.20 a GB otherwise. AI steps cost $0.01, $0.05 or $0.10 by model tier from 21 August 2026. Automation Task runs cost 0.1 credits ($0.10) each, or the infrastructure cost if higher, and failed runs pay no task fee. Starter is $50 a month and Growth $2,000, with overage at $1 a credit. Enterprise is priced through sales. Agent Access, which gave an agent 1 credit with no account, answered \"Agent Access is disabled\" on 1 November (https://docs.anchorbrowser.io/pricing, checked 2026-11-01).", "priceSummary": "$0.01 / call", "where": "hosted", "x402": { "level": "no", "evidence": "A blog post dated 29 August 2025 shows x402 payment on POST https://api.anchorbrowser.io/v1/sessions and says it is enabled per project. Unpaid POSTs on 2026-10-08 and 2026-11-01 returned 401 with no payment terms, and the docs and OpenAPI document describe `x402` only as a session option that lets the browser pay other sites through Amazon Bedrock AgentCore Payments.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 43004, "pypiWeekly": 10135, "asOf": "2026-10-08" }, "docsUrl": "https://docs.anchorbrowser.io", "llmsTxt": "https://docs.anchorbrowser.io/llms.txt", "openapi": "https://docs.anchorbrowser.io/openapi.yaml", "capabilities": [ "browser.control", "browser.hosted", "browser.debug", "web.fetch", "web.scrape", "scraping.proxies", "scraping.anti-bot", "pdf.generate" ], "tags": [ "official", "hosted", "freemium", "no-card", "openapi", "llms-txt", "mcp", "oauth", "python", "typescript", "proxies", "status-page", "soc2" ], "lastRelease": "2026-07-28", "graded": true, "anchor": { "graded": true, "score": 60.1, "grade": "C", "agentReady": false, "rank": 599, "ranked": true, "rankOf": 1354, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 57, "payments": 30, "reliability": 77, "schema": 80, "security": 54, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "1 November 2026. Agent Access answers 404 \"Agent Access is disabled\" on both `GET /v1/agent-access` and `GET /v1/agent-access/challenge`, for every caller. Its quickstart page now says it is \"temporarily unavailable\" and issues no keys, with no date, while the for-agents page (\"issues one without a dashboard account\"), llms.txt, llms-full.txt and the OpenAPI paths still present it as the way to get a key. An endpoint withdrawn while still advertised, at the low end of the range since the vendor calls the pause temporary (-3). https://docs.anchorbrowser.io/for-agents.md" ], "verdict": "The API has a public OpenAPI 3.1 document, per-unit prices and documented retry behaviour on session creation. No service agreement is published, only a website terms of use, the documented CDP connection puts the API key in the URL, and Agent Access, still advertised as keyless onboarding, answered as disabled on 1 November.", "bestFor": "Agents that must work inside signed-in accounts, with managed identities, MFA handling and a human sign-in link, and agents that need to start with no human signup.", "strengths": [ "OpenAPI 3.1 document with 101 paths and 136 operations, llms.txt, llms-full.txt and a Markdown twin of every docs page", "Per-unit prices published without login, $0.01 a browser, $0.05 a browser-hour, $8 a GB of proxy traffic and $0.10 an Automation Task run", "429s on session creation carry `Retry-After` and come before a session exists, and the docs say which statuses are safe to retry", "Hosted MCP servers at api.anchorbrowser.io/v1/mcp accept OAuth sign-in or the API key header, with read and write endpoint calls as separate tools", "Managed identities sign in and handle MFA without returning credentials to the agent, and secrets can be limited to matching domains, per the docs" ], "weaknesses": [ "No service agreement or API terms found. anchorbrowser.io/terms is a website terms of use dated 16 March 2025", "The documented CDP connection passes the API key as `apiKey` in the `wss://connect.anchorbrowser.io` URL", "Agent Access, documented as keyless onboarding, answered \"Agent Access is disabled\" on 1 November 2026, so a key needs a dashboard account", "No changelog, deprecation policy or published SLA found, and docs.anchorbrowser.io/changelog returns 404", "No SDK release or commit since 28 July 2026, and the status page has two components with no incident ever posted" ], "agentNotes": [ "Send the key in the `anchor-api-key` header. For CDP, build `wss://connect.anchorbrowser.io?apiKey=\u003ckey\u003e\u0026sessionId=\u003cid\u003e` and keep that URL out of logs", "Ask the operator for a key from app.anchorbrowser.io. Agent Access answered \"Agent Access is disabled\" on 1 November 2026", "Session creation is capped at 5 a minute on Free, 25 on Starter and 100 on Growth. On 429, wait for the `Retry-After` seconds. Before retrying a 5xx or 409, list sessions, since a retry can create a second one", "Set `session.timeout.idle_timeout` and `max_duration` and end sessions with DELETE. The default maximum is 180 minutes, and browser time bills by the minute", "Connect the `Anchor` MCP server or `Anchor (all)`, not both, because the docs say the pair duplicates tool names" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.1 } ], "editorialScores": { "ergonomics": 73, "maintenance": 57, "payments": 30, "reliability": 77, "schema": 80, "security": 54, "transparency": 40 }, "provenanceScore": 66, "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": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install anchorbrowser", "http": "curl -X POST https://api.anchorbrowser.io/v1/tools/perform-web-task -H \"anchor-api-key: YOUR_API_KEY\" -H \"Content-Type: application/json\" -d '{\"prompt\":\"Go to example.com and return the page title\",\"url\":\"https://example.com\"}'", "claudeCode": "claude mcp add --transport http anchor https://api.anchorbrowser.io/v1/mcp", "config": { "mcpServers": { "anchor": { "headers": { "anchor-api-key": "YOUR_ANCHOR_API_KEY" }, "url": "https://api.anchorbrowser.io/v1/mcp" } } } }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/anchor-browser" }, "area": "developer", "unitPrices": [ { "item": "Browser creation", "unit": "call", "usd": 0.01, "note": "Per browser instance created" }, { "item": "Browser usage", "unit": "browser-hour", "usd": 0.05, "note": "Counted to the nearest full minute" }, { "item": "Anchor proxy traffic", "unit": "gb", "usd": 8 }, { "item": "Egress with your own proxy or none", "unit": "gb", "usd": 0.2 }, { "item": "AI step, Light model tier", "unit": "call", "usd": 0.01, "note": "Also the flat rate with your own model key" }, { "item": "AI step, Standard model tier", "unit": "call", "usd": 0.05 }, { "item": "AI step, High Performance model tier", "unit": "call", "usd": 0.1 }, { "item": "Automation Task run", "unit": "call", "usd": 0.1, "note": "0.1 credits a run, or the session's infrastructure cost if higher. Failed runs pay no task fee" }, { "item": "Overage credit, Starter and Growth", "unit": "credit", "usd": 1 }, { "item": "Starter plan", "unit": "month", "usd": 50 }, { "item": "Growth plan", "unit": "month", "usd": 2000 } ], "provenance": { "legalEntity": "Anchor Forge Inc.", "domain": "anchorbrowser.io", "domainRegistered": "2024-09-18", "endpointOnVendorDomain": true, "terms": "", "privacy": "https://anchorbrowser.io/privacy-policy", "statusPage": "https://status.anchorbrowser.io", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The website terms of use (last updated 16 March 2025) and the privacy policy (last updated 24 February 2026) name Anchor Forge Inc. and its affiliates. The terms choose New York law.", "No terms URL is recorded. anchorbrowser.io/terms is a website terms of use that grants personal, non-commercial use of the site, and no service agreement or API terms were found.", "The privacy policy is written for the website and customer contacts and has one product section, on Gmail access for sign-in codes. A DPA is listed in the trust portal behind an access request.", "The API and MCP servers answer at api.anchorbrowser.io, CDP at connect.anchorbrowser.io and OAuth sign-in at signin.anchorbrowser.io.", "anchorbrowser.io/.well-known/security.txt and docs.anchorbrowser.io/.well-known/security.txt both return 404. The trust portal at trust.anchorbrowser.io runs on SafeBase.", "RDAP for anchorbrowser.io gives a registration date of 2024-09-18.", "docs.anchorbrowser.io/changelog returns 404 and no API changelog was found." ], "score": 66 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/anchor-browser.json", "live": { "slug": "anchor-browser", "probe": { "target": "https://api.anchorbrowser.io", "method": "get", "lastAt": "2026-11-06T09:47:18.208351941Z", "lastOk": true, "lastStatus": 404, "lastMs": 395, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 391, "p95ms24h": 499, "samples24h": 221, "samples30d": 7114, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "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.anchorbrowser.io", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-06T09:42:34.840499645Z" }, "versions": [ { "registry": "github", "name": "anchorbrowser/AnchorBrowser-SDK-Typescript", "version": "v0.16.3", "released": "2026-03-19", "seenAt": "2026-11-05T21:12:22.062254213Z" }, { "registry": "npm", "name": "anchorbrowser", "version": "1.0.0", "seenAt": "2026-11-05T21:12:20.954101007Z" }, { "registry": "pypi", "name": "anchorbrowser", "version": "1.0.1", "released": "2026-07-28", "seenAt": "2026-11-05T21:12:21.834818495Z" } ], "githubStars": 5, "npmWeekly": 30679, "pypiWeekly": 12824, "securityTxt": { "url": "https://anchorbrowser.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-05T15:56:05.253107984Z" }, "llmsTxt": { "url": "https://docs.anchorbrowser.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:25:10.832934381Z" }, "domain": { "domain": "anchorbrowser.io", "checkedAt": "2026-11-01T14:12:30.70276996Z" }, "pages": [ { "url": "https://docs.anchorbrowser.io/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-11-05T12:51:21.839546136Z", "changedAt": "2026-10-29T05:03:21.383241613Z", "fingerprint": "719a857cd0b2" }, { "url": "https://anchorbrowser.io/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-05T12:46:09.965599296Z", "changedAt": "2026-10-26T03:09:12.167781207Z", "fingerprint": "6c92322677c5" } ], "github": { "repo": "anchorbrowser/anchorbrowser-sdk-typescript", "checkedAt": "2026-11-02T08:30:33.082695474Z", "stars": 5, "archived": false, "issuesEnabled": true, "pushedAt": "2026-09-29T10:28:59Z", "openIssues": 0, "openPRs": 1, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 0, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-07-28T15:37:45Z" }, "replies": { "sampled": 4, "unanswered": 0, "medianDays": 50.2 } }, "updatedAt": "2026-11-06T09:47:18.208351941Z" } }, "answer": "Anchor Browser scores 60.1 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 5 of 7 scored categories. AutoCua leads on payments \u0026 pricing and maintenance \u0026 community.", "b": { "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" }, "edges": [ { "by": 52, "category": "reliability", "leads": "anchor-browser", "name": "Reliability", "reasons": { "a": "Graded as a hosted service. status.anchorbrowser.io runs on incident.io with two components, Website and Anchor Application (20). Both show operational on 1 November, and the RSS feed is still empty. The page has recorded no incident since it was set up in June 2025. This run reads a readable page that has never posted an incident as a clean record at 20, as for quicken-simplifi, outline and linkup, where the 8 October check gave 25, a value the checklist doesn't name (20). Limits are published, 5, 25 and 100 session creations a minute and 5, 25 and 200 concurrent browsers by plan, and 2,000 requests a minute on Web Unlocker (15). The OpenAPI document declares 429 on ten operations, with `RateLimit` and `Retry-After` headers on session creation, and the Web Unlocker docs say to retry 429, 500, 503 and 504 with exponential backoff. The sessions guide now says a 429 from the per-minute limiter comes before a session exists, so retrying it doesn't create a second one, that the API reads no `Idempotency-Key`, so retrying a 5xx or 409 can, and which statuses are terminal. Safe-retry guidance without idempotency keys, read as e2b's (12). No SLA was found on the pricing page, the docs or the site (0). The API is version 1.0.0, the SDKs are 1.0 and nothing marks the sessions API as beta (10). 20 + 20 + 15 + 12 + 0 + 10 = 77.", "b": "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." }, "scores": { "a": 77, "b": 25 } }, { "by": 38, "category": "schema", "leads": "anchor-browser", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI 3.1.0 at docs.anchorbrowser.io/openapi.yaml with 101 paths and 136 operations, unchanged on 1 November, and the `anchor-api-key` header scheme (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). All 136 operations carry a description, the spec's introduction says which resource suits which job, and a docs page compares the task types. Few descriptions say when not to use an endpoint (16). Inputs are typed with 90 enum declarations and named request schemas. We did not audit every field for bounds (11). The spec holds 121 examples and declares 400, 401, 404 and 500 widely, with one shared error schema of `code` and `message` (12). Paths are versioned under /v1 and a legacy spec is kept. No API changelog was found, docs.anchorbrowser.io/changelog still returns 404 on 1 November, and the SDK changelog stops at 1.0.0-dev.4 (6). 25 + 10 + 16 + 11 + 12 + 6 = 80.", "b": "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." }, "scores": { "a": 80, "b": 42 } }, { "by": 30, "category": "payments", "leads": "autocua", "name": "Payments \u0026 pricing", "reasons": { "a": "No machine payment protocol was confirmed on Anchor's own endpoints. A blog post dated 29 August 2025 shows x402 on `POST /v1/sessions`, but our unpaid request on 1 November 2026 returned 401 \"Unauthorized, please log in.\", as on 8 October, and the docs don't describe it. The session option named `x402` lets a browser pay other sites (0). Per-browser, per-hour, per-GB, per-step and, now, per-run prices for Automation Tasks (0.1 credits, $0.10, with failed runs not charged the task fee) are published without login (20). The Free plan has $5 of credits a month. Agent Access, which granted 1 credit with no account and no card, answered \"Agent Access is disabled\" on 1 November, and whether dashboard sign-up asks for a card wasn't read, so half, as smartsheet's unconfirmed trial (10). With Agent Access disabled, a key comes from a dashboard account at app.anchorbrowser.io, which a person creates in a browser (0). 0 + 20 + 10 + 0 = 30.", "b": "Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60." }, "scores": { "a": 30, "b": 60 } }, { "by": 18, "category": "ergonomics", "leads": "anchor-browser", "name": "Agent ergonomics", "reasons": { "a": "The main MCP server lists about 24 tools and reaches the other REST routes through `list_endpoints`, `get_endpoint` and two call tools. Browser control and per-site actions are separate servers, and the docs warn that `/v1/mcp/actions` without a domain lists thousands of tools. 15 for the tool count plus 5 for the split servers (20). Session lists take `page`, `limit`, sort, search and filters by status, tag, domain and date, volumes use a cursor, and webhook deliveries take `limit` and `offset` (17). Errors return an integer code and a message, 402 marks exhausted credits, and Agent Access errors name the next call. No stable machine-readable error codes were found (13). No idempotency keys. The MCP server splits `call_endpoint_read` from `call_endpoint_write`, and batch sessions have a retry-failed call. Tool annotations were not read because the server needs a key (8). A session starts from an empty body, and the SDKs cover TypeScript and Python (15). 20 + 17 + 13 + 8 + 15 = 73.", "b": "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." }, "scores": { "a": 73, "b": 55 } }, { "by": 16, "category": "security", "leads": "anchor-browser", "name": "Security \u0026 auth", "reasons": { "a": "API keys in the `anchor-api-key` header, per project. The MCP servers also accept OAuth through signin.anchorbrowser.io with `mcp:tools` and `mcp:admin` scopes. No key scopes, expiry or rotation guidance were found in the docs (22). The documented CDP connection passes the key as `apiKey` in the `wss://connect.anchorbrowser.io` URL, a secret in a query string (minus 10). No read-only API key. Live view has a read-only mode, volumes mount read-only, secrets can be limited to matching domains, identities sign in without returning credentials, and tasks can pause for a person's input (13). No prompt-injection guidance was found in the docs. Secret values and sensitive data masking keep credentials out of the model's view, which is a partial mitigation (4). Recordings, session history, webhook delivery logs and a billing endpoint give the operator a trail. The audit logs on the security page are restricted to Anchor's staff (11). SOC 2 Type 2, ISO 27001 and HIPAA per the security page and trust portal, with reports behind an access request, and a disclosure contact in the SDK's SECURITY.md. No security.txt (404 again on 1 November) or bug bounty was found (14). The documented CDP URL still carries `apiKey` on 1 November. 22 - 10 + 13 + 4 + 11 + 14 = 54.", "b": "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." }, "scores": { "a": 54, "b": 38 } }, { "by": 11, "category": "transparency", "leads": "anchor-browser", "name": "Transparency \u0026 trust", "reasons": { "a": "The service is closed. The SDKs and the self-hosted MCP server are Apache-2.0. The only terms published are a website terms of use dated 16 March 2025, which grants personal, non-commercial use of the site and does not cover the API, so the terms for the paid service are unclear (8). The security page says session data is not stored and each browser's virtual machine is destroyed, the pricing page gives 7 days of data retention, recordings are on by default, and Zero Data Retention is by request. The privacy policy (24 February 2026) covers the website and customer contacts, with one product section on Gmail access. The DPA and data handling policy sit behind an access request (15). The legacy tasks API and the old MCP address are labelled and still work, and the SDK has a migration guide. No deprecation policy or dates (5). The security page names AWS us-east-2 and eu-central-1. The trust portal has a subprocessor section, of which our reader saw only OpenAI and Anthropic (12). Terms and privacy policy dates unchanged on 1 November. 8 + 15 + 5 + 12 = 40.", "b": "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." }, "scores": { "a": 53, "b": 42 } } ], "facts": [ { "a": "HTTP API", "b": "Agent framework", "name": "Kind" }, { "a": "Anchor Forge Inc.", "b": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)", "name": "Vendor" }, { "a": "https://api.anchorbrowser.io", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary cloud service. No service agreement was found, only a website terms of use. The TypeScript and Python SDKs and the self-hosted MCP server are Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-07-28", "b": "2026-11-04", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-02-24", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "43k npm/wk, 10k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Anchor Browser scores 60.1 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 5 of 7 scored categories. AutoCua leads on payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Anchor Browser or AutoCua?" }, { "answer": "Anchor Browser has a hosted endpoint at https://api.anchorbrowser.io. No hosted endpoint is listed for AutoCua.", "question": "Can an agent call Anchor Browser and AutoCua without installing anything?" }, { "answer": "No open-source release is listed for Anchor Browser. AutoCua is open source (MIT).", "question": "Are Anchor Browser and AutoCua open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 77 against 25", "Schema \u0026 documentation, 80 against 42", "Agent ergonomics, 73 against 55", "Security \u0026 auth, 54 against 38", "Transparency \u0026 trust, 53 against 42" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Agents that must work inside signed-in accounts, with managed identities, MFA handling and a human sign-in link, and agents that need to start with no human signup.", "slug": "anchor-browser", "watchFor": "No service agreement or API terms found. anchorbrowser.io/terms is a website terms of use dated 16 March 2025" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 30", "Maintenance \u0026 community, 65 against 57" ], "also": [ "No key needed to call it", "Open source", "No incidents deducted, where Anchor Browser loses 3 points for them" ], "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" } ], "history": { "anchor-browser": [ { "causes": [ "product", "correction", "event" ], "date": "2026-11-01", "delta": -7.3, "from": 67.4, "fromGrade": "B", "to": 60.1, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 67.3, "fromGrade": "B", "to": 67.4, "toGrade": "B" } ], "autocua": null }, "job": { "capability": "browser.control", "name": "Browser automation" }, "others": [ { "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-autocua.json", "title": "agent-browser vs AutoCua", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-autocua" }, { "json": "https://www.anchorterminal.com/compare/airtop-vs-anchor-browser.json", "title": "Airtop vs Anchor Browser", "url": "https://www.anchorterminal.com/compare/airtop-vs-anchor-browser" }, { "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/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/anchor-browser-vs-browserbase.json", "title": "Anchor Browser vs Browserbase", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-browserbase" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-browserless.json", "title": "Anchor Browser vs Browserless", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-bx-playwright.json", "title": "Anchor Browser vs BxPlaywright", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-bx-playwright" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-chrome-devtools-mcp.json", "title": "Anchor Browser vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp.json", "title": "Anchor Browser vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-hyperbrowser.json", "title": "Anchor Browser vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-kane-cli.json", "title": "Anchor Browser vs Kane CLI", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-kane-cli" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-lightpanda.json", "title": "Anchor Browser vs Lightpanda", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-lightpanda" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-notte.json", "title": "Anchor Browser vs Notte", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-playwright-mcp.json", "title": "Anchor Browser vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-pomerado.json", "title": "Anchor Browser vs Pomerado", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-pomerado" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer.json", "title": "Anchor Browser vs Puppeteer", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer-reference-server-archived.json", "title": "Anchor Browser vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer-reference-server-archived" }, { "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/anchor-browser-vs-skyvern.json", "title": "Anchor Browser vs Skyvern", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-steel.json", "title": "Anchor Browser vs Steel", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-tinyfish.json", "title": "Anchor Browser vs TinyFish", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-browser-use.json", "title": "AutoCua vs Browser Use", "url": "https://www.anchorterminal.com/compare/autocua-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" } ], "panel": null, "scores": [ { "anchor-browser": 77, "autocua": 25, "by": 52, "edge": "anchor-browser", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "anchor-browser": 80, "autocua": 42, "by": 38, "edge": "anchor-browser", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "anchor-browser": 73, "autocua": 55, "by": 18, "edge": "anchor-browser", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "anchor-browser": 54, "autocua": 38, "by": 16, "edge": "anchor-browser", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "anchor-browser": 30, "autocua": 60, "by": 30, "edge": "autocua", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "anchor-browser": 57, "autocua": 65, "by": 8, "edge": "autocua", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "anchor-browser": 53, "autocua": 42, "by": 11, "edge": "anchor-browser", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Anchor Browser scores 60.1 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 5 of 7 scored categories. AutoCua leads on payments \u0026 pricing and maintenance \u0026 community. Both do browser automation.", "tasks": null, "tutorials": [], "verdicts": { "anchor-browser": "The API has a public OpenAPI 3.1 document, per-unit prices and documented retry behaviour on session creation. No service agreement is published, only a website terms of use, the documented CDP connection puts the API key in the URL, and Agent Access, still advertised as keyless onboarding, answered as disabled on 1 November.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua", "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.min.md" }, "markdown": "Anchor Browser scores 60.1 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 5 of 7 scored categories. AutoCua leads on payments \u0026 pricing and maintenance \u0026 community. Both do browser automation.\n\n- Anchor Browser: grade C, 60.1/100, rank #599 of 1354. Markdown https://www.anchorterminal.com/tools/anchor-browser.md · JSON https://www.anchorterminal.com/api/v1/tools/anchor-browser.json\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- 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- 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\n## Which one, for what\n\n### Anchor Browser (C)\n\nGood for: Agents that must work inside signed-in accounts, with managed identities, MFA handling and a human sign-in link, and agents that need to start with no human signup.\n\nAhead on:\n- Reliability, 77 against 25\n- Schema \u0026 documentation, 80 against 42\n- Agent ergonomics, 73 against 55\n- Security \u0026 auth, 54 against 38\n- Transparency \u0026 trust, 53 against 42\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: No service agreement or API terms found. anchorbrowser.io/terms is a website terms of use dated 16 March 2025\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\nAhead on:\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 65 against 57\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n- No incidents deducted, where Anchor Browser loses 3 points for them\n\nWatch for: Two weeks old at version 0.1.9, with no changelog file\n\n\n## Why the edge\n\n### Reliability: Anchor Browser +52\n\n- Anchor Browser (77): Graded as a hosted service. status.anchorbrowser.io runs on incident.io with two components, Website and Anchor Application (20). Both show operational on 1 November, and the RSS feed is still empty. The page has recorded no incident since it was set up in June 2025. This run reads a readable page that has never posted an incident as a clean record at 20, as for quicken-simplifi, outline and linkup, where the 8 October check gave 25, a value the checklist doesn't name (20). Limits are published, 5, 25 and 100 session creations a minute and 5, 25 and 200 concurrent browsers by plan, and 2,000 requests a minute on Web Unlocker (15). The OpenAPI document declares 429 on ten operations, with `RateLimit` and `Retry-After` headers on session creation, and the Web Unlocker docs say to retry 429, 500, 503 and 504 with exponential backoff. The sessions guide now says a 429 from the per-minute limiter comes before a session exists, so retrying it doesn't create a second one, that the API reads no `Idempotency-Key`, so retrying a 5xx or 409 can, and which statuses are terminal. Safe-retry guidance without idempotency keys, read as e2b's (12). No SLA was found on the pricing page, the docs or the site (0). The API is version 1.0.0, the SDKs are 1.0 and nothing marks the sessions API as beta (10). 20 + 20 + 15 + 12 + 0 + 10 = 77.\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\n### Schema \u0026 documentation: Anchor Browser +38\n\n- Anchor Browser (80): OpenAPI 3.1.0 at docs.anchorbrowser.io/openapi.yaml with 101 paths and 136 operations, unchanged on 1 November, and the `anchor-api-key` header scheme (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). All 136 operations carry a description, the spec's introduction says which resource suits which job, and a docs page compares the task types. Few descriptions say when not to use an endpoint (16). Inputs are typed with 90 enum declarations and named request schemas. We did not audit every field for bounds (11). The spec holds 121 examples and declares 400, 401, 404 and 500 widely, with one shared error schema of `code` and `message` (12). Paths are versioned under /v1 and a legacy spec is kept. No API changelog was found, docs.anchorbrowser.io/changelog still returns 404 on 1 November, and the SDK changelog stops at 1.0.0-dev.4 (6). 25 + 10 + 16 + 11 + 12 + 6 = 80.\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\n### Payments \u0026 pricing: AutoCua +30\n\n- Anchor Browser (30): No machine payment protocol was confirmed on Anchor's own endpoints. A blog post dated 29 August 2025 shows x402 on `POST /v1/sessions`, but our unpaid request on 1 November 2026 returned 401 \"Unauthorized, please log in.\", as on 8 October, and the docs don't describe it. The session option named `x402` lets a browser pay other sites (0). Per-browser, per-hour, per-GB, per-step and, now, per-run prices for Automation Tasks (0.1 credits, $0.10, with failed runs not charged the task fee) are published without login (20). The Free plan has $5 of credits a month. Agent Access, which granted 1 credit with no account and no card, answered \"Agent Access is disabled\" on 1 November, and whether dashboard sign-up asks for a card wasn't read, so half, as smartsheet's unconfirmed trial (10). With Agent Access disabled, a key comes from a dashboard account at app.anchorbrowser.io, which a person creates in a browser (0). 0 + 20 + 10 + 0 = 30.\n- AutoCua (60): Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.\n\n### Agent ergonomics: Anchor Browser +18\n\n- Anchor Browser (73): The main MCP server lists about 24 tools and reaches the other REST routes through `list_endpoints`, `get_endpoint` and two call tools. Browser control and per-site actions are separate servers, and the docs warn that `/v1/mcp/actions` without a domain lists thousands of tools. 15 for the tool count plus 5 for the split servers (20). Session lists take `page`, `limit`, sort, search and filters by status, tag, domain and date, volumes use a cursor, and webhook deliveries take `limit` and `offset` (17). Errors return an integer code and a message, 402 marks exhausted credits, and Agent Access errors name the next call. No stable machine-readable error codes were found (13). No idempotency keys. The MCP server splits `call_endpoint_read` from `call_endpoint_write`, and batch sessions have a retry-failed call. Tool annotations were not read because the server needs a key (8). A session starts from an empty body, and the SDKs cover TypeScript and Python (15). 20 + 17 + 13 + 8 + 15 = 73.\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\n### Security \u0026 auth: Anchor Browser +16\n\n- Anchor Browser (54): API keys in the `anchor-api-key` header, per project. The MCP servers also accept OAuth through signin.anchorbrowser.io with `mcp:tools` and `mcp:admin` scopes. No key scopes, expiry or rotation guidance were found in the docs (22). The documented CDP connection passes the key as `apiKey` in the `wss://connect.anchorbrowser.io` URL, a secret in a query string (minus 10). No read-only API key. Live view has a read-only mode, volumes mount read-only, secrets can be limited to matching domains, identities sign in without returning credentials, and tasks can pause for a person's input (13). No prompt-injection guidance was found in the docs. Secret values and sensitive data masking keep credentials out of the model's view, which is a partial mitigation (4). Recordings, session history, webhook delivery logs and a billing endpoint give the operator a trail. The audit logs on the security page are restricted to Anchor's staff (11). SOC 2 Type 2, ISO 27001 and HIPAA per the security page and trust portal, with reports behind an access request, and a disclosure contact in the SDK's SECURITY.md. No security.txt (404 again on 1 November) or bug bounty was found (14). The documented CDP URL still carries `apiKey` on 1 November. 22 - 10 + 13 + 4 + 11 + 14 = 54.\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\n### Transparency \u0026 trust: Anchor Browser +11\n\n- Anchor Browser (53): The service is closed. The SDKs and the self-hosted MCP server are Apache-2.0. The only terms published are a website terms of use dated 16 March 2025, which grants personal, non-commercial use of the site and does not cover the API, so the terms for the paid service are unclear (8). The security page says session data is not stored and each browser's virtual machine is destroyed, the pricing page gives 7 days of data retention, recordings are on by default, and Zero Data Retention is by request. The privacy policy (24 February 2026) covers the website and customer contacts, with one product section on Gmail access. The DPA and data handling policy sit behind an access request (15). The legacy tasks API and the old MCP address are labelled and still work, and the SDK has a migration guide. No deprecation policy or dates (5). The security page names AWS us-east-2 and eu-central-1. The trust portal has a subprocessor section, of which our reader saw only OpenAI and Anthropic (12). Terms and privacy policy dates unchanged on 1 November. 8 + 15 + 5 + 12 = 40.\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\n## Score by category\n\n| Category | Weight | Anchor Browser | AutoCua | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 77 | 25 | Anchor Browser +52 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 42 | Anchor Browser +38 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 55 | Anchor Browser +18 |\n| Security \u0026 auth | 14% (17.5 this run) | 54 | 38 | Anchor Browser +16 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | AutoCua +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 57 | 65 | AutoCua +8 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 42 | Anchor Browser +11 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **60.1 · C** | **44.3 · E** | |\n\n## Facts side by side\n\n| Fact | Anchor Browser | AutoCua |\n| --- | --- | --- |\n| Kind | HTTP API | Agent framework |\n| Vendor | Anchor Forge Inc. | Ashish Yadav and contributors (ComputerUseAgent on GitHub) |\n| Hosted endpoint | `https://api.anchorbrowser.io` | no (local only) |\n| Transports | HTTP | |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Proprietary cloud service. No service agreement was found, only a website terms of use. The TypeScript and Python SDKs and the self-hosted MCP server are Apache-2.0 | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-07-28 | 2026-11-04 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | 2026-02-24 | no document linked |\n| Popularity | 43k npm/wk, 10k PyPI/wk | none |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### Anchor Browser\n\n- -7.3 on 1 November 2026 (B to C): product, correction, negative event\n- +0.1 on 27 October 2026: checklist\n\n### AutoCua\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Anchor Browser.** The API has a public OpenAPI 3.1 document, per-unit prices and documented retry behaviour on session creation. No service agreement is published, only a website terms of use, the documented CDP connection puts the API key in the URL, and Agent Access, still advertised as keyless onboarding, answered as disabled on 1 November.\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## Before you call either\n\n### Anchor Browser\n\n1. Send the key in the `anchor-api-key` header. For CDP, build `wss://connect.anchorbrowser.io?apiKey=\u003ckey\u003e\u0026sessionId=\u003cid\u003e` and keep that URL out of logs\n2. Ask the operator for a key from app.anchorbrowser.io. Agent Access answered \"Agent Access is disabled\" on 1 November 2026\n3. Session creation is capped at 5 a minute on Free, 25 on Starter and 100 on Growth. On 429, wait for the `Retry-After` seconds. Before retrying a 5xx or 409, list sessions, since a retry can create a second one\n4. Set `session.timeout.idle_timeout` and `max_duration` and end sessions with DELETE. The default maximum is 180 minutes, and browser time bills by the minute\n5. Connect the `Anchor` MCP server or `Anchor (all)`, not both, because the docs say the pair duplicates tool names\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## Questions\n\n### Which is better for AI agents, Anchor Browser or AutoCua?\n\nAnchor Browser scores 60.1 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 5 of 7 scored categories. AutoCua leads on payments \u0026 pricing and maintenance \u0026 community.\n\n### Can an agent call Anchor Browser and AutoCua without installing anything?\n\nAnchor Browser has a hosted endpoint at https://api.anchorbrowser.io. No hosted endpoint is listed for AutoCua.\n\n### Are Anchor Browser and AutoCua open source?\n\nNo open-source release is listed for Anchor Browser. AutoCua is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.json, and with the fewest tokens: https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"anchor-browser\", \"b\": \"autocua\"}`. From a terminal: `anchor compare anchor-browser autocua`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/anchor-browser.json and https://www.anchorterminal.com/api/v1/tools/autocua.json\n\n## Other comparisons with Anchor Browser or AutoCua\n\n- [agent-browser vs Anchor Browser](https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.md)\n- [agent-browser vs AutoCua](https://www.anchorterminal.com/compare/agent-browser-vs-autocua.md)\n- [Airtop vs Anchor Browser](https://www.anchorterminal.com/compare/airtop-vs-anchor-browser.md)\n- [Airtop vs AutoCua](https://www.anchorterminal.com/compare/airtop-vs-autocua.md)\n- [Anchor Browser vs Browser Use](https://www.anchorterminal.com/compare/anchor-browser-vs-browser-use.md)\n- [Anchor Browser vs Browserbase](https://www.anchorterminal.com/compare/anchor-browser-vs-browserbase.md)\n- [Anchor Browser vs Browserless](https://www.anchorterminal.com/compare/anchor-browser-vs-browserless.md)\n- [Anchor Browser vs BxPlaywright](https://www.anchorterminal.com/compare/anchor-browser-vs-bx-playwright.md)\n- [Anchor Browser vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/anchor-browser-vs-chrome-devtools-mcp.md)\n- [Anchor Browser vs Functionize MCP server](https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp.md)\n- [Anchor Browser vs Hyperbrowser](https://www.anchorterminal.com/compare/anchor-browser-vs-hyperbrowser.md)\n- [Anchor Browser vs Kane CLI](https://www.anchorterminal.com/compare/anchor-browser-vs-kane-cli.md)\n- [Anchor Browser vs Lightpanda](https://www.anchorterminal.com/compare/anchor-browser-vs-lightpanda.md)\n- [Anchor Browser vs Notte](https://www.anchorterminal.com/compare/anchor-browser-vs-notte.md)\n- [Anchor Browser vs Playwright MCP](https://www.anchorterminal.com/compare/anchor-browser-vs-playwright-mcp.md)\n- [Anchor Browser vs Pomerado](https://www.anchorterminal.com/compare/anchor-browser-vs-pomerado.md)\n- [Anchor Browser vs Puppeteer](https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer.md)\n- [Anchor Browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer-reference-server-archived.md)\n- [Anchor Browser vs Selenium](https://www.anchorterminal.com/compare/anchor-browser-vs-selenium.md)\n- [Anchor Browser vs Skyvern](https://www.anchorterminal.com/compare/anchor-browser-vs-skyvern.md)\n- [Anchor Browser vs Steel](https://www.anchorterminal.com/compare/anchor-browser-vs-steel.md)\n- [Anchor Browser vs TinyFish](https://www.anchorterminal.com/compare/anchor-browser-vs-tinyfish.md)\n- [AutoCua vs Browser Use](https://www.anchorterminal.com/compare/autocua-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", "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": "Anchor Browser vs AutoCua", "url": "" } ], "description": "Anchor Browser scores 60.1 (C) to AutoCua's 44.3 (E) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Anchor Browser C 60.1", "AutoCua E 44.3", "scores" ], "h1": "Anchor Browser vs AutoCua", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/anchor-browser-vs-autocua", "published": "2026-10-01", "section": "tools", "title": "Anchor Browser vs AutoCua for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua" }, "tokens": { "markdown": 5300, "slim": 2980 }, "version": 1 }