{ "data": { "a": { "slug": "qwenpaw", "name": "QwenPaw", "vendor": "AgentScope", "vendorUrl": "https://qwenpaw.agentscope.io", "kind": "harness", "category": "personal-assistants", "summary": "Open-source personal assistant from the AgentScope team that the owner runs on their own machine or server. It answers on chat apps, runs scheduled and proactive tasks, manages a mailbox over IMAP and SMTP, and keeps memory as Markdown files.", "url": "https://www.anchorterminal.com/tools/qwenpaw", "markdownUrl": "https://www.anchorterminal.com/tools/qwenpaw.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/qwenpaw.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/qwenpaw.json", "repo": "https://github.com/agentscope-ai/QwenPaw", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "packages": [ { "registry": "pypi", "name": "qwenpaw" }, { "registry": "oci", "name": "agentscope/qwenpaw" } ], "auth": "none", "authNotes": "No account. The Console and API bind to 127.0.0.1:8088 with login off by default. `QWENPAW_AUTH_ENABLED=true` adds one admin account with a salted SHA-256 password hash and a signed token valid for seven days, and requests from localhost skip it. Each channel takes its own bot credentials, and the mailbox takes an IMAP and SMTP authorisation code or app password.", "pricing": "free", "pricingNotes": "Free under Apache-2.0 with nothing to buy. Model usage is billed by whichever provider the owner configures, and local models through llama.cpp, Ollama or LM Studio need no key. The README describes a hosted deployment on AgentScope Platform as free. That platform's pages are script-drawn and its terms and limits were not read (checked 2026-10-12).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs source or the dependency list (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 35621, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://qwenpaw.agentscope.io/docs", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "tags": [ "open-source", "self-hosted", "local", "free", "python", "docker", "desktop-app", "mcp", "telemetry-default-on" ], "lastRelease": "2026-09-11", "graded": true, "anchor": { "graded": true, "score": 62.4, "grade": "B", "agentReady": false, "rank": 508, "ranked": true, "rankOf": 1244, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 73, "payments": 60, "reliability": 70, "schema": 68, "security": 60, "transparency": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": -3, "negativeNotes": [ "2026-09-11. Version 2.2.1 began enforcing each MCP server's tool allowlist on the agent runtime path (commit f2a292d of 4 September, #7504). Before it, a tool the owner had disabled on an MCP client could still be invoked by the agent. Fixed and listed in the release notes, with no security advisory, -2. https://github.com/agentscope-ai/QwenPaw/pull/7504", "2026-09-03. Version 2.2.0 blocked shell line-continuation variants that bypassed sensitive-path protections (#7472). Fixed and listed in the release notes, with no security advisory, -1. https://github.com/agentscope-ai/QwenPaw/blob/main/website/public/release-notes/v2.2.0.md" ], "verdict": "Mail tools ask for approval by default, automatic mail handling may not delete permanently, and the security docs list what each sandbox backend fails to enforce. Usage data is sent by default, the default approval level passes every tool call no rule flags, and no privacy policy or security advisory is published.", "bestFor": "One person who wants an assistant on Chinese and Western chat apps with scheduled digests, a consumer mailbox and file-based memory, on their own machine and with a model of their choice.", "strengths": [ "New mail driver cards default to the `ask` policy, and automatic mail handling may not call `delete_message` or write to unknown recipients", "Kernel sandbox on macOS, Linux and Windows, with a documented list of constraints each backend does not enforce", "Model keys, mail credentials and environment secrets are encrypted with a master key held in the OS keychain or a 0600 file", "Memory is plain Markdown in the agent workspace that the owner can read, edit and remove", "Four stable releases in the 90 days to 12 October 2026, each with dated release notes" ], "weaknesses": [ "Usage data is on by default, `qwenpaw init --defaults` accepts it without a prompt, and the opt-out variable is absent from the README and docs", "The default approval level AUTO asks only for tool calls a guard rule flags, and `/proactive` skips approval prompts entirely", "Channel direct-message and group policies default to `open`, and Console login is off by default", "No privacy policy, terms of service or security.txt on qwenpaw.agentscope.io, and no published GitHub security advisory", "Inside containers the sandbox falls back to `mode=none`, which the docs say enforces no isolation", "671 open issues and 381 open pull requests on 12 October 2026, and the Tests workflow on main had not completed a run since 30 September" ], "agentNotes": [ "Set `QWENPAW_TELEMETRY_DISABLED=true` before `qwenpaw init --defaults` or `qwenpaw app`. Both send usage data without asking", "Set `approval_level` to `STRICT` or `SMART` in `agent.json`. The default `AUTO` runs every tool call no guard rule flags", "Set `dm_policy` and `group_policy` to `allowlist` with `allow_from` on each channel. Both default to `open`", "Set `QWENPAW_AUTH_ENABLED=true` before binding beyond 127.0.0.1. Requests from localhost skip login even then", "Keep mail tools on `ask` for `send_message`, `delete_message` and `delete_thread`, and turn on Mail Access Control with automatic handling" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.4 } ], "editorialScores": { "ergonomics": 67, "maintenance": 73, "payments": 60, "reliability": 70, "schema": 68, "security": 60, "transparency": 58 }, "provenanceScore": 58, "checked": { "categories": { "ergonomics": "2026-10-12", "maintenance": "2026-10-12", "payments": "2026-10-12", "reliability": "2026-10-12", "schema": "2026-10-12", "security": "2026-10-12", "transparency": "2026-10-12" }, "last": "2026-10-12", "lastMoved": "2026-10-27", "oldest": "2026-10-12", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install qwenpaw \u0026\u0026 qwenpaw init --defaults \u0026\u0026 qwenpaw app # Python 3.11 to 3.13; or: docker pull agentscope/qwenpaw:latest", "http": "curl -X POST http://localhost:8088/api/console/chat -H \"Content-Type: application/json\" -H \"X-Agent-Id: default\" -d '{\"input\": [...]}'" }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/qwenpaw" }, "area": "frameworks", "provenance": { "legalEntity": "Qwenpaw PRIVATE LIMITED", "domain": "agentscope.io", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://qwenpaw.agentscope.io/release-notes", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The site footer in the repository's website source reads © 2026 Qwenpaw PRIVATE LIMITED. The LICENSE file names The QwenPaw Authors, and the README credits the AgentScope team.", "SECURITY.md sends vulnerability reports to the Alibaba Security Response Centre. We found no other first-hand statement of ownership by Alibaba.", "The site links a Usage Policy dated 26 August 2026 and no terms of service or privacy policy, so both links are left out and the Apache-2.0 licence stands in.", "qwenpaw.agentscope.io answered 404 for robots.txt, llms.txt and /.well-known/security.txt on 12 October 2026.", "No hosted endpoint is graded. A self-hosted instance answers on its owner's own host. We did not look up the domain's registration date." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/qwenpaw.json", "live": { "slug": "qwenpaw", "versions": [ { "registry": "github", "name": "agentscope-ai/QwenPaw", "version": "v2.2.2.post1", "released": "2026-10-22", "seenAt": "2026-10-30T14:40:30.202481312Z" }, { "registry": "pypi", "name": "qwenpaw", "version": "2.2.2.post1", "released": "2026-10-22", "seenAt": "2026-10-30T14:40:28.201920797Z" } ], "githubStars": 37005, "pypiWeekly": 6002, "securityTxt": { "url": "https://agentscope.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-30T15:38:17.243013426Z" }, "domain": { "domain": "agentscope.io", "checkedAt": "2026-10-25T14:05:08.651487695Z" }, "pages": [ { "url": "https://qwenpaw.agentscope.io/release-notes", "kind": "changelog", "status": 404, "checkedAt": "2026-10-30T05:46:52.099856896Z", "changedAt": "0001-01-01T00:00:00Z" } ], "github": { "repo": "agentscope-ai/qwenpaw", "checkedAt": "2026-10-26T07:08:22.236751997Z", "stars": 36257, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-26T06:27:59Z", "openIssues": 716, "openPRs": 426, "issuesOpened90d": 778, "issuesClosed90d": 687, "prsMerged90d": 664, "ci": { "branch": "main", "runs": 50, "success": 48, "failure": 0, "other": 2, "latest": "success", "latestAt": "2026-10-26T06:42:16Z" }, "replies": { "sampled": 25, "unanswered": 15, "medianDays": 0 } }, "updatedAt": "2026-10-30T15:38:17.243013426Z" } }, "answer": "QwenPaw scores 62.4 (B) on agent readiness against Skydive's 52.1 (D), and leads in 5 of 7 scored categories. Skydive leads on schema \u0026 documentation and transparency \u0026 trust.", "b": { "slug": "skydive", "name": "Skydive", "vendor": "Create, Inc.", "vendorUrl": "https://www.skydive.com", "kind": "platform", "category": "personal-assistants", "summary": "Skydive, from Create, Inc., hosts AI agents that each get a cloud Linux computer, file-based memory and connected apps. People reach them on the web, in Slack, by email, SMS or iMessage, in a Mac app or from a CLI.", "url": "https://www.anchorterminal.com/tools/skydive", "markdownUrl": "https://www.anchorterminal.com/tools/skydive.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/skydive.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/skydive.json", "license": "Closed service under the Skydive Terms of Service (Create, Inc.), effective 29 July 2026. The skydive-cli npm package is published under the MIT licence.", "transports": [ "http" ], "remoteUrl": "https://api.skydive.com/v1", "packages": [ { "registry": "npm", "name": "skydive-cli" } ], "auth": "mixed", "authNotes": "The REST API takes a bearer API key (sky_live_...) with a `use` or `edit` scope, bound to one agent or to the account (https://www.skydive.com/docs/api-reference/overview.md). The CLI uses that key or a browser device sign-in, or SKYDIVE_SESSION_TOKEN for non-interactive use (https://www.skydive.com/docs/cli/authentication.md). People sign in to the web app with Google, Slack or a password (https://www.skydive.com/docs/changelog.md). Connected services use OAuth, MCP OAuth or stored secrets injected by Skydive's proxy.", "pricing": "freemium", "pricingNotes": "Free at US$0 a month, pay as you go with no card, starting with a small amount of credit. Starter is US$20 a month and Team US$200 a month, each flat per workspace with unlimited seats and agents, and the fee becomes usage credit 1:1. Enterprise is custom. Model usage is passed through at cost with no markup (the vendor's claim), and compute and metered services also draw the balance. A dedicated iMessage line is US$100 a month per agent (https://www.skydive.com/docs/account/pricing.md, checked 31 October 2026).", "priceSummary": "$20 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs llms.txt, the blog llms.txt, the OpenAPI document or the site's JS bundle, checked 31 October 2026. Usage is paid from a prepaid credit balance by card through the billing page.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 5465, "pypiWeekly": null, "asOf": "2026-10-31" }, "docsUrl": "https://www.skydive.com/docs/get-started/welcome", "llmsTxt": "https://www.skydive.com/docs/llms.txt", "openapi": "https://api.skydive.com/v1/openapi.json", "capabilities": [ "assistant.memory", "assistant.messaging", "assistant.accounts", "assistant.proactive", "agent.mcp-client", "agent.multi-agent", "browser.hosted", "email.inbound", "email.send", "mailbox.read", "mailbox.send", "calendar.write", "messaging.inbound", "web.search", "desktop.control" ], "tags": [ "hosted", "official", "closed-source", "freemium", "no-card", "llms-txt", "openapi", "api-key", "cli", "status-page", "security-txt", "mcp-client", "slack", "email", "imessage", "sms", "macos", "desktop-app", "trains-on-data-by-default", "enterprise" ], "lastRelease": "2026-08-26", "graded": true, "disclosure": "Skydive competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.", "competesWith": "localghost", "anchor": { "graded": true, "score": 52.1, "grade": "D", "agentReady": false, "rank": 899, "ranked": true, "rankOf": 1244, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 56, "payments": 35, "reliability": 41, "schema": 81, "security": 59, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-31" }, "negative": -5, "negativeNotes": [ "Misleading claims, -5 for the three below together, read by us on 31 October 2026. 1) Training. The pricing page FAQ answers \"Is my data used to train models?\" with \"No. Your data is never used to train models, ours or anyone else's\", and the home page's security section says \"your data is never used to train models\", while the privacy policy (section 4) and the Terms of Service (9.2), both of 29 July 2026, say training on customer content \"is on by default\" with a workspace or organisation opt-out. Alone this would be Lindy's -3 for a pricing-page answer the vendor's own pages contradict (https://www.skydive.com/assets/main-MHOpsky7.js, https://www.skydive.com/privacy).", "2) Certification, one of the three. The home page says \"SOC 2 compliant\" twice and the site footer shows a badge with the alt text \"SOC 2 Type 1\", while the DPA (7.2) says that as of 29 July 2026 Create is pursuing SOC 2 compliance and does not represent that any SOC 2 or ISO 27001 report or certification has been completed, and the privacy policy says Create is pursuing SOC 2. No report or trust centre was found. Alone this would be the ScaleDown and Nevermined -2 (https://www.skydive.com/assets/main-MHOpsky7.js, https://www.skydive.com/dpa).", "3) Secrets, one of the three. The Secrets, Network controls and Permissioning pages say the agent never sees a secret, that it \"was never in the sandbox to begin with\" and that the design \"removes the whole class of risk\", and the pricing FAQ says secrets are \"never shown to the model\". The platform CLI, which the docs say is inside every agent's sandbox, lists `secrets get` to read a value and `secrets download --plain` to print raw values, and the OpenAPI description of setAgentSecret says the value becomes an environment variable in the sandbox. Alone this would be at least the -2 Picoclaw and OpenInstinct took for a security claim the product doesn't keep. None of the three is corrected, so the deduction is the top of the range for misleading claims rather than -7, as Self Agent Vault and AgentOS folded several claims into one deduction (https://www.skydive.com/docs/integrations/secrets.md, https://www.skydive.com/docs/capabilities/network.md, https://www.skydive.com/docs/api-reference/cli/secrets.md, https://www.skydive.com/docs/api-reference/platform-cli.md, https://api.skydive.com/v1/openapi.json)." ], "verdict": "Skydive publishes an OpenAPI 3.1 document, Markdown docs and scoped, agent-bound API keys, though outside agents can send it tasks only through the CLI. Its status page records several major incidents, including a 25-hour Agent Hosting outage, and its home and pricing pages say data is never used for training while the privacy policy turns training on by default.", "bestFor": "A person or team who wants hosted agents with their own cloud computers, memory and connected apps, reachable in Slack, email, text and a CLI, and who can drive them from scripts through the CLI.", "disclosure": "Skydive competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.", "strengths": [ "A public OpenAPI 3.1 document covers all 11 API operations, and llms.txt indexes a Markdown copy of every docs page.", "API keys carry a read-only `use` or an `edit` scope, can be bound to one agent, are stored hashed and revoke immediately.", "Owners and admins get an always-on, exportable audit log covering secret access, API-key changes and sign-ins, per the Roles page.", "The privacy policy names 22 subprocessors and gives retention periods of 30, 60 and 90 days and 12 months.", "Free workspaces start with credit and no card, and per-token model rates are published at cost (the vendor's claim)." ], "weaknesses": [ "The API has no operation for sending an agent a task. That runs through the CLI's `chat -p`, outside the OpenAPI contract.", "Several major incidents in 90 days, among them a 25-hour Agent Hosting outage on 28 and 29 October 2026, per status.skydive.com.", "The home page and pricing FAQ say data is never used to train models, while the privacy policy turns training on by default.", "The docs say agents never see secrets, but the platform CLI inside the sandbox can print raw secret values.", "The site says SOC 2 compliant and shows a SOC 2 Type 1 badge, while the DPA says no SOC 2 report has been completed." ], "agentNotes": [ "Send tasks with `skydive chat -p \"...\" --agent \u003cid\u003e --json` and pass `--conversation \u003cid\u003e` from the JSON to keep context. The REST API can't send a task.", "Don't retry `chat -p` or a create blindly after a timeout. There's no idempotency key, so list agents or keys before retrying.", "Ask the owner for an agent-bound `use` key when you only need to read. Account-level `edit` keys can create agents and mint keys.", "Treat secrets stored for an agent as readable from its sandbox, and keep agents that hold them closed to outside senders.", "Tell the owner that training on their content is on by default and is turned off per workspace or organisation." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.1 } ], "editorialScores": { "ergonomics": 59, "maintenance": 56, "payments": 35, "reliability": 41, "schema": 81, "security": 59, "transparency": 55 }, "provenanceScore": 95, "checked": { "categories": { "ergonomics": "2026-10-31", "maintenance": "2026-10-31", "payments": "2026-10-31", "reliability": "2026-10-31", "schema": "2026-10-31", "security": "2026-10-31", "transparency": "2026-10-31" }, "last": "2026-10-31", "oldest": "2026-10-31", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g skydive-cli", "http": "curl https://api.skydive.com/v1/agents \\\n -H \"Authorization: Bearer $SKYDIVE_API_KEY\"" }, "letme": { "capability": "https://letme.dev/assistant.memory", "tool": "https://letme.dev/skydive" }, "area": "frameworks", "unitPrices": [ { "item": "Starter plan", "unit": "month", "usd": 20, "note": "Flat per workspace, unlimited seats, US$20 of usage credit a month. Yearly US$240 with US$264 of credit." }, { "item": "Team plan", "unit": "month", "usd": 200, "note": "Flat per workspace, unlimited seats, US$200 of usage credit a month. Yearly US$2,400 with US$2,640 of credit." }, { "item": "Dedicated iMessage line", "unit": "month", "usd": 100, "note": "Per agent, an add-on that grants no usage credit. A shared pool line is free." } ], "provenance": { "legalEntity": "Create, Inc.", "domain": "skydive.com", "domainRegistered": "1993-05-04", "endpointOnVendorDomain": true, "terms": "https://www.skydive.com/terms", "privacy": "https://www.skydive.com/privacy", "statusPage": "https://status.skydive.com", "changelog": "https://www.skydive.com/docs/changelog", "securityTxt": "valid", "checked": "2026-10-31", "notes": [ "skydive.com was registered 4 May 1993 and last changed 2 July 2026 (Amazon Registrar); getskydive.com was registered 21 May 2026 (Realtime Register) and redirects to www.skydive.com (https://rdap.verisign.com/com/v1/domain/skydive.com).", "The DPA (https://www.skydive.com/dpa, last updated 29 July 2026) applies only to customers with an executed Order Form, and gives privacy@skydive.com and security@skydive.com as contacts.", "The privacy policy names subprocessors including E2B, Vercel, Anthropic, OpenAI, Google, xAI, OpenRouter, Vercel AI Gateway, Exa, Pierre, AWS, Cloudflare, Slack, AgentMail, Linq, Resend, Segment, PostHog, Sentry, Stripe, Metronome and Intercom, and points to skydive.com/subprocessors.", "robots.txt on www.skydive.com allows all; the docs robots.txt sends `Content-Signal: ai-train=yes, search=yes, ai-input=yes`. api.skydive.com/robots.txt returns 404.", "The home page and legal pages render client-side; their text was read from https://www.skydive.com/assets/main-MHOpsky7.js." ], "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/skydive.json", "live": { "slug": "skydive", "probe": { "target": "https://api.skydive.com/v1", "method": "get", "lastAt": "2026-10-31T04:40:46.228598891Z", "lastOk": true, "lastStatus": 404, "lastMs": 322, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 331, "p95ms24h": 454, "samples24h": 26, "samples30d": 26, "days": [ { "date": "2026-10-31", "probes": 26, "ok": 26 } ] }, "vendorStatus": { "page": "https://status.skydive.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-31T04:36:12.356112019Z" }, "updatedAt": "2026-10-31T04:40:46.228598891Z" } }, "facts": [ { "a": "Agent harness", "b": "Platform", "name": "Kind" }, { "a": "AgentScope", "b": "Create, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.skydive.com/v1", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Closed service under the Skydive Terms of Service (Create, Inc.), effective 29 July 2026. The skydive-cli npm package is published under the MIT licence.", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-11", "b": "2026-08-26", "name": "Last release" }, { "a": "no document linked", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "36k stars", "b": "5.5k npm/wk", "name": "Popularity" }, { "a": "2.8/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "QwenPaw scores 62.4 (B) on agent readiness against Skydive's 52.1 (D), and leads in 5 of 7 scored categories. Skydive leads on schema \u0026 documentation and transparency \u0026 trust.", "question": "Which is better for AI agents, QwenPaw or Skydive?" }, { "answer": "QwenPaw is open source (Apache-2.0). No open-source release is listed for Skydive.", "question": "Are QwenPaw and Skydive open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 41", "Agent ergonomics, 67 against 59", "Payments \u0026 pricing, 60 against 35", "Maintenance \u0026 community, 73 against 56" ], "also": [ "No key needed to call it", "Runs on your own machine", "Open source" ], "goodFor": "One person who wants an assistant on Chinese and Western chat apps with scheduled digests, a consumer mailbox and file-based memory, on their own machine and with a model of their choice.", "slug": "qwenpaw", "watchFor": "Usage data is on by default, `qwenpaw init --defaults` accepts it without a prompt, and the opt-out variable is absent from the README and docs" }, { "aheadOn": [ "Schema \u0026 documentation, 81 against 68", "Transparency \u0026 trust, 75 against 58" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "A person or team who wants hosted agents with their own cloud computers, memory and connected apps, reachable in Slack, email, text and a CLI, and who can drive them from scripts through the CLI.", "slug": "skydive", "watchFor": "The API has no operation for sending an agent a task. That runs through the CLI's `chat -p`, outside the OpenAPI contract." } ], "job": { "capability": "assistant.proactive", "name": "Proactive personal assistants" }, "others": [ { "json": "https://www.anchorterminal.com/compare/asaply-vs-qwenpaw.json", "title": "asaply vs QwenPaw", "url": "https://www.anchorterminal.com/compare/asaply-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/asaply-vs-skydive.json", "title": "asaply vs Skydive", "url": "https://www.anchorterminal.com/compare/asaply-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/asmi-vs-qwenpaw.json", "title": "Asmi vs QwenPaw", "url": "https://www.anchorterminal.com/compare/asmi-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/asmi-vs-skydive.json", "title": "Asmi vs Skydive", "url": "https://www.anchorterminal.com/compare/asmi-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/boba-vs-qwenpaw.json", "title": "Boba vs QwenPaw", "url": "https://www.anchorterminal.com/compare/boba-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/boba-vs-skydive.json", "title": "Boba vs Skydive", "url": "https://www.anchorterminal.com/compare/boba-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/brea-vs-qwenpaw.json", "title": "Brea vs QwenPaw", "url": "https://www.anchorterminal.com/compare/brea-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/brea-vs-skydive.json", "title": "Brea vs Skydive", "url": "https://www.anchorterminal.com/compare/brea-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/del-vs-qwenpaw.json", "title": "Del vs QwenPaw", "url": "https://www.anchorterminal.com/compare/del-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/del-vs-skydive.json", "title": "Del vs Skydive", "url": "https://www.anchorterminal.com/compare/del-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/hirealpha-vs-qwenpaw.json", "title": "HireAlpha vs QwenPaw", "url": "https://www.anchorterminal.com/compare/hirealpha-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/hirealpha-vs-skydive.json", "title": "HireAlpha vs Skydive", "url": "https://www.anchorterminal.com/compare/hirealpha-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/openinstinct-vs-qwenpaw.json", "title": "OpenInstinct vs QwenPaw", "url": "https://www.anchorterminal.com/compare/openinstinct-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/openinstinct-vs-skydive.json", "title": "OpenInstinct vs Skydive", "url": "https://www.anchorterminal.com/compare/openinstinct-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/orbits-vs-qwenpaw.json", "title": "Orbits vs QwenPaw", "url": "https://www.anchorterminal.com/compare/orbits-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/orbits-vs-skydive.json", "title": "Orbits vs Skydive", "url": "https://www.anchorterminal.com/compare/orbits-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/orchid-ai-vs-qwenpaw.json", "title": "Orchid vs QwenPaw", "url": "https://www.anchorterminal.com/compare/orchid-ai-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/orchid-ai-vs-skydive.json", "title": "Orchid vs Skydive", "url": "https://www.anchorterminal.com/compare/orchid-ai-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-szn.json", "title": "QwenPaw vs szn", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-szn" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-tab-bot.json", "title": "QwenPaw vs Tab", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-tab-bot" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-zapia.json", "title": "QwenPaw vs Zapia", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-zapia" }, { "json": "https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw.json", "title": "AstrBot vs QwenPaw", "url": "https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/astrbot-vs-skydive.json", "title": "AstrBot vs Skydive", "url": "https://www.anchorterminal.com/compare/astrbot-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/boski-vs-qwenpaw.json", "title": "Boski vs QwenPaw", "url": "https://www.anchorterminal.com/compare/boski-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/boski-vs-skydive.json", "title": "Boski vs Skydive", "url": "https://www.anchorterminal.com/compare/boski-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/caddy-app-vs-qwenpaw.json", "title": "Caddy vs QwenPaw", "url": "https://www.anchorterminal.com/compare/caddy-app-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/caddy-app-vs-skydive.json", "title": "Caddy vs Skydive", "url": "https://www.anchorterminal.com/compare/caddy-app-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/claude-duet-vs-qwenpaw.json", "title": "Claude Duet vs QwenPaw", "url": "https://www.anchorterminal.com/compare/claude-duet-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/claude-duet-vs-skydive.json", "title": "Claude Duet vs Skydive", "url": "https://www.anchorterminal.com/compare/claude-duet-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.json", "title": "CowAgent vs QwenPaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-skydive.json", "title": "CowAgent vs Skydive", "url": "https://www.anchorterminal.com/compare/cowagent-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/folk-nozomio-vs-qwenpaw.json", "title": "folk vs QwenPaw", "url": "https://www.anchorterminal.com/compare/folk-nozomio-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/folk-nozomio-vs-skydive.json", "title": "folk vs Skydive", "url": "https://www.anchorterminal.com/compare/folk-nozomio-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-qwenpaw.json", "title": "GAIA vs QwenPaw", "url": "https://www.anchorterminal.com/compare/gaia-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-skydive.json", "title": "GAIA vs Skydive", "url": "https://www.anchorterminal.com/compare/gaia-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.json", "title": "Gemini Spark vs QwenPaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-skydive.json", "title": "Gemini Spark vs Skydive", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.json", "title": "Grok Bot vs QwenPaw", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-skydive.json", "title": "Grok Bot vs Skydive", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-qwenpaw.json", "title": "Haven vs QwenPaw", "url": "https://www.anchorterminal.com/compare/haven-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-skydive.json", "title": "Haven vs Skydive", "url": "https://www.anchorterminal.com/compare/haven-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.json", "title": "Hermes Agent vs QwenPaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-skydive.json", "title": "Hermes Agent vs Skydive", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/instinct-vs-qwenpaw.json", "title": "Instinct vs QwenPaw", "url": "https://www.anchorterminal.com/compare/instinct-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/instinct-vs-skydive.json", "title": "Instinct vs Skydive", "url": "https://www.anchorterminal.com/compare/instinct-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.json", "title": "IronClaw vs QwenPaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-skydive.json", "title": "IronClaw vs Skydive", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/leon-vs-qwenpaw.json", "title": "Leon vs QwenPaw", "url": "https://www.anchorterminal.com/compare/leon-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/leon-vs-skydive.json", "title": "Leon vs Skydive", "url": "https://www.anchorterminal.com/compare/leon-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/lindy-vs-qwenpaw.json", "title": "Lindy vs QwenPaw", "url": "https://www.anchorterminal.com/compare/lindy-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/lindy-vs-skydive.json", "title": "Lindy vs Skydive", "url": "https://www.anchorterminal.com/compare/lindy-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw.json", "title": "nanobot vs QwenPaw", "url": "https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/nanobot-vs-skydive.json", "title": "nanobot vs Skydive", "url": "https://www.anchorterminal.com/compare/nanobot-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.json", "title": "NanoClaw vs QwenPaw", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-skydive.json", "title": "NanoClaw vs Skydive", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/openai-dots-vs-qwenpaw.json", "title": "Dots vs QwenPaw", "url": "https://www.anchorterminal.com/compare/openai-dots-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/openai-dots-vs-skydive.json", "title": "Dots vs Skydive", "url": "https://www.anchorterminal.com/compare/openai-dots-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.json", "title": "OpenClaw vs QwenPaw", "url": "https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/openclaw-vs-skydive.json", "title": "OpenClaw vs Skydive", "url": "https://www.anchorterminal.com/compare/openclaw-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/openduet-vs-qwenpaw.json", "title": "OpenDuet vs QwenPaw", "url": "https://www.anchorterminal.com/compare/openduet-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/openduet-vs-skydive.json", "title": "OpenDuet vs Skydive", "url": "https://www.anchorterminal.com/compare/openduet-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/picoclaw-vs-qwenpaw.json", "title": "PicoClaw vs QwenPaw", "url": "https://www.anchorterminal.com/compare/picoclaw-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/picoclaw-vs-skydive.json", "title": "PicoClaw vs Skydive", "url": "https://www.anchorterminal.com/compare/picoclaw-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/poke-vs-qwenpaw.json", "title": "Poke vs QwenPaw", "url": "https://www.anchorterminal.com/compare/poke-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/poke-vs-skydive.json", "title": "Poke vs Skydive", "url": "https://www.anchorterminal.com/compare/poke-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-tasker-ai.json", "title": "QwenPaw vs Tasker AI", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-tasker-ai" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-town.json", "title": "QwenPaw vs Town", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-town" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.json", "title": "QwenPaw vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-zo-computer.json", "title": "QwenPaw vs Zo Computer", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-zo-computer" }, { "json": "https://www.anchorterminal.com/compare/atticus-vs-qwenpaw.json", "title": "Atticus vs QwenPaw", "url": "https://www.anchorterminal.com/compare/atticus-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/atticus-vs-skydive.json", "title": "Atticus vs Skydive", "url": "https://www.anchorterminal.com/compare/atticus-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/deeptutor-vs-qwenpaw.json", "title": "DeepTutor vs QwenPaw", "url": "https://www.anchorterminal.com/compare/deeptutor-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/deeptutor-vs-skydive.json", "title": "DeepTutor vs Skydive", "url": "https://www.anchorterminal.com/compare/deeptutor-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/hark-pro-vs-qwenpaw.json", "title": "Hark Pro vs QwenPaw", "url": "https://www.anchorterminal.com/compare/hark-pro-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/hark-pro-vs-skydive.json", "title": "Hark Pro vs Skydive", "url": "https://www.anchorterminal.com/compare/hark-pro-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-qwenpaw.json", "title": "LearnHarness vs QwenPaw", "url": "https://www.anchorterminal.com/compare/learnharness-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-skydive.json", "title": "LearnHarness vs Skydive", "url": "https://www.anchorterminal.com/compare/learnharness-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.json", "title": "QwenPaw vs Talorys", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-szn.json", "title": "Skydive vs szn", "url": "https://www.anchorterminal.com/compare/skydive-vs-szn" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-tab-bot.json", "title": "Skydive vs Tab", "url": "https://www.anchorterminal.com/compare/skydive-vs-tab-bot" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-talorys.json", "title": "Skydive vs Talorys", "url": "https://www.anchorterminal.com/compare/skydive-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-tasker-ai.json", "title": "Skydive vs Tasker AI", "url": "https://www.anchorterminal.com/compare/skydive-vs-tasker-ai" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-tomo.json", "title": "Skydive vs Tomo", "url": "https://www.anchorterminal.com/compare/skydive-vs-tomo" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-town.json", "title": "Skydive vs Town", "url": "https://www.anchorterminal.com/compare/skydive-vs-town" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-wajo.json", "title": "Skydive vs Wajo (Fo)", "url": "https://www.anchorterminal.com/compare/skydive-vs-wajo" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-zapia.json", "title": "Skydive vs Zapia", "url": "https://www.anchorterminal.com/compare/skydive-vs-zapia" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-zeroclaw.json", "title": "Skydive vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/skydive-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/skydive-vs-zo-computer.json", "title": "Skydive vs Zo Computer", "url": "https://www.anchorterminal.com/compare/skydive-vs-zo-computer" }, { "json": "https://www.anchorterminal.com/compare/lobby-os-vs-qwenpaw.json", "title": "Lobby vs QwenPaw", "url": "https://www.anchorterminal.com/compare/lobby-os-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/lobby-os-vs-skydive.json", "title": "Lobby vs Skydive", "url": "https://www.anchorterminal.com/compare/lobby-os-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/natura-vs-qwenpaw.json", "title": "Natura tinyNature vs QwenPaw", "url": "https://www.anchorterminal.com/compare/natura-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/natura-vs-skydive.json", "title": "Natura tinyNature vs Skydive", "url": "https://www.anchorterminal.com/compare/natura-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/pally-vs-qwenpaw.json", "title": "Pally vs QwenPaw", "url": "https://www.anchorterminal.com/compare/pally-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/pally-vs-skydive.json", "title": "Pally vs Skydive", "url": "https://www.anchorterminal.com/compare/pally-vs-skydive" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-tomo.json", "title": "QwenPaw vs Tomo", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-tomo" }, { "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-wajo.json", "title": "QwenPaw vs Wajo (Fo)", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-wajo" } ], "scores": [ { "by": 29, "edge": "qwenpaw", "key": "reliability", "name": "Reliability", "qwenpaw": 70, "skydive": 41, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 13, "edge": "skydive", "key": "schema", "name": "Schema \u0026 documentation", "qwenpaw": 68, "skydive": 81, "weight": 13 }, { "by": 8, "edge": "qwenpaw", "key": "ergonomics", "name": "Agent ergonomics", "qwenpaw": 67, "skydive": 59, "weight": 13 }, { "by": 1, "edge": "qwenpaw", "key": "security", "name": "Security \u0026 auth", "qwenpaw": 60, "skydive": 59, "weight": 14 }, { "by": 25, "edge": "qwenpaw", "key": "payments", "name": "Payments \u0026 pricing", "qwenpaw": 60, "skydive": 35, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 17, "edge": "qwenpaw", "key": "maintenance", "name": "Maintenance \u0026 community", "qwenpaw": 73, "skydive": 56, "weight": 7 }, { "by": 17, "edge": "skydive", "key": "transparency", "name": "Transparency \u0026 trust", "qwenpaw": 58, "skydive": 75, "weight": 7 } ], "summary": "QwenPaw scores 62.4 (B) on agent readiness against Skydive's 52.1 (D), and leads in 5 of 7 scored categories. Skydive leads on schema \u0026 documentation and transparency \u0026 trust. Both do proactive personal assistants.", "tutorials": [], "verdicts": { "qwenpaw": "Mail tools ask for approval by default, automatic mail handling may not delete permanently, and the security docs list what each sandbox backend fails to enforce. Usage data is sent by default, the default approval level passes every tool call no rule flags, and no privacy policy or security advisory is published.", "skydive": "Skydive publishes an OpenAPI 3.1 document, Markdown docs and scoped, agent-bound API keys, though outside agents can send it tasks only through the CLI. Its status page records several major incidents, including a 25-hour Agent Hosting outage, and its home and pricing pages say data is never used for training while the privacy policy turns training on by default." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/qwenpaw-vs-skydive", "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-skydive.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/qwenpaw-vs-skydive.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/qwenpaw-vs-skydive.min.md" }, "markdown": "QwenPaw scores 62.4 (B) on agent readiness against Skydive's 52.1 (D), and leads in 5 of 7 scored categories. Skydive leads on schema \u0026 documentation and transparency \u0026 trust. Both do proactive personal assistants.\n\n- QwenPaw: grade B, 62.4/100, rank #508 of 1244. Markdown https://www.anchorterminal.com/tools/qwenpaw.md · JSON https://www.anchorterminal.com/api/v1/tools/qwenpaw.json\n- Skydive: grade D, 52.1/100, rank #899 of 1244. Markdown https://www.anchorterminal.com/tools/skydive.md · JSON https://www.anchorterminal.com/api/v1/tools/skydive.json\n- Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 1245 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md\n\n## Which one, for what\n\n### QwenPaw (B)\n\nGood for: One person who wants an assistant on Chinese and Western chat apps with scheduled digests, a consumer mailbox and file-based memory, on their own machine and with a model of their choice.\n\nAhead on:\n- Reliability, 70 against 41\n- Agent ergonomics, 67 against 59\n- Payments \u0026 pricing, 60 against 35\n- Maintenance \u0026 community, 73 against 56\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- Open source\n\nWatch for: Usage data is on by default, `qwenpaw init --defaults` accepts it without a prompt, and the opt-out variable is absent from the README and docs\n\n### Skydive (D)\n\nGood for: A person or team who wants hosted agents with their own cloud computers, memory and connected apps, reachable in Slack, email, text and a CLI, and who can drive them from scripts through the CLI.\n\nAhead on:\n- Schema \u0026 documentation, 81 against 68\n- Transparency \u0026 trust, 75 against 58\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: The API has no operation for sending an agent a task. That runs through the CLI's `chat -p`, outside the OpenAPI contract.\n\n\n## Score by category\n\n| Category | Weight | QwenPaw | Skydive | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 41 | QwenPaw +29 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 68 | 81 | Skydive +13 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 59 | QwenPaw +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 59 | QwenPaw +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 35 | QwenPaw +25 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 73 | 56 | QwenPaw +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 58 | 75 | Skydive +17 |\n| Negative events | ≤15 | -3 | -5 | |\n| **Total** | | **62.4 · B** | **52.1 · D** | |\n\n## Facts side by side\n\n| Fact | QwenPaw | Skydive |\n| --- | --- | --- |\n| Kind | Agent harness | Platform |\n| Vendor | AgentScope | Create, Inc. |\n| Hosted endpoint | no (local only) | `https://api.skydive.com/v1` |\n| Transports | HTTP, stdio | HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 | Closed service under the Skydive Terms of Service (Create, Inc.), effective 29 July 2026. The skydive-cli npm package is published under the MIT licence. |\n| Read-only variant documented | no | yes |\n| llms.txt | no | yes |\n| Last release | 2026-09-11 | 2026-08-26 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | | couldn't be read |\n| Terms restrict automated access | | couldn't be read |\n| Terms restrict benchmarking | | couldn't be read |\n| Terms or service can change without notice | | couldn't be read |\n| Arbitration or class-action waiver | | couldn't be read |\n| Popularity | 36k stars | 5.5k npm/wk |\n| Agent reviews | 2.8/5 (4) | none |\n\n## Verdicts\n\n**QwenPaw.** Mail tools ask for approval by default, automatic mail handling may not delete permanently, and the security docs list what each sandbox backend fails to enforce. Usage data is sent by default, the default approval level passes every tool call no rule flags, and no privacy policy or security advisory is published.\n\n**Skydive.** Skydive publishes an OpenAPI 3.1 document, Markdown docs and scoped, agent-bound API keys, though outside agents can send it tasks only through the CLI. Its status page records several major incidents, including a 25-hour Agent Hosting outage, and its home and pricing pages say data is never used for training while the privacy policy turns training on by default.\n\n## Before you call either\n\n### QwenPaw\n\n1. Set `QWENPAW_TELEMETRY_DISABLED=true` before `qwenpaw init --defaults` or `qwenpaw app`. Both send usage data without asking\n2. Set `approval_level` to `STRICT` or `SMART` in `agent.json`. The default `AUTO` runs every tool call no guard rule flags\n3. Set `dm_policy` and `group_policy` to `allowlist` with `allow_from` on each channel. Both default to `open`\n4. Set `QWENPAW_AUTH_ENABLED=true` before binding beyond 127.0.0.1. Requests from localhost skip login even then\n5. Keep mail tools on `ask` for `send_message`, `delete_message` and `delete_thread`, and turn on Mail Access Control with automatic handling\n\n### Skydive\n\n1. Send tasks with `skydive chat -p \"...\" --agent \u003cid\u003e --json` and pass `--conversation \u003cid\u003e` from the JSON to keep context. The REST API can't send a task.\n2. Don't retry `chat -p` or a create blindly after a timeout. There's no idempotency key, so list agents or keys before retrying.\n3. Ask the owner for an agent-bound `use` key when you only need to read. Account-level `edit` keys can create agents and mint keys.\n4. Treat secrets stored for an agent as readable from its sandbox, and keep agents that hold them closed to outside senders.\n5. Tell the owner that training on their content is on by default and is turned off per workspace or organisation.\n\n## Questions\n\n### Which is better for AI agents, QwenPaw or Skydive?\n\nQwenPaw scores 62.4 (B) on agent readiness against Skydive's 52.1 (D), and leads in 5 of 7 scored categories. Skydive leads on schema \u0026 documentation and transparency \u0026 trust.\n\n### Are QwenPaw and Skydive open source?\n\nQwenPaw is open source (Apache-2.0). No open-source release is listed for Skydive.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/qwenpaw-vs-skydive.json, and with the fewest tokens: https://www.anchorterminal.com/compare/qwenpaw-vs-skydive.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"qwenpaw\", \"b\": \"skydive\"}`. From a terminal: `anchor compare qwenpaw skydive`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/qwenpaw.json and https://www.anchorterminal.com/api/v1/tools/skydive.json\n\n## Other comparisons with QwenPaw or Skydive\n\n- [asaply vs QwenPaw](https://www.anchorterminal.com/compare/asaply-vs-qwenpaw.md)\n- [asaply vs Skydive](https://www.anchorterminal.com/compare/asaply-vs-skydive.md)\n- [Asmi vs QwenPaw](https://www.anchorterminal.com/compare/asmi-vs-qwenpaw.md)\n- [Asmi vs Skydive](https://www.anchorterminal.com/compare/asmi-vs-skydive.md)\n- [Boba vs QwenPaw](https://www.anchorterminal.com/compare/boba-vs-qwenpaw.md)\n- [Boba vs Skydive](https://www.anchorterminal.com/compare/boba-vs-skydive.md)\n- [Brea vs QwenPaw](https://www.anchorterminal.com/compare/brea-vs-qwenpaw.md)\n- [Brea vs Skydive](https://www.anchorterminal.com/compare/brea-vs-skydive.md)\n- [Del vs QwenPaw](https://www.anchorterminal.com/compare/del-vs-qwenpaw.md)\n- [Del vs Skydive](https://www.anchorterminal.com/compare/del-vs-skydive.md)\n- [HireAlpha vs QwenPaw](https://www.anchorterminal.com/compare/hirealpha-vs-qwenpaw.md)\n- [HireAlpha vs Skydive](https://www.anchorterminal.com/compare/hirealpha-vs-skydive.md)\n- [OpenInstinct vs QwenPaw](https://www.anchorterminal.com/compare/openinstinct-vs-qwenpaw.md)\n- [OpenInstinct vs Skydive](https://www.anchorterminal.com/compare/openinstinct-vs-skydive.md)\n- [Orbits vs QwenPaw](https://www.anchorterminal.com/compare/orbits-vs-qwenpaw.md)\n- [Orbits vs Skydive](https://www.anchorterminal.com/compare/orbits-vs-skydive.md)\n- [Orchid vs QwenPaw](https://www.anchorterminal.com/compare/orchid-ai-vs-qwenpaw.md)\n- [Orchid vs Skydive](https://www.anchorterminal.com/compare/orchid-ai-vs-skydive.md)\n- [QwenPaw vs szn](https://www.anchorterminal.com/compare/qwenpaw-vs-szn.md)\n- [QwenPaw vs Tab](https://www.anchorterminal.com/compare/qwenpaw-vs-tab-bot.md)\n- [QwenPaw vs Zapia](https://www.anchorterminal.com/compare/qwenpaw-vs-zapia.md)\n- [AstrBot vs QwenPaw](https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw.md)\n- [AstrBot vs Skydive](https://www.anchorterminal.com/compare/astrbot-vs-skydive.md)\n- [Boski vs QwenPaw](https://www.anchorterminal.com/compare/boski-vs-qwenpaw.md)\n- [Boski vs Skydive](https://www.anchorterminal.com/compare/boski-vs-skydive.md)\n- [Caddy vs QwenPaw](https://www.anchorterminal.com/compare/caddy-app-vs-qwenpaw.md)\n- [Caddy vs Skydive](https://www.anchorterminal.com/compare/caddy-app-vs-skydive.md)\n- [Claude Duet vs QwenPaw](https://www.anchorterminal.com/compare/claude-duet-vs-qwenpaw.md)\n- [Claude Duet vs Skydive](https://www.anchorterminal.com/compare/claude-duet-vs-skydive.md)\n- [CowAgent vs QwenPaw](https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.md)\n- [CowAgent vs Skydive](https://www.anchorterminal.com/compare/cowagent-vs-skydive.md)\n- [folk vs QwenPaw](https://www.anchorterminal.com/compare/folk-nozomio-vs-qwenpaw.md)\n- [folk vs Skydive](https://www.anchorterminal.com/compare/folk-nozomio-vs-skydive.md)\n- [GAIA vs QwenPaw](https://www.anchorterminal.com/compare/gaia-vs-qwenpaw.md)\n- [GAIA vs Skydive](https://www.anchorterminal.com/compare/gaia-vs-skydive.md)\n- [Gemini Spark vs QwenPaw](https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.md)\n- [Gemini Spark vs Skydive](https://www.anchorterminal.com/compare/gemini-spark-vs-skydive.md)\n- [Grok Bot vs QwenPaw](https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.md)\n- [Grok Bot vs Skydive](https://www.anchorterminal.com/compare/grok-bot-vs-skydive.md)\n- [Haven vs QwenPaw](https://www.anchorterminal.com/compare/haven-vs-qwenpaw.md)\n- [Haven vs Skydive](https://www.anchorterminal.com/compare/haven-vs-skydive.md)\n- [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md)\n- [Hermes Agent vs Skydive](https://www.anchorterminal.com/compare/hermes-agent-vs-skydive.md)\n- [Instinct vs QwenPaw](https://www.anchorterminal.com/compare/instinct-vs-qwenpaw.md)\n- [Instinct vs Skydive](https://www.anchorterminal.com/compare/instinct-vs-skydive.md)\n- [IronClaw vs QwenPaw](https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.md)\n- [IronClaw vs Skydive](https://www.anchorterminal.com/compare/ironclaw-vs-skydive.md)\n- [Leon vs QwenPaw](https://www.anchorterminal.com/compare/leon-vs-qwenpaw.md)\n- [Leon vs Skydive](https://www.anchorterminal.com/compare/leon-vs-skydive.md)\n- [Lindy vs QwenPaw](https://www.anchorterminal.com/compare/lindy-vs-qwenpaw.md)\n- [Lindy vs Skydive](https://www.anchorterminal.com/compare/lindy-vs-skydive.md)\n- [nanobot vs QwenPaw](https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw.md)\n- [nanobot vs Skydive](https://www.anchorterminal.com/compare/nanobot-vs-skydive.md)\n- [NanoClaw vs QwenPaw](https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.md)\n- [NanoClaw vs Skydive](https://www.anchorterminal.com/compare/nanoclaw-vs-skydive.md)\n- [Dots vs QwenPaw](https://www.anchorterminal.com/compare/openai-dots-vs-qwenpaw.md)\n- [Dots vs Skydive](https://www.anchorterminal.com/compare/openai-dots-vs-skydive.md)\n- [OpenClaw vs QwenPaw](https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.md)\n- [OpenClaw vs Skydive](https://www.anchorterminal.com/compare/openclaw-vs-skydive.md)\n- [OpenDuet vs QwenPaw](https://www.anchorterminal.com/compare/openduet-vs-qwenpaw.md)\n- [OpenDuet vs Skydive](https://www.anchorterminal.com/compare/openduet-vs-skydive.md)\n- [PicoClaw vs QwenPaw](https://www.anchorterminal.com/compare/picoclaw-vs-qwenpaw.md)\n- [PicoClaw vs Skydive](https://www.anchorterminal.com/compare/picoclaw-vs-skydive.md)\n- [Poke vs QwenPaw](https://www.anchorterminal.com/compare/poke-vs-qwenpaw.md)\n- [Poke vs Skydive](https://www.anchorterminal.com/compare/poke-vs-skydive.md)\n- [QwenPaw vs Tasker AI](https://www.anchorterminal.com/compare/qwenpaw-vs-tasker-ai.md)\n- [QwenPaw vs Town](https://www.anchorterminal.com/compare/qwenpaw-vs-town.md)\n- [QwenPaw vs ZeroClaw](https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.md)\n- [QwenPaw vs Zo Computer](https://www.anchorterminal.com/compare/qwenpaw-vs-zo-computer.md)\n- [Atticus vs QwenPaw](https://www.anchorterminal.com/compare/atticus-vs-qwenpaw.md)\n- [Atticus vs Skydive](https://www.anchorterminal.com/compare/atticus-vs-skydive.md)\n- [DeepTutor vs QwenPaw](https://www.anchorterminal.com/compare/deeptutor-vs-qwenpaw.md)\n- [DeepTutor vs Skydive](https://www.anchorterminal.com/compare/deeptutor-vs-skydive.md)\n- [Hark Pro vs QwenPaw](https://www.anchorterminal.com/compare/hark-pro-vs-qwenpaw.md)\n- [Hark Pro vs Skydive](https://www.anchorterminal.com/compare/hark-pro-vs-skydive.md)\n- [LearnHarness vs QwenPaw](https://www.anchorterminal.com/compare/learnharness-vs-qwenpaw.md)\n- [LearnHarness vs Skydive](https://www.anchorterminal.com/compare/learnharness-vs-skydive.md)\n- [QwenPaw vs Talorys](https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.md)\n- [Skydive vs szn](https://www.anchorterminal.com/compare/skydive-vs-szn.md)\n- [Skydive vs Tab](https://www.anchorterminal.com/compare/skydive-vs-tab-bot.md)\n- [Skydive vs Talorys](https://www.anchorterminal.com/compare/skydive-vs-talorys.md)\n- [Skydive vs Tasker AI](https://www.anchorterminal.com/compare/skydive-vs-tasker-ai.md)\n- [Skydive vs Tomo](https://www.anchorterminal.com/compare/skydive-vs-tomo.md)\n- [Skydive vs Town](https://www.anchorterminal.com/compare/skydive-vs-town.md)\n- [Skydive vs Wajo (Fo)](https://www.anchorterminal.com/compare/skydive-vs-wajo.md)\n- [Skydive vs Zapia](https://www.anchorterminal.com/compare/skydive-vs-zapia.md)\n- [Skydive vs ZeroClaw](https://www.anchorterminal.com/compare/skydive-vs-zeroclaw.md)\n- [Skydive vs Zo Computer](https://www.anchorterminal.com/compare/skydive-vs-zo-computer.md)\n- [Lobby vs QwenPaw](https://www.anchorterminal.com/compare/lobby-os-vs-qwenpaw.md)\n- [Lobby vs Skydive](https://www.anchorterminal.com/compare/lobby-os-vs-skydive.md)\n- [Natura tinyNature vs QwenPaw](https://www.anchorterminal.com/compare/natura-vs-qwenpaw.md)\n- [Natura tinyNature vs Skydive](https://www.anchorterminal.com/compare/natura-vs-skydive.md)\n- [Pally vs QwenPaw](https://www.anchorterminal.com/compare/pally-vs-qwenpaw.md)\n- [Pally vs Skydive](https://www.anchorterminal.com/compare/pally-vs-skydive.md)\n- [QwenPaw vs Tomo](https://www.anchorterminal.com/compare/qwenpaw-vs-tomo.md)\n- [QwenPaw vs Wajo (Fo)](https://www.anchorterminal.com/compare/qwenpaw-vs-wajo.md)\n\n## Disclosure\n\n- Skydive competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.\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": "2026-10-31", "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": "QwenPaw vs Skydive", "url": "" } ], "description": "QwenPaw scores 62.4 (B) to Skydive's 52.1 (D) for proactive personal assistants. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "QwenPaw B 62.4", "Skydive D 52.1", "scores" ], "h1": "QwenPaw vs Skydive", "image": "https://www.anchorterminal.com/assets/og/compare-qwenpaw-vs-skydive.png", "path": "/compare/qwenpaw-vs-skydive", "published": "2026-10-01", "section": "tools", "title": "QwenPaw vs Skydive for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-31", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-skydive" }, "tokens": { "markdown": 4050, "slim": 780 }, "version": 1 }