{ "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": 62.2, "grade": "B", "agentReady": false, "rank": 454, "ranked": true, "rankOf": 993, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 73, "payments": 60, "reliability": 70, "schema": 68, "security": 60, "transparency": 56 }, "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": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.2 } ], "editorialScores": { "ergonomics": 67, "maintenance": 73, "payments": 60, "reliability": 70, "schema": 68, "security": 60, "transparency": 58 }, "provenanceScore": 53 }, "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": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/qwenpaw.json", "live": { "slug": "qwenpaw", "versions": [ { "registry": "github", "name": "agentscope-ai/QwenPaw", "version": "v2.2.1", "released": "2026-09-11", "seenAt": "2026-10-12T22:24:57.483839518Z" }, { "registry": "pypi", "name": "qwenpaw", "version": "2.2.1", "released": "2026-09-11", "seenAt": "2026-10-12T22:24:55.482265352Z" } ], "githubStars": 35631, "pypiWeekly": 2631, "pages": [ { "url": "https://qwenpaw.agentscope.io/release-notes", "kind": "changelog", "status": 404, "checkedAt": "2026-10-12T19:57:10.985296131Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-12T22:24:57.483839518Z" } }, "answer": "QwenPaw scores 62.2 (B) on agent readiness against Talorys's 28.9 (F), and leads in 5 of 7 scored categories. Talorys leads on maintenance \u0026 community.", "b": { "slug": "talorys", "name": "Talorys", "vendor": "Roc Yu (rociiu) and contributors", "vendorUrl": "https://github.com/rociiu/talorys", "kind": "platform", "category": "personal-assistants", "summary": "Talorys is an open-source, single-user personal AI assistant that its owner deploys into their own Cloudflare account with one command. It chats, keeps editable memories, and manages tasks, notes, projects, reminders and scheduled routines.", "url": "https://www.anchorterminal.com/tools/talorys", "markdownUrl": "https://www.anchorterminal.com/tools/talorys.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/talorys.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/talorys.json", "repo": "https://github.com/rociiu/talorys", "license": "MIT (Copyright 2026 The Talorys contributors). It runs on the owner's Cloudflare account under Cloudflare's own terms.", "transports": [], "packages": [ { "registry": "npm", "name": "create-talorys" } ], "auth": "mixed", "authNotes": "The installer signs in to Cloudflare through Wrangler's OAuth flow, or uses an API token with Workers Scripts, Pages, Workers AI and Account Settings permissions. The owner password is hashed locally with PBKDF2-SHA256 and stored as a Worker secret. The web app uses an HttpOnly session cookie, and every non-GET request needs an x-talorys-request header and a same-origin Origin (https://github.com/rociiu/talorys/blob/main/docs/security.md). There is no API key, MCP server or signup.", "pricing": "free", "pricingNotes": "Free and MIT-licensed, designed to fit the Cloudflare Workers Free plan, including a daily Workers AI allocation. On a paid Cloudflare plan, use beyond the included amounts is billed by Cloudflare (https://github.com/rociiu/talorys#7-what-is-free-and-what-may-cost-money).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol. Talorys has no billing of its own, checked 12 October 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 978, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://github.com/rociiu/talorys/tree/main/docs", "capabilities": [ "assistant.memory", "assistant.self-hosted", "memory.user", "memory.search", "tasks.create", "tasks.update", "notify.in-app" ], "tags": [ "open-source", "self-hosted", "free", "typescript", "cloudflare" ], "lastRelease": "2026-10-12", "graded": true, "disclosure": "Talorys 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": 28.9, "grade": "F", "agentReady": false, "rank": 976, "ranked": true, "rankOf": 993, "categoryRank": 19, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 0, "maintenance": 83, "payments": 60, "reliability": 41, "schema": 0, "security": 8, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": 0, "verdict": "Talorys is an MIT-licensed assistant its owner deploys to their own Cloudflare account, with no telemetry, a documented threat model and code-enforced confirmation for destructive tools. It is two days old at version 0.1.5, has no mail, calendar or payment connections, and no interface for an outside agent.", "bestFor": "A single person who wants a private assistant for memory, tasks, notes and reminders on their own Cloudflare account.", "disclosure": "Talorys 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": [ "MIT licence, and no telemetry, analytics or tracking, stated in the README and confirmed in the code.", "Destructive tools need confirmation in the owner's latest message, enforced in code, and scheduled runs get read-only tools.", "SECURITY.md with private reporting, a 3-business-day acknowledgement target and a threat model.", "Designed to fit Cloudflare's Workers Free plan, with nothing to buy from Talorys." ], "weaknesses": [ "No API key, MCP server or A2A endpoint, and the /api routes need the owner's browser session.", "First released on 10 October 2026 and still pre-1.0 at 0.1.5.", "No changelog or breaking-change notes.", "No mail, calendar, booking, payment or messaging connections in the code." ], "agentNotes": [ "Run `npx create-talorys@latest` with Node.js 22 or later and a Cloudflare login or an API token with Workers, Pages and Workers AI permissions.", "Don't script the /api routes. They need the owner's session cookie and CSRF header and aren't documented for other callers.", "Update with `npx create-talorys@latest update`. Only the latest version gets security fixes." ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 28.9 } ], "editorialScores": { "ergonomics": 0, "maintenance": 83, "payments": 60, "reliability": 41, "schema": 0, "security": 8, "transparency": 77 }, "provenanceScore": 27 }, "connect": { "install": "npx create-talorys@latest # Node.js 22+, signs in to Cloudflare and deploys into your account" }, "letme": { "capability": "https://letme.dev/assistant.memory", "tool": "https://letme.dev/talorys" }, "sameCompany": [ "github-mcp-server", "github-copilot-cli" ], "area": "frameworks", "provenance": { "legalEntity": "", "domain": "github.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/rociiu/talorys/commits/main", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "No company, terms of service or privacy policy. The MIT licence names The Talorys contributors, and Cloudflare's terms and privacy policy cover the hosting.", "Security reports go through GitHub private vulnerability reporting per SECURITY.md. There is no security.txt.", "There is no hosted endpoint. Each install answers on the owner's own pages.dev address.", "GitHub star count was not checked because the GitHub API was not available to us." ], "score": 27 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/talorys.json", "live": { "slug": "talorys", "versions": [ { "registry": "npm", "name": "create-talorys", "version": "0.1.5", "seenAt": "2026-10-12T22:32:28.340613655Z" } ], "githubStars": 892, "npmWeekly": 978, "updatedAt": "2026-10-12T22:32:29.267294141Z" } }, "facts": [ { "a": "Agent harness", "b": "Platform", "name": "Kind" }, { "a": "AgentScope", "b": "Roc Yu (rociiu) and contributors", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT (Copyright 2026 The Talorys contributors). It runs on the owner's Cloudflare account under Cloudflare's own terms.", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-09-11", "b": "2026-10-12", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "36k stars", "b": "978 npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "QwenPaw scores 62.2 (B) on agent readiness against Talorys's 28.9 (F), and leads in 5 of 7 scored categories. Talorys leads on maintenance \u0026 community.", "question": "Which is better for AI agents, QwenPaw or Talorys?" }, { "answer": "Yes. QwenPaw is open source (Apache-2.0). Talorys is open source (MIT (Copyright 2026 The Talorys contributors). It runs on the owner's Cloudflare account under Cloudflare's own terms.).", "question": "Are QwenPaw and Talorys open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 41", "Schema \u0026 documentation, 68 against 0", "Agent ergonomics, 67 against 0", "Security \u0026 auth, 60 against 8" ], "also": [ "No key needed to call it", "Runs on your own machine" ], "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": [ "Maintenance \u0026 community, 83 against 73" ], "also": [ "No incidents deducted, where QwenPaw loses 3 points for them" ], "goodFor": "A single person who wants a private assistant for memory, tasks, notes and reminders on their own Cloudflare account.", "slug": "talorys", "watchFor": "No API key, MCP server or A2A endpoint, and the /api routes need the owner's browser session." } ], "job": { "capability": "assistant.memory", "name": "Assistants that remember you" }, "others": [ { "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/cowagent-vs-qwenpaw.json", "title": "CowAgent vs QwenPaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw" }, { "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/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/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/haven-vs-qwenpaw.json", "title": "Haven vs QwenPaw", "url": "https://www.anchorterminal.com/compare/haven-vs-qwenpaw" }, { "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/instinct-vs-qwenpaw.json", "title": "Instinct vs QwenPaw", "url": "https://www.anchorterminal.com/compare/instinct-vs-qwenpaw" }, { "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/leon-vs-qwenpaw.json", "title": "Leon vs QwenPaw", "url": "https://www.anchorterminal.com/compare/leon-vs-qwenpaw" }, { "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/nanobot-vs-qwenpaw.json", "title": "nanobot vs QwenPaw", "url": "https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw" }, { "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/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/openclaw-vs-qwenpaw.json", "title": "OpenClaw vs QwenPaw", "url": "https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw" }, { "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/poke-vs-qwenpaw.json", "title": "Poke vs QwenPaw", "url": "https://www.anchorterminal.com/compare/poke-vs-qwenpaw" }, { "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/natura-vs-qwenpaw.json", "title": "Natura tinyNature vs QwenPaw", "url": "https://www.anchorterminal.com/compare/natura-vs-qwenpaw" }, { "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/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" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-talorys.json", "title": "CowAgent vs Talorys", "url": "https://www.anchorterminal.com/compare/cowagent-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-talorys.json", "title": "GAIA vs Talorys", "url": "https://www.anchorterminal.com/compare/gaia-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-talorys.json", "title": "Gemini Spark vs Talorys", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-talorys.json", "title": "Grok Bot vs Talorys", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-talorys.json", "title": "Haven vs Talorys", "url": "https://www.anchorterminal.com/compare/haven-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-talorys.json", "title": "Hermes Agent vs Talorys", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/instinct-vs-talorys.json", "title": "Instinct vs Talorys", "url": "https://www.anchorterminal.com/compare/instinct-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-talorys.json", "title": "IronClaw vs Talorys", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/leon-vs-talorys.json", "title": "Leon vs Talorys", "url": "https://www.anchorterminal.com/compare/leon-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/lindy-vs-talorys.json", "title": "Lindy vs Talorys", "url": "https://www.anchorterminal.com/compare/lindy-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/nanobot-vs-talorys.json", "title": "nanobot vs Talorys", "url": "https://www.anchorterminal.com/compare/nanobot-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-talorys.json", "title": "NanoClaw vs Talorys", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/natura-vs-talorys.json", "title": "Natura tinyNature vs Talorys", "url": "https://www.anchorterminal.com/compare/natura-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/openai-dots-vs-talorys.json", "title": "Dots vs Talorys", "url": "https://www.anchorterminal.com/compare/openai-dots-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/openclaw-vs-talorys.json", "title": "OpenClaw vs Talorys", "url": "https://www.anchorterminal.com/compare/openclaw-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/pally-vs-talorys.json", "title": "Pally vs Talorys", "url": "https://www.anchorterminal.com/compare/pally-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/picoclaw-vs-talorys.json", "title": "PicoClaw vs Talorys", "url": "https://www.anchorterminal.com/compare/picoclaw-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/poke-vs-talorys.json", "title": "Poke vs Talorys", "url": "https://www.anchorterminal.com/compare/poke-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/talorys-vs-tomo.json", "title": "Talorys vs Tomo", "url": "https://www.anchorterminal.com/compare/talorys-vs-tomo" }, { "json": "https://www.anchorterminal.com/compare/talorys-vs-wajo.json", "title": "Talorys vs Wajo (Fo)", "url": "https://www.anchorterminal.com/compare/talorys-vs-wajo" }, { "json": "https://www.anchorterminal.com/compare/talorys-vs-zeroclaw.json", "title": "Talorys vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/talorys-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/talorys-vs-zo-computer.json", "title": "Talorys vs Zo Computer", "url": "https://www.anchorterminal.com/compare/talorys-vs-zo-computer" }, { "json": "https://www.anchorterminal.com/compare/astrbot-vs-talorys.json", "title": "AstrBot vs Talorys", "url": "https://www.anchorterminal.com/compare/astrbot-vs-talorys" } ], "scores": [ { "by": 29, "edge": "qwenpaw", "key": "reliability", "name": "Reliability", "qwenpaw": 70, "talorys": 41, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 68, "edge": "qwenpaw", "key": "schema", "name": "Schema \u0026 documentation", "qwenpaw": 68, "talorys": 0, "weight": 13 }, { "by": 67, "edge": "qwenpaw", "key": "ergonomics", "name": "Agent ergonomics", "qwenpaw": 67, "talorys": 0, "weight": 13 }, { "by": 52, "edge": "qwenpaw", "key": "security", "name": "Security \u0026 auth", "qwenpaw": 60, "talorys": 8, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "qwenpaw": 60, "talorys": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 10, "edge": "talorys", "key": "maintenance", "name": "Maintenance \u0026 community", "qwenpaw": 73, "talorys": 83, "weight": 7 }, { "by": 4, "edge": "qwenpaw", "key": "transparency", "name": "Transparency \u0026 trust", "qwenpaw": 56, "talorys": 52, "weight": 7 } ], "summary": "QwenPaw scores 62.2 (B) on agent readiness against Talorys's 28.9 (F), and leads in 5 of 7 scored categories. Talorys leads on maintenance \u0026 community. Both do assistants that remember you.", "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.", "talorys": "Talorys is an MIT-licensed assistant its owner deploys to their own Cloudflare account, with no telemetry, a documented threat model and code-enforced confirmation for destructive tools. It is two days old at version 0.1.5, has no mail, calendar or payment connections, and no interface for an outside agent." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys", "json": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.md", "slim": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.min.md" }, "markdown": "QwenPaw scores 62.2 (B) on agent readiness against Talorys's 28.9 (F), and leads in 5 of 7 scored categories. Talorys leads on maintenance \u0026 community. Both do assistants that remember you.\n\n- QwenPaw: grade B, 62.2/100, rank #454 of 993. Markdown https://www.anchorterminal.com/tools/qwenpaw.md · JSON https://www.anchorterminal.com/api/v1/tools/qwenpaw.json\n- Talorys: grade F, 28.9/100, rank #976 of 993. Markdown https://www.anchorterminal.com/tools/talorys.md · JSON https://www.anchorterminal.com/api/v1/tools/talorys.json\n- Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 314 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- Schema \u0026 documentation, 68 against 0\n- Agent ergonomics, 67 against 0\n- Security \u0026 auth, 60 against 8\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\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### Talorys (F)\n\nGood for: A single person who wants a private assistant for memory, tasks, notes and reminders on their own Cloudflare account.\n\nAhead on:\n- Maintenance \u0026 community, 83 against 73\n\nAlso in its favour:\n- No incidents deducted, where QwenPaw loses 3 points for them\n\nWatch for: No API key, MCP server or A2A endpoint, and the /api routes need the owner's browser session.\n\n\n## Score by category\n\n| Category | Weight | QwenPaw | Talorys | 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 | 0 | QwenPaw +68 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 0 | QwenPaw +67 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 8 | QwenPaw +52 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 73 | 83 | Talorys +10 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 56 | 52 | QwenPaw +4 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **62.2 · B** | **28.9 · F** | |\n\n## Facts side by side\n\n| Fact | QwenPaw | Talorys |\n| --- | --- | --- |\n| Kind | Agent harness | Platform |\n| Vendor | AgentScope | Roc Yu (rociiu) and contributors |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP, stdio | |\n| Auth | None | OAuth or key |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT (Copyright 2026 The Talorys contributors). It runs on the owner's Cloudflare account under Cloudflare's own terms. |\n| Read-only variant documented | no | yes |\n| llms.txt | no | no |\n| Last release | 2026-09-11 | 2026-10-12 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 36k stars | 978 npm/wk |\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**Talorys.** Talorys is an MIT-licensed assistant its owner deploys to their own Cloudflare account, with no telemetry, a documented threat model and code-enforced confirmation for destructive tools. It is two days old at version 0.1.5, has no mail, calendar or payment connections, and no interface for an outside agent.\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### Talorys\n\n1. Run `npx create-talorys@latest` with Node.js 22 or later and a Cloudflare login or an API token with Workers, Pages and Workers AI permissions.\n2. Don't script the /api routes. They need the owner's session cookie and CSRF header and aren't documented for other callers.\n3. Update with `npx create-talorys@latest update`. Only the latest version gets security fixes.\n\n## Questions\n\n### Which is better for AI agents, QwenPaw or Talorys?\n\nQwenPaw scores 62.2 (B) on agent readiness against Talorys's 28.9 (F), and leads in 5 of 7 scored categories. Talorys leads on maintenance \u0026 community.\n\n### Are QwenPaw and Talorys open source?\n\nYes. QwenPaw is open source (Apache-2.0). Talorys is open source (MIT (Copyright 2026 The Talorys contributors). It runs on the owner's Cloudflare account under Cloudflare's own terms.).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.json, and with the fewest tokens: https://www.anchorterminal.com/compare/qwenpaw-vs-talorys.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"qwenpaw\", \"b\": \"talorys\"}`. From a terminal: `anchor compare qwenpaw talorys`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/qwenpaw.json and https://www.anchorterminal.com/api/v1/tools/talorys.json\n\n## Other comparisons with QwenPaw or Talorys\n\n- [AstrBot vs QwenPaw](https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw.md)\n- [CowAgent vs QwenPaw](https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.md)\n- [GAIA vs QwenPaw](https://www.anchorterminal.com/compare/gaia-vs-qwenpaw.md)\n- [Gemini Spark vs QwenPaw](https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.md)\n- [Grok Bot vs QwenPaw](https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.md)\n- [Haven vs QwenPaw](https://www.anchorterminal.com/compare/haven-vs-qwenpaw.md)\n- [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md)\n- [Instinct vs QwenPaw](https://www.anchorterminal.com/compare/instinct-vs-qwenpaw.md)\n- [IronClaw vs QwenPaw](https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.md)\n- [Leon vs QwenPaw](https://www.anchorterminal.com/compare/leon-vs-qwenpaw.md)\n- [Lindy vs QwenPaw](https://www.anchorterminal.com/compare/lindy-vs-qwenpaw.md)\n- [nanobot vs QwenPaw](https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw.md)\n- [NanoClaw vs QwenPaw](https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.md)\n- [Dots vs QwenPaw](https://www.anchorterminal.com/compare/openai-dots-vs-qwenpaw.md)\n- [OpenClaw vs QwenPaw](https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.md)\n- [PicoClaw vs QwenPaw](https://www.anchorterminal.com/compare/picoclaw-vs-qwenpaw.md)\n- [Poke vs QwenPaw](https://www.anchorterminal.com/compare/poke-vs-qwenpaw.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- [Natura tinyNature vs QwenPaw](https://www.anchorterminal.com/compare/natura-vs-qwenpaw.md)\n- [Pally vs QwenPaw](https://www.anchorterminal.com/compare/pally-vs-qwenpaw.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- [CowAgent vs Talorys](https://www.anchorterminal.com/compare/cowagent-vs-talorys.md)\n- [GAIA vs Talorys](https://www.anchorterminal.com/compare/gaia-vs-talorys.md)\n- [Gemini Spark vs Talorys](https://www.anchorterminal.com/compare/gemini-spark-vs-talorys.md)\n- [Grok Bot vs Talorys](https://www.anchorterminal.com/compare/grok-bot-vs-talorys.md)\n- [Haven vs Talorys](https://www.anchorterminal.com/compare/haven-vs-talorys.md)\n- [Hermes Agent vs Talorys](https://www.anchorterminal.com/compare/hermes-agent-vs-talorys.md)\n- [Instinct vs Talorys](https://www.anchorterminal.com/compare/instinct-vs-talorys.md)\n- [IronClaw vs Talorys](https://www.anchorterminal.com/compare/ironclaw-vs-talorys.md)\n- [Leon vs Talorys](https://www.anchorterminal.com/compare/leon-vs-talorys.md)\n- [Lindy vs Talorys](https://www.anchorterminal.com/compare/lindy-vs-talorys.md)\n- [nanobot vs Talorys](https://www.anchorterminal.com/compare/nanobot-vs-talorys.md)\n- [NanoClaw vs Talorys](https://www.anchorterminal.com/compare/nanoclaw-vs-talorys.md)\n- [Natura tinyNature vs Talorys](https://www.anchorterminal.com/compare/natura-vs-talorys.md)\n- [Dots vs Talorys](https://www.anchorterminal.com/compare/openai-dots-vs-talorys.md)\n- [OpenClaw vs Talorys](https://www.anchorterminal.com/compare/openclaw-vs-talorys.md)\n- [Pally vs Talorys](https://www.anchorterminal.com/compare/pally-vs-talorys.md)\n- [PicoClaw vs Talorys](https://www.anchorterminal.com/compare/picoclaw-vs-talorys.md)\n- [Poke vs Talorys](https://www.anchorterminal.com/compare/poke-vs-talorys.md)\n- [Talorys vs Tomo](https://www.anchorterminal.com/compare/talorys-vs-tomo.md)\n- [Talorys vs Wajo (Fo)](https://www.anchorterminal.com/compare/talorys-vs-wajo.md)\n- [Talorys vs ZeroClaw](https://www.anchorterminal.com/compare/talorys-vs-zeroclaw.md)\n- [Talorys vs Zo Computer](https://www.anchorterminal.com/compare/talorys-vs-zo-computer.md)\n- [AstrBot vs Talorys](https://www.anchorterminal.com/compare/astrbot-vs-talorys.md)\n\n## Disclosure\n\n- Talorys 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)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "QwenPaw vs Talorys", "url": "" } ], "description": "QwenPaw scores 62.2 (B) to Talorys's 28.9 (F) for assistants that remember you. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "QwenPaw B 62.2", "Talorys F 28.9", "scores" ], "h1": "QwenPaw vs Talorys", "image": "https://www.anchorterminal.com/assets/og/compare-qwenpaw-vs-talorys.png", "path": "/compare/qwenpaw-vs-talorys", "published": "2026-10-01", "section": "tools", "title": "QwenPaw vs Talorys for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/qwenpaw-vs-talorys" }, "tokens": { "markdown": 2800, "slim": 580 }, "version": 1 }