{ "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": "Skyvern scores 57.5 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories. AutoCua leads on payments \u0026 pricing.", "b": { "slug": "skyvern", "name": "Skyvern", "vendor": "Ikonomos Inc. (Skyvern)", "vendorUrl": "https://www.skyvern.com", "kind": "http-api", "category": "browser", "summary": "Skyvern is a browser agent that completes multi-step web workflows from natural-language goals using language models and computer vision. It runs as an AGPL-3.0 open-source server or a hosted cloud with a REST API and MCP server.", "url": "https://www.anchorterminal.com/tools/skyvern", "markdownUrl": "https://www.anchorterminal.com/tools/skyvern.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/skyvern.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/skyvern.json", "dns": "skyvern.grade.anchorterminal.com", "repo": "https://github.com/Skyvern-AI/skyvern", "license": "AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.skyvern.com/v1", "packages": [ { "registry": "pypi", "name": "skyvern" }, { "registry": "npm", "name": "@skyvern/client" } ], "auth": "mixed", "authNotes": "Self-serve. Sign up at app.skyvern.com and copy the organisation API key from Settings, sent as `x-api-key`. MCP clients can use OAuth 2.0 with browser sign-in, PKCE and dynamic client registration, with no client ID to configure. Both credentials carry full authority over the organisation. OAuth scopes are identity claims, and there are no read-only or per-endpoint keys (https://www.skyvern.com/docs/developers/api/authentication-and-permissions.md).", "pricing": "paid", "pricingNotes": "Every new account starts a 14-day trial with 30,000 credits and Hobby limits, and a card is added to start (nothing is charged before day 14). Hobby $29 a month with 30,000 credits and 10 concurrent runs. Pro $149 with 150,000 credits and 25 concurrent runs. Enterprise is custom. One credit is $0.001, an action costs 30 credits, a cached action 15, browser uptime 200 credits an hour and a one-time code read 10. Top-ups start at $10. The pricing page FAQ says runs are charged per workflow execution. Self-hosting the AGPL-3.0 server is free with your own model keys (https://www.skyvern.com/pricing, https://www.skyvern.com/docs/cloud/account.md, checked 2026-11-02).", "priceSummary": "$29 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs (llms-full.txt), llms.txt or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 118, "popularity": { "githubStars": 23155, "npmWeekly": 3193, "pypiWeekly": 1636, "asOf": "2026-10-08" }, "docsUrl": "https://www.skyvern.com/docs", "llmsTxt": "https://www.skyvern.com/docs/llms.txt", "openapi": "https://www.skyvern.com/docs/api-reference/openapi.json", "registryName": "io.github.Skyvern-AI/skyvern", "capabilities": [ "browser.control", "browser.hosted", "web.extract", "automation.workflows", "browser.debug" ], "tags": [ "official", "hosted", "open-source", "free-trial", "card-required", "mcp", "oauth", "openapi", "llms-txt", "python", "typescript", "status-page", "soc2" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 57.5, "grade": "C", "agentReady": false, "rank": 709, "ranked": true, "rankOf": 1354, "categoryRank": 15, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 85, "payments": 16, "reliability": 67, "schema": 88, "security": 59, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -9, "negativeNotes": [ "2026-06-30. Unadvised fixes, -3. A public issue reports non-blind SSRF from workflow `http_request` and file download blocks to loopback, private and metadata addresses in version 1.0.39, with a reproduction (https://github.com/Skyvern-AI/skyvern/issues/6915). It was open on 8 October 2026 with no advisory, and the released source routes these requests through an SSRF-guarded resolver. The week of 12 October changelog also fixed sensitive run values appearing in self-heal recovery details, again with no advisory, which folds into this term. OSV holds no advisory for either on 2 November (https://www.skyvern.com/docs/changelog.md).", "2026-10-18. Unreleased security fix, -3. Commit 2e02161d0, \"Keep credentials and request bodies off cross-origin redirects, and internal errors out of workflow-create responses\", changes how outbound HTTP requests follow a redirect to another origin. In v1.0.56 only the Authorization and Cookie headers are dropped, so other credential headers, cookies held in the session and request bodies still reach the new origin. The commit keeps only three non-credential headers, clears the session cookies and refuses a redirect that would replay a body. The newest release is v1.0.56 of 14 October, so the fix is in no release on 2 November (https://github.com/Skyvern-AI/skyvern).", "2026-10-19. Same-day behaviour change, -3. The week of 19 October changelog says the runs list API now defaults free-text search to the last 30 days, and the OpenAPI document says supplying `created_at_start` replaces that window. Existing callers of GET /v1/agents/runs with `search_key` get fewer results, with notice only in that week's entry (https://www.skyvern.com/docs/changelog.md)." ], "verdict": "The hosted MCP server annotates all 118 tools as read-only or destructive and can serve a 31 or 34-tool scope, and the API has a written six-month deprecation policy. Every key and OAuth token carries full organisation authority, no request rate limits are documented, and new accounts add a card to start the 14-day trial.", "bestFor": "Agents that must finish a multi-step job on sites with logins, 2FA and forms, where stored credentials, saved workflows and cached scripts matter more than raw browser time.", "strengths": [ "Every MCP tool carries readOnlyHint, destructiveHint and openWorldHint annotations, 118 registrations in the source on 2 November 2026", "Hosted MCP scopes cut the advertised tools from 118 to 31 (`operate`) or 34 (`lean`) by URL or `X-Skyvern-Scope` header", "Written deprecation policy with six months' notice, 12 for a major version, and `Deprecation` and `Sunset` response headers", "OpenAPI 3.1.0 with 106 operations, llms.txt, Markdown twins of every docs page and a weekly dated changelog", "Unit prices are published in the billing docs, one credit $0.001 and an action 30 credits" ], "weaknesses": [ "Every API key and OAuth token has full organisation authority. The docs state there are no read-only, per-endpoint or per-agent keys", "No request rate limits in the docs, only plan concurrency (10 or 25 runs)", "The free plan has gone. New accounts start a 14-day trial and add a card to start", "A fix keeping credentials off cross-origin redirects (18 October 2026) is in no release, and the SSRF report against 1.0.39 has no advisory", "Retention is \"as long as necessary\", and anonymised data may train models unless an enterprise agreement opts you out" ], "agentNotes": [ "Connect to https://api.skyvern.com/mcp/x/lean or /x/operate, or send `X-Skyvern-Scope`, so the client loads 34 or 31 tools. The scope filters the list and does not limit permissions", "Use a separate Skyvern organisation for each blast radius. Any key or OAuth token can read and write stored credentials and delete workflows", "Never pass passwords to `skyvern_act` or `skyvern_type`. Store them as credentials and call `skyvern_login`", "Set `max_steps` on tasks, or `x-max-steps-override` on agent runs, to cap credits. A run refused for credits answers 402 before a browser opens", "Pass `created_at_start` with `search_key` on GET /v1/agents/runs. Free-text search otherwise covers only the last 30 days" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 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": 57.5 } ], "editorialScores": { "ergonomics": 76, "maintenance": 85, "payments": 16, "reliability": 67, "schema": 88, "security": 59, "transparency": 70 }, "provenanceScore": 81, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install skyvern", "http": "curl -X POST \"https://api.skyvern.com/v1/run/tasks\" -H \"x-api-key: YOUR_API_KEY\" -H \"Content-Type: application/json\" -d '{ \"url\": \"https://example.com\", \"prompt\": \"Extract the pricing table\" }'", "claudeCode": "claude mcp add --transport http skyvern https://api.skyvern.com/mcp/ --scope user", "config": { "mcpServers": { "Skyvern": { "headers": { "x-api-key": "YOUR_SKYVERN_API_KEY" }, "type": "streamable-http", "url": "https://api.skyvern.com/mcp/" } } } }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/skyvern" }, "area": "developer", "unitPrices": [ { "item": "Hobby plan", "unit": "month", "usd": 29, "note": "30,000 credits, 10 concurrent runs" }, { "item": "Pro plan", "unit": "month", "usd": 149, "note": "150,000 credits, 25 concurrent runs" }, { "item": "Credit", "unit": "credit", "usd": 0.001, "note": "an action costs 30 credits, a cached action 15" }, { "item": "Browser uptime", "unit": "browser-hour", "usd": 0.2, "note": "200 credits an hour" }, { "item": "Skyvern SMS number, Pro plan", "unit": "month", "usd": 10, "note": "per number, for SMS 2FA codes" } ], "provenance": { "legalEntity": "Ikonomos Inc.", "domain": "skyvern.com", "domainRegistered": "2023-10-16", "endpointOnVendorDomain": true, "terms": "https://www.skyvern.com/terms", "privacy": "https://www.skyvern.com/privacy", "statusPage": "https://status.skyvern.com", "changelog": "https://www.skyvern.com/docs/changelog", "securityTxt": "none", "checked": "2026-11-02", "notes": [ "The terms (last modified 6 October 2026) and privacy policy (last modified 30 October 2026) name Ikonomos Inc., doing business as Skyvern, with Delaware law governing the terms.", "The API and the hosted MCP server answer at api.skyvern.com. OAuth is issued through clerk.skyvern.com, backed by Clerk.", "www.skyvern.com/.well-known/security.txt answered 404 on 2 November 2026 (api.skyvern.com's did on 8 October). SECURITY.md in the repository sends reports to GitHub private advisories.", "RDAP for skyvern.com gives a registration date of 2023-10-16.", "docs.skyvern.com redirects to www.skyvern.com/docs." ], "score": 81 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/skyvern.json", "live": { "slug": "skyvern", "probe": { "target": "https://api.skyvern.com/v1", "method": "get", "lastAt": "2026-11-06T09:47:50.332667808Z", "lastOk": true, "lastStatus": 404, "lastMs": 284, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 266, "p95ms24h": 367, "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": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "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.skyvern.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-06T09:43:49.457297625Z" }, "versions": [ { "registry": "github", "name": "Skyvern-AI/skyvern", "version": "v1.0.56", "released": "2026-10-14", "seenAt": "2026-11-05T22:09:04.102836694Z" }, { "registry": "mcp-registry", "name": "io.github.Skyvern-AI/skyvern", "version": "1.0.23", "seenAt": "2026-11-05T17:32:31.346782632Z" }, { "registry": "npm", "name": "@skyvern/client", "version": "1.0.56", "seenAt": "2026-11-05T22:09:02.351747043Z" }, { "registry": "pypi", "name": "skyvern", "version": "1.0.56", "released": "2026-10-14", "seenAt": "2026-11-05T22:09:02.103556735Z" } ], "githubStars": 23341, "npmWeekly": 4534, "pypiWeekly": 1038, "securityTxt": { "url": "https://skyvern.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-05T15:56:41.39730977Z" }, "llmsTxt": { "url": "https://www.skyvern.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:27:18.771797193Z" }, "domain": { "domain": "skyvern.com", "registered": "2023-10-16", "source": "https://rdap.verisign.com/com/v1/domain/skyvern.com", "checkedAt": "2026-11-01T14:25:24.865450524Z" }, "pages": [ { "url": "https://www.skyvern.com/docs/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-05T13:18:12.232607817Z", "changedAt": "2026-11-03T08:11:16.724689533Z", "fingerprint": "0bad8f051834" }, { "url": "https://www.skyvern.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-05T13:18:14.917667296Z", "changedAt": "2026-10-31T06:32:32.749728928Z", "fingerprint": "92e3753e0242" }, { "url": "https://www.skyvern.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-05T13:18:16.434406969Z", "changedAt": "2026-10-31T06:32:34.481955065Z", "fingerprint": "e5e84aee318f" }, { "url": "https://www.skyvern.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-05T13:18:18.40262646Z", "changedAt": "2026-10-31T06:32:36.677413768Z", "fingerprint": "273b6a8af36e" } ], "github": { "repo": "skyvern-ai/skyvern", "checkedAt": "2026-11-02T09:26:16.168324862Z", "stars": 23335, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T09:10:33Z", "openIssues": 55, "openPRs": 237, "issuesOpened90d": 35, "issuesClosed90d": 19, "prsMerged90d": 960, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-11-02T09:10:30Z" }, "replies": { "sampled": 25, "unanswered": 20, "medianDays": 0.6 } }, "updatedAt": "2026-11-06T09:47:50.332667808Z" } }, "edges": [ { "by": 46, "category": "schema", "leads": "skyvern", "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 at /docs/api-reference/openapi.json, now 106 operations on 80 paths with 279 schemas, and MCP tools with typed parameters (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). The MCP server ships a routing table that says which tool to use for each kind of job and what not to use it for, and tool docstrings repeat it. Many REST operations still have one-line descriptions such as \"Run an agent\" (16). Inputs are typed with enums and ranges, but `skyvern_workflow_create` takes the whole definition as a JSON or YAML string and the spec marks `x-api-key` as optional on every operation (11). Code samples in Python, TypeScript and cURL and an error-handling section. 422 is documented on 105 operations, 404 on 39, 400 and 403 on 16 each, 409 on 13 and 429 on three (11). `/v1` path versioning with a written compatibility policy and a weekly dated changelog (15). 25 + 10 + 16 + 11 + 11 + 15 = 88." }, "scores": { "a": 42, "b": 88 } }, { "by": 44, "category": "payments", "leads": "autocua", "name": "Payments \u0026 pricing", "reasons": { "a": "Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.", "b": "No x402, MPP or L402 in the docs, llms.txt or pricing page (0). The billing docs now publish unit prices, one credit $0.001, an action 30 credits ($0.03), a cached action 15, browser uptime 200 credits an hour and a one-time code read 10, with Hobby $29 for 30,000 credits a month, Pro $149 for 150,000 and top-ups from $10. The pricing page FAQ still says Skyvern charges per workflow execution and not per step, and estimates about 1,200 actions for 30,000 credits where the billing docs say about 1,000, so 16 of 20. The free plan has gone. Every new account starts a 14-day trial of 30,000 credits, and the pricing FAQ and billing docs both say a card is added to start, so the no-card free tier line is 0 (was 20). Signup is a browser flow, including `skyvern signup` from the CLI, so a person has to create the account (0). The open-source server is free to run under AGPL-3.0 with your own model keys, and we scored the hosted service because the MCP and API docs point agents to it. 0 + 16 + 0 + 0 = 16." }, "scores": { "a": 60, "b": 16 } }, { "by": 42, "category": "reliability", "leads": "skyvern", "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, Skyvern Cloud at api.skyvern.com. status.skyvern.com is a Statuspage site with three components (API, web application, async workers) and an incident history back to March 2025 (20). Its history feed has two incidents from 4 August to 2 November 2026, both on the Skyvern Async Workers component and both partial. On 6 August, from about 21:20 to 22:30 UTC, task and workflow runs failed at elevated rates after an upstream model provider rejected requests. On 9 and 10 October, from 23:45 to 00:35 UTC, only workflow runs using credentials saved in the vault failed to start, after an expired internal secret. Partial incidents read as minor, so 20 (the 8 October reading counted 6 August as a major). The 3 July 503 run is outside the window. Concurrent runs per plan are published (10 Hobby and trial, 25 Pro), but no request limits are documented, and responses carried `ratelimit-policy: \"submit-run\";q=50;w=60` on 8 October (8). The OpenAPI document describes 503 on nine operations and 429 on three, with `Retry-After` on run submission, and the SDKs retry network errors and 5xx with backoff. `Idempotency-Key` exists only on POST /v1/agents (9). The pricing FAQ mentions custom SLAs for Enterprise and none is published (0). `/v1` is declared stable (10). 20 + 20 + 8 + 9 + 0 + 10 = 67." }, "scores": { "a": 25, "b": 67 } }, { "by": 34, "category": "transparency", "leads": "skyvern", "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 core is AGPL-3.0, an OSI licence, in a public repository. The README says anti-bot measures are in the managed cloud only (27). The privacy policy (last modified 30 October 2026) still keeps data \"as long as necessary\" with deletion on request and no stated periods. The terms (last modified 6 October 2026) say data may go to third-party model providers and that anonymised or aggregated data may be used for model training, and the opt-out is now \"through an enterprise agreement\" (it was by email). Section 7.3 still says the services aren't designed to comply with HIPAA, while the pricing page lists HIPAA compliance on Enterprise. No public DPA found (12). The deprecation policy promises at least six months' notice, 12 for a major version, a changelog entry, `Deprecation` and `Sunset` headers and `deprecated` flags in the spec (20). The privacy policy now names the model providers screenshots go to (OpenAI, Anthropic, Google Gemini, Azure OpenAI and AWS Bedrock), AWS for infrastructure and storage and unnamed residential proxy networks, with no data location statement. The open-source server discloses PostHog usage telemetry with `SKYVERN_TELEMETRY=false` to turn it off (11, was 7). 27 + 12 + 20 + 11 = 70." }, "scores": { "a": 42, "b": 76 } }, { "by": 21, "category": "ergonomics", "leads": "skyvern", "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 full MCP surface is 118 tools by the docs' count (5). Scopes cut that to 31 (`operate`), 34 (`lean`), 55 (`browser`) or 63 (`build`) through a URL such as /mcp/x/lean or the `X-Skyvern-Scope` header, and page reads are size-capped and selector-scoped (9, so 14). List endpoints take `page` and `page_size`, with `status`, `search_key`, tag and date filters, the task list added optional cursor pagination in the week of 12 October, and `max_steps` bounds a run (17). MCP results return codes such as SELECTOR_NOT_FOUND and SESSION_EXPIRED with a hint, runs report `status`, `failure_reason` and a caller-defined `error_code_mapping`, and the SDKs raise typed errors. HTTP error bodies are mostly unspecified (16). Every tool has readOnlyHint, destructiveHint and openWorldHint annotations, 118 registrations in the source on 2 November. `Idempotency-Key` covers agent creation only, not run submission (14). A task needs only a prompt, and official SDKs exist for Python and TypeScript (15). 14 + 17 + 16 + 14 + 15 = 76." }, "scores": { "a": 55, "b": 76 } }, { "by": 21, "category": "security", "leads": "skyvern", "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": "An organisation-wide API key in the `x-api-key` header, rotated from Settings, with additional organisation keys an Admin can create, revoke or reissue in the app, or OAuth 2.0 with PKCE, dynamic client registration and rotating single-use refresh tokens. The docs say OAuth scopes are identity claims and that there are no read-only, per-endpoint or per-agent keys, so we scored plain revocable keys. No secret travels in a URL (20). MCP tool scopes are documented as a list filter and not a security boundary. Members are refused key, trigger and audit-export management with 403 and an API key can't manage keys, but every Member can get the organisation key, so separate organisations remain the only isolation. Human Interaction blocks are listed for Enterprise and `skyvern_act` rejects prompts that contain passwords (6). Web pages are untrusted content. Stored credentials reach the browser directly and appear to the model as placeholders, the May 2026 changelog records sanitising of page content in prompt templates, and one tool description says page content is data, not instructions. We found no guidance page on prompt injection (8). GET /v1/audit-events/export returns organisation audit events for a default 90 days as JSON or CSV, and each run keeps a recording, screenshots, an action timeline and a HAR file (14). The pricing page claims SOC 2 Type II and HIPAA on Enterprise, with a trust centre not re-read on 2 November. SECURITY.md routes reports to GitHub private advisories and its supported-versions table still says 0.1.x. No security.txt (404 on 2 November) and no bug bounty found. OSV holds one advisory, CVE-2025-49619 of June 2025 (11). 20 + 6 + 8 + 14 + 11 = 59." }, "scores": { "a": 38, "b": 59 } } ], "facts": [ { "a": "Agent framework", "b": "HTTP API", "name": "Kind" }, { "a": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)", "b": "Ikonomos Inc. (Skyvern)", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.skyvern.com/v1", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, Streamable HTTP, stdio", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Paid", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository", "name": "Licence" }, { "a": "none", "b": "118", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.github.Skyvern-AI/skyvern", "name": "MCP registry" }, { "a": "2026-11-04", "b": "2026-10-14", "name": "Last release" }, { "a": "no document linked", "b": "2026-02-27", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-10-01", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "23k stars, 3.2k npm/wk, 1.6k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Skyvern scores 57.5 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories. AutoCua leads on payments \u0026 pricing.", "question": "Which is better for AI agents, AutoCua or Skyvern?" }, { "answer": "No hosted endpoint is listed for AutoCua. Skyvern has a hosted endpoint at https://api.skyvern.com/v1.", "question": "Can an agent call AutoCua and Skyvern without installing anything?" }, { "answer": "Yes. AutoCua is open source (MIT). Skyvern is open source (AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository).", "question": "Are AutoCua and Skyvern open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 16" ], "also": [ "No key needed to call it", "No incidents deducted, where Skyvern loses 9 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" }, { "aheadOn": [ "Reliability, 67 against 25", "Schema \u0026 documentation, 88 against 42", "Agent ergonomics, 76 against 55", "Security \u0026 auth, 59 against 38", "Maintenance \u0026 community, 85 against 65", "Transparency \u0026 trust, 76 against 42" ], "also": [ "A hosted endpoint, with nothing to install", "Runs on your own machine" ], "goodFor": "Agents that must finish a multi-step job on sites with logins, 2FA and forms, where stored credentials, saved workflows and cached scripts matter more than raw browser time.", "slug": "skyvern", "watchFor": "Every API key and OAuth token has full organisation authority. The docs state there are no read-only, per-endpoint or per-agent keys" } ], "history": { "autocua": null, "skyvern": [ { "causes": [ "terms", "pricing", "security", "correction" ], "date": "2026-11-02", "delta": -5.8, "from": 63.3, "fromGrade": "B", "to": 57.5, "toGrade": "C" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 63.2, "fromGrade": "B", "to": 63.3, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 63.1, "fromGrade": "B", "to": 63.2, "toGrade": "B" } ] }, "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-skyvern.json", "title": "agent-browser vs Skyvern", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-skyvern" }, { "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-skyvern.json", "title": "Airtop vs Skyvern", "url": "https://www.anchorterminal.com/compare/airtop-vs-skyvern" }, { "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-skyvern.json", "title": "Anchor Browser vs Skyvern", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-skyvern" }, { "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-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-skyvern.json", "title": "Browser Use vs Skyvern", "url": "https://www.anchorterminal.com/compare/browser-use-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-skyvern.json", "title": "Browserless vs Skyvern", "url": "https://www.anchorterminal.com/compare/browserless-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/bx-playwright-vs-skyvern.json", "title": "BxPlaywright vs Skyvern", "url": "https://www.anchorterminal.com/compare/bx-playwright-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-skyvern.json", "title": "Chrome DevTools MCP vs Skyvern", "url": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern.json", "title": "Functionize MCP server vs Skyvern", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/hyperbrowser-vs-skyvern.json", "title": "Hyperbrowser vs Skyvern", "url": "https://www.anchorterminal.com/compare/hyperbrowser-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/kane-cli-vs-skyvern.json", "title": "Kane CLI vs Skyvern", "url": "https://www.anchorterminal.com/compare/kane-cli-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/lightpanda-vs-skyvern.json", "title": "Lightpanda vs Skyvern", "url": "https://www.anchorterminal.com/compare/lightpanda-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/notte-vs-skyvern.json", "title": "Notte vs Skyvern", "url": "https://www.anchorterminal.com/compare/notte-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/playwright-mcp-vs-skyvern.json", "title": "Playwright MCP vs Skyvern", "url": "https://www.anchorterminal.com/compare/playwright-mcp-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/pomerado-vs-skyvern.json", "title": "Pomerado vs Skyvern", "url": "https://www.anchorterminal.com/compare/pomerado-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-skyvern.json", "title": "Puppeteer (archived MCP reference server) vs Skyvern", "url": "https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/puppeteer-vs-skyvern.json", "title": "Puppeteer vs Skyvern", "url": "https://www.anchorterminal.com/compare/puppeteer-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/selenium-vs-skyvern.json", "title": "Selenium vs Skyvern", "url": "https://www.anchorterminal.com/compare/selenium-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/skyvern-vs-steel.json", "title": "Skyvern vs Steel", "url": "https://www.anchorterminal.com/compare/skyvern-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/skyvern-vs-tinyfish.json", "title": "Skyvern vs TinyFish", "url": "https://www.anchorterminal.com/compare/skyvern-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/browserbase-vs-skyvern.json", "title": "Browserbase vs Skyvern", "url": "https://www.anchorterminal.com/compare/browserbase-vs-skyvern" } ], "panel": null, "scores": [ { "autocua": 25, "by": 42, "edge": "skyvern", "key": "reliability", "name": "Reliability", "skyvern": 67, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "autocua": 42, "by": 46, "edge": "skyvern", "key": "schema", "name": "Schema \u0026 documentation", "skyvern": 88, "weight": 13 }, { "autocua": 55, "by": 21, "edge": "skyvern", "key": "ergonomics", "name": "Agent ergonomics", "skyvern": 76, "weight": 13 }, { "autocua": 38, "by": 21, "edge": "skyvern", "key": "security", "name": "Security \u0026 auth", "skyvern": 59, "weight": 14 }, { "autocua": 60, "by": 44, "edge": "autocua", "key": "payments", "name": "Payments \u0026 pricing", "skyvern": 16, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "autocua": 65, "by": 20, "edge": "skyvern", "key": "maintenance", "name": "Maintenance \u0026 community", "skyvern": 85, "weight": 7 }, { "autocua": 42, "by": 34, "edge": "skyvern", "key": "transparency", "name": "Transparency \u0026 trust", "skyvern": 76, "weight": 7 } ], "summary": "Skyvern scores 57.5 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories. AutoCua leads on payments \u0026 pricing. Both do browser automation.", "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.", "skyvern": "The hosted MCP server annotates all 118 tools as read-only or destructive and can serve a 31 or 34-tool scope, and the API has a written six-month deprecation policy. Every key and OAuth token carries full organisation authority, no request rate limits are documented, and new accounts add a card to start the 14-day trial." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/autocua-vs-skyvern", "json": "https://www.anchorterminal.com/compare/autocua-vs-skyvern.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/autocua-vs-skyvern.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/autocua-vs-skyvern.min.md" }, "markdown": "Skyvern scores 57.5 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories. AutoCua leads on payments \u0026 pricing. Both do browser automation.\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- Skyvern: grade C, 57.5/100, rank #709 of 1354. Markdown https://www.anchorterminal.com/tools/skyvern.md · JSON https://www.anchorterminal.com/api/v1/tools/skyvern.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\nAhead on:\n- Payments \u0026 pricing, 60 against 16\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Skyvern loses 9 points for them\n\nWatch for: Two weeks old at version 0.1.9, with no changelog file\n\n### Skyvern (C)\n\nGood for: Agents that must finish a multi-step job on sites with logins, 2FA and forms, where stored credentials, saved workflows and cached scripts matter more than raw browser time.\n\nAhead on:\n- Reliability, 67 against 25\n- Schema \u0026 documentation, 88 against 42\n- Agent ergonomics, 76 against 55\n- Security \u0026 auth, 59 against 38\n- Maintenance \u0026 community, 85 against 65\n- Transparency \u0026 trust, 76 against 42\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n\nWatch for: Every API key and OAuth token has full organisation authority. The docs state there are no read-only, per-endpoint or per-agent keys\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Skyvern +46\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- Skyvern (88): OpenAPI 3.1.0 at /docs/api-reference/openapi.json, now 106 operations on 80 paths with 279 schemas, and MCP tools with typed parameters (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). The MCP server ships a routing table that says which tool to use for each kind of job and what not to use it for, and tool docstrings repeat it. Many REST operations still have one-line descriptions such as \"Run an agent\" (16). Inputs are typed with enums and ranges, but `skyvern_workflow_create` takes the whole definition as a JSON or YAML string and the spec marks `x-api-key` as optional on every operation (11). Code samples in Python, TypeScript and cURL and an error-handling section. 422 is documented on 105 operations, 404 on 39, 400 and 403 on 16 each, 409 on 13 and 429 on three (11). `/v1` path versioning with a written compatibility policy and a weekly dated changelog (15). 25 + 10 + 16 + 11 + 11 + 15 = 88.\n\n### Payments \u0026 pricing: AutoCua +44\n\n- AutoCua (60): Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.\n- Skyvern (16): No x402, MPP or L402 in the docs, llms.txt or pricing page (0). The billing docs now publish unit prices, one credit $0.001, an action 30 credits ($0.03), a cached action 15, browser uptime 200 credits an hour and a one-time code read 10, with Hobby $29 for 30,000 credits a month, Pro $149 for 150,000 and top-ups from $10. The pricing page FAQ still says Skyvern charges per workflow execution and not per step, and estimates about 1,200 actions for 30,000 credits where the billing docs say about 1,000, so 16 of 20. The free plan has gone. Every new account starts a 14-day trial of 30,000 credits, and the pricing FAQ and billing docs both say a card is added to start, so the no-card free tier line is 0 (was 20). Signup is a browser flow, including `skyvern signup` from the CLI, so a person has to create the account (0). The open-source server is free to run under AGPL-3.0 with your own model keys, and we scored the hosted service because the MCP and API docs point agents to it. 0 + 16 + 0 + 0 = 16.\n\n### Reliability: Skyvern +42\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- Skyvern (67): Graded as a hosted service, Skyvern Cloud at api.skyvern.com. status.skyvern.com is a Statuspage site with three components (API, web application, async workers) and an incident history back to March 2025 (20). Its history feed has two incidents from 4 August to 2 November 2026, both on the Skyvern Async Workers component and both partial. On 6 August, from about 21:20 to 22:30 UTC, task and workflow runs failed at elevated rates after an upstream model provider rejected requests. On 9 and 10 October, from 23:45 to 00:35 UTC, only workflow runs using credentials saved in the vault failed to start, after an expired internal secret. Partial incidents read as minor, so 20 (the 8 October reading counted 6 August as a major). The 3 July 503 run is outside the window. Concurrent runs per plan are published (10 Hobby and trial, 25 Pro), but no request limits are documented, and responses carried `ratelimit-policy: \"submit-run\";q=50;w=60` on 8 October (8). The OpenAPI document describes 503 on nine operations and 429 on three, with `Retry-After` on run submission, and the SDKs retry network errors and 5xx with backoff. `Idempotency-Key` exists only on POST /v1/agents (9). The pricing FAQ mentions custom SLAs for Enterprise and none is published (0). `/v1` is declared stable (10). 20 + 20 + 8 + 9 + 0 + 10 = 67.\n\n### Transparency \u0026 trust: Skyvern +34\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- Skyvern (76): The core is AGPL-3.0, an OSI licence, in a public repository. The README says anti-bot measures are in the managed cloud only (27). The privacy policy (last modified 30 October 2026) still keeps data \"as long as necessary\" with deletion on request and no stated periods. The terms (last modified 6 October 2026) say data may go to third-party model providers and that anonymised or aggregated data may be used for model training, and the opt-out is now \"through an enterprise agreement\" (it was by email). Section 7.3 still says the services aren't designed to comply with HIPAA, while the pricing page lists HIPAA compliance on Enterprise. No public DPA found (12). The deprecation policy promises at least six months' notice, 12 for a major version, a changelog entry, `Deprecation` and `Sunset` headers and `deprecated` flags in the spec (20). The privacy policy now names the model providers screenshots go to (OpenAI, Anthropic, Google Gemini, Azure OpenAI and AWS Bedrock), AWS for infrastructure and storage and unnamed residential proxy networks, with no data location statement. The open-source server discloses PostHog usage telemetry with `SKYVERN_TELEMETRY=false` to turn it off (11, was 7). 27 + 12 + 20 + 11 = 70.\n\n### Agent ergonomics: Skyvern +21\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- Skyvern (76): The full MCP surface is 118 tools by the docs' count (5). Scopes cut that to 31 (`operate`), 34 (`lean`), 55 (`browser`) or 63 (`build`) through a URL such as /mcp/x/lean or the `X-Skyvern-Scope` header, and page reads are size-capped and selector-scoped (9, so 14). List endpoints take `page` and `page_size`, with `status`, `search_key`, tag and date filters, the task list added optional cursor pagination in the week of 12 October, and `max_steps` bounds a run (17). MCP results return codes such as SELECTOR_NOT_FOUND and SESSION_EXPIRED with a hint, runs report `status`, `failure_reason` and a caller-defined `error_code_mapping`, and the SDKs raise typed errors. HTTP error bodies are mostly unspecified (16). Every tool has readOnlyHint, destructiveHint and openWorldHint annotations, 118 registrations in the source on 2 November. `Idempotency-Key` covers agent creation only, not run submission (14). A task needs only a prompt, and official SDKs exist for Python and TypeScript (15). 14 + 17 + 16 + 14 + 15 = 76.\n\n### Security \u0026 auth: Skyvern +21\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- Skyvern (59): An organisation-wide API key in the `x-api-key` header, rotated from Settings, with additional organisation keys an Admin can create, revoke or reissue in the app, or OAuth 2.0 with PKCE, dynamic client registration and rotating single-use refresh tokens. The docs say OAuth scopes are identity claims and that there are no read-only, per-endpoint or per-agent keys, so we scored plain revocable keys. No secret travels in a URL (20). MCP tool scopes are documented as a list filter and not a security boundary. Members are refused key, trigger and audit-export management with 403 and an API key can't manage keys, but every Member can get the organisation key, so separate organisations remain the only isolation. Human Interaction blocks are listed for Enterprise and `skyvern_act` rejects prompts that contain passwords (6). Web pages are untrusted content. Stored credentials reach the browser directly and appear to the model as placeholders, the May 2026 changelog records sanitising of page content in prompt templates, and one tool description says page content is data, not instructions. We found no guidance page on prompt injection (8). GET /v1/audit-events/export returns organisation audit events for a default 90 days as JSON or CSV, and each run keeps a recording, screenshots, an action timeline and a HAR file (14). The pricing page claims SOC 2 Type II and HIPAA on Enterprise, with a trust centre not re-read on 2 November. SECURITY.md routes reports to GitHub private advisories and its supported-versions table still says 0.1.x. No security.txt (404 on 2 November) and no bug bounty found. OSV holds one advisory, CVE-2025-49619 of June 2025 (11). 20 + 6 + 8 + 14 + 11 = 59.\n\n## Score by category\n\n| Category | Weight | AutoCua | Skyvern | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 67 | Skyvern +42 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 42 | 88 | Skyvern +46 |\n| Agent ergonomics | 13% (16.2 this run) | 55 | 76 | Skyvern +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 59 | Skyvern +21 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 16 | AutoCua +44 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 85 | Skyvern +20 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 42 | 76 | Skyvern +34 |\n| Negative events | ≤15 | 0 | -9 | |\n| **Total** | | **44.3 · E** | **57.5 · C** | |\n\n## Facts side by side\n\n| Fact | AutoCua | Skyvern |\n| --- | --- | --- |\n| Kind | Agent framework | HTTP API |\n| Vendor | Ashish Yadav and contributors (ComputerUseAgent on GitHub) | Ikonomos Inc. (Skyvern) |\n| Hosted endpoint | no (local only) | `https://api.skyvern.com/v1` |\n| Transports | | HTTP, Streamable HTTP, stdio |\n| Auth | None | OAuth or key |\n| Pricing | Free | Paid |\n| x402 | no | no |\n| Licence | MIT | AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository |\n| Tools exposed | none | 118 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `io.github.Skyvern-AI/skyvern` |\n| Last release | 2026-11-04 | 2026-10-14 |\n| Terms last updated | no document linked | 2026-02-27 |\n| Privacy policy last updated | no document linked | 2026-10-01 |\n| Customer content may train models | not read yet | yes, with an opt-out |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | yes |\n| Popularity | none | 23k stars, 3.2k npm/wk, 1.6k 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### Skyvern\n\n- -5.8 on 2 November 2026 (B to C): terms, pricing, security, correction\n- +0.1 on 28 October 2026: new evidence\n- +0.1 on 27 October 2026: checklist\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**Skyvern.** The hosted MCP server annotates all 118 tools as read-only or destructive and can serve a 31 or 34-tool scope, and the API has a written six-month deprecation policy. Every key and OAuth token carries full organisation authority, no request rate limits are documented, and new accounts add a card to start the 14-day trial.\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### Skyvern\n\n1. Connect to https://api.skyvern.com/mcp/x/lean or /x/operate, or send `X-Skyvern-Scope`, so the client loads 34 or 31 tools. The scope filters the list and does not limit permissions\n2. Use a separate Skyvern organisation for each blast radius. Any key or OAuth token can read and write stored credentials and delete workflows\n3. Never pass passwords to `skyvern_act` or `skyvern_type`. Store them as credentials and call `skyvern_login`\n4. Set `max_steps` on tasks, or `x-max-steps-override` on agent runs, to cap credits. A run refused for credits answers 402 before a browser opens\n5. Pass `created_at_start` with `search_key` on GET /v1/agents/runs. Free-text search otherwise covers only the last 30 days\n\n## Questions\n\n### Which is better for AI agents, AutoCua or Skyvern?\n\nSkyvern scores 57.5 (C) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories. AutoCua leads on payments \u0026 pricing.\n\n### Can an agent call AutoCua and Skyvern without installing anything?\n\nNo hosted endpoint is listed for AutoCua. Skyvern has a hosted endpoint at https://api.skyvern.com/v1.\n\n### Are AutoCua and Skyvern open source?\n\nYes. AutoCua is open source (MIT). Skyvern is open source (AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/autocua-vs-skyvern.json, and with the fewest tokens: https://www.anchorterminal.com/compare/autocua-vs-skyvern.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"autocua\", \"b\": \"skyvern\"}`. From a terminal: `anchor compare autocua skyvern`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/autocua.json and https://www.anchorterminal.com/api/v1/tools/skyvern.json\n\n## Other comparisons with AutoCua or Skyvern\n\n- [agent-browser vs AutoCua](https://www.anchorterminal.com/compare/agent-browser-vs-autocua.md)\n- [agent-browser vs Skyvern](https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.md)\n- [Airtop vs AutoCua](https://www.anchorterminal.com/compare/airtop-vs-autocua.md)\n- [Airtop vs Skyvern](https://www.anchorterminal.com/compare/airtop-vs-skyvern.md)\n- [Anchor Browser vs AutoCua](https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.md)\n- [Anchor Browser vs Skyvern](https://www.anchorterminal.com/compare/anchor-browser-vs-skyvern.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 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 Skyvern](https://www.anchorterminal.com/compare/browser-use-vs-skyvern.md)\n- [Browserless vs Skyvern](https://www.anchorterminal.com/compare/browserless-vs-skyvern.md)\n- [BxPlaywright vs Skyvern](https://www.anchorterminal.com/compare/bx-playwright-vs-skyvern.md)\n- [Chrome DevTools MCP vs Skyvern](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-skyvern.md)\n- [Functionize MCP server vs Skyvern](https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern.md)\n- [Hyperbrowser vs Skyvern](https://www.anchorterminal.com/compare/hyperbrowser-vs-skyvern.md)\n- [Kane CLI vs Skyvern](https://www.anchorterminal.com/compare/kane-cli-vs-skyvern.md)\n- [Lightpanda vs Skyvern](https://www.anchorterminal.com/compare/lightpanda-vs-skyvern.md)\n- [Notte vs Skyvern](https://www.anchorterminal.com/compare/notte-vs-skyvern.md)\n- [Playwright MCP vs Skyvern](https://www.anchorterminal.com/compare/playwright-mcp-vs-skyvern.md)\n- [Pomerado vs Skyvern](https://www.anchorterminal.com/compare/pomerado-vs-skyvern.md)\n- [Puppeteer (archived MCP reference server) vs Skyvern](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-skyvern.md)\n- [Puppeteer vs Skyvern](https://www.anchorterminal.com/compare/puppeteer-vs-skyvern.md)\n- [Selenium vs Skyvern](https://www.anchorterminal.com/compare/selenium-vs-skyvern.md)\n- [Skyvern vs Steel](https://www.anchorterminal.com/compare/skyvern-vs-steel.md)\n- [Skyvern vs TinyFish](https://www.anchorterminal.com/compare/skyvern-vs-tinyfish.md)\n- [Browserbase vs Skyvern](https://www.anchorterminal.com/compare/browserbase-vs-skyvern.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 Skyvern", "url": "" } ], "description": "Skyvern scores 57.5 (C) to AutoCua's 44.3 (E) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "AutoCua E 44.3", "Skyvern C 57.5", "scores" ], "h1": "AutoCua vs Skyvern", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/autocua-vs-skyvern", "published": "2026-10-01", "section": "tools", "title": "AutoCua vs Skyvern for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/autocua-vs-skyvern" }, "tokens": { "markdown": 5450, "slim": 3280 }, "version": 1 }