{ "data": { "a": { "slug": "nanoclaw", "name": "NanoClaw", "vendor": "NanoCo, Inc.", "vendorUrl": "https://nanoclaw.dev", "kind": "harness", "category": "personal-assistants", "summary": "Open-source personal assistant that the owner runs on their own machine. It answers on messaging apps, runs each agent session in a Docker container, keeps Markdown memory on disk and runs scheduled tasks.", "url": "https://www.anchorterminal.com/tools/nanoclaw", "markdownUrl": "https://www.anchorterminal.com/tools/nanoclaw.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nanoclaw.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nanoclaw.json", "repo": "https://github.com/nanocoai/nanoclaw", "license": "MIT", "transports": [], "packages": [], "auth": "none", "authNotes": "No account is needed to run it. Owners and admins are rows in a local `user_roles` table, and strangers are handled by each chat's `unknown_sender_policy` (https://docs.nanoclaw.dev/concepts/security). Model and service credentials are registered with a credential gateway on the host, OneCLI Agent Vault by default, which adds them to outbound HTTPS requests. Containers receive placeholders such as `onecli-managed` (https://docs.nanoclaw.dev/operate/credentials). Channel tokens stay in the host's `.env`. An optional free NanoClaw account, used for a prebuilt agent image and a managed Slack app, keeps its token in `~/.config/nanoclaw/account.json` with mode 0600 (https://github.com/nanocoai/nanoclaw/blob/main/README.md).", "pricing": "free", "pricingNotes": "Free under the MIT licence, with nothing on sale. The optional NanoClaw account, the Echo image and the managed Slack app are free of charge per the terms of 31 July 2026 (https://nanoclaw.dev/terms). The owner pays the model provider through a Claude subscription, an API key or another provider, and any service a channel or tool uses, such as Dial. Since 2.4.0 Claude groups default to Opus 5.5 (checked 2026-10-12).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 30929, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://docs.nanoclaw.dev", "llmsTxt": "https://docs.nanoclaw.dev/llms.txt", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "agent.mcp-client", "assistant.accounts" ], "tags": [ "open-source", "local", "free", "no-card", "docker", "llms-txt" ], "lastRelease": "2026-10-09", "graded": true, "anchor": { "graded": true, "score": 68.3, "grade": "B", "agentReady": false, "rank": 229, "ranked": true, "rankOf": 986, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 78, "payments": 60, "reliability": 78, "schema": 82, "security": 74, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": -5, "negativeNotes": [ "2026-10-09. Release 2026.10.0 fixed four symlink flaws through which a manipulated agent could make the host read, write or delete files outside its folders, plus an admin-command bypass, a cross-group read through `ncl` and a command injection in Mattermost setup. Fixed and described in the changelog within the week, but the advisories it links (GHSA-frvf-5rf5-89fq and seven others) were not public on 12 October 2026. -5. https://github.com/nanocoai/nanoclaw/blob/main/CHANGELOG.md" ], "verdict": "Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval.", "bestFor": "A technical owner who wants an assistant on their own machine, reachable from chat apps, with container isolation and scheduled tasks, and who is willing to keep a fork.", "strengths": [ "Each session runs in a non-root Docker container with all capabilities dropped, and the project root and `.env` are never mounted", "API keys sit in a credential gateway on the host, which adds them to outbound requests, so the container holds only placeholders", "Installing packages, adding an MCP server and admitting a new chat each wait for an admin's approval, and no reachable approver means denial", "Memory is plain Markdown under `groups/\u003cfolder\u003e/memory/`, which the owner can read, edit or delete on the host", "The security page states what the design does not stop, including messages to wired chats and spending through granted credentials" ], "weaknesses": [ "The Claude provider runs with `permissionMode: 'bypassPermissions'`, so shell, file and web tools run inside the container with no prompt", "Egress lockdown is off by default, so a container can reach the internet directly unless `NANOCLAW_EGRESS_LOCKDOWN=true` is set", "The 2026.10.0 changelog links eight advisories on the repository, and on 12 October 2026 the advisories page listed none and one linked advisory returned 404", "Setup sends events to PostHog unless `NANOCLAW_NO_DIAGNOSTICS=1` is set, and the privacy policy does not mention them", "The docs say trunk has no Gmail or Google Calendar integration, while the GitHub repository description still names Gmail", "294 open issues and 750 open pull requests on 12 October 2026, and 10 of the 12 newest open issues had no reply" ], "agentNotes": [ "Install with `git clone` and `bash nanoclaw.sh`. There is no registry package, and setup needs Docker, Node 22 or later and a Claude or Codex credential", "Set `NANOCLAW_EGRESS_LOCKDOWN=true` before giving an agent credentials or an audience of strangers. The default leaves egress open", "Put chats with different audiences in separate agent groups. Every session of a group shares one read-write workspace and memory tree", "Turn on per-request approval for a secret in the gateway when its use should wait for a person. It is off unless configured", "On OneCLI installs, move the gateway to 1.42.0 by the upgrade guide before updating to 2026.10.0. The updater stops until that is done" ], "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": 68.3 } ], "editorialScores": { "ergonomics": 70, "maintenance": 78, "payments": 60, "reliability": 78, "schema": 82, "security": 74, "transparency": 77 }, "provenanceScore": 53 }, "connect": { "install": "git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2 \u0026\u0026 cd nanoclaw-v2 \u0026\u0026 bash nanoclaw.sh" }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/nanoclaw" }, "area": "frameworks", "provenance": { "legalEntity": "NanoCo, Inc.", "domain": "nanoclaw.dev", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/nanocoai/nanoclaw/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The terms and privacy policy at nanoclaw.dev name NanoCo, Inc. and Delaware law. Both say they cover the website and the optional account, not the software, so neither is linked and the MIT licence stands in.", "nanoclaw.dev/.well-known/security.txt returned 404 on 12 October 2026. The repository's SECURITY.md points to GitHub private vulnerability reporting.", "There is no hosted endpoint. The assistant runs on the owner's machine, and the optional account service is at portal.nanoclaw.dev, which we did not open.", "The registration date of nanoclaw.dev was not checked." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nanoclaw.json" }, "answer": "NanoClaw scores 68.3 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories.", "b": { "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": 986, "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" }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "NanoCo, Inc.", "b": "AgentScope", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, stdio", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-09", "b": "2026-09-11", "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": "31k stars", "b": "36k stars", "name": "Popularity" } ], "faq": [ { "answer": "NanoClaw scores 68.3 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, NanoClaw or QwenPaw?" }, { "answer": "Yes. NanoClaw is open source (MIT). QwenPaw is open source (Apache-2.0).", "question": "Are NanoClaw and QwenPaw open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 78 against 70", "Schema \u0026 documentation, 82 against 68", "Security \u0026 auth, 74 against 60", "Maintenance \u0026 community, 78 against 73", "Transparency \u0026 trust, 65 against 56" ], "also": [ "Free to start without a card" ], "goodFor": "A technical owner who wants an assistant on their own machine, reachable from chat apps, with container isolation and scheduled tasks, and who is willing to keep a fork.", "slug": "nanoclaw", "watchFor": "The Claude provider runs with `permissionMode: 'bypassPermissions'`, so shell, file and web tools run inside the container with no prompt" }, { "aheadOn": null, "also": [ "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" } ], "job": { "capability": "assistant.proactive", "name": "Assistant proactive" }, "others": [ { "json": "https://www.anchorterminal.com/compare/astrbot-vs-nanoclaw.json", "title": "AstrBot vs NanoClaw", "url": "https://www.anchorterminal.com/compare/astrbot-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "CowAgent vs NanoClaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "GAIA vs NanoClaw", "url": "https://www.anchorterminal.com/compare/gaia-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Gemini Spark vs NanoClaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Grok Bot vs NanoClaw", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Haven vs NanoClaw", "url": "https://www.anchorterminal.com/compare/haven-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Hermes Agent vs NanoClaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Instinct vs NanoClaw", "url": "https://www.anchorterminal.com/compare/instinct-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "IronClaw vs NanoClaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Leon vs NanoClaw", "url": "https://www.anchorterminal.com/compare/leon-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "Lindy vs NanoClaw", "url": "https://www.anchorterminal.com/compare/lindy-vs-nanoclaw" }, { "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-nanoclaw.json", "title": "nanobot vs NanoClaw", "url": "https://www.anchorterminal.com/compare/nanobot-vs-nanoclaw" }, { "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-openai-dots.json", "title": "NanoClaw vs Dots", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-openai-dots" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-openclaw.json", "title": "NanoClaw vs OpenClaw", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-openclaw" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-picoclaw.json", "title": "NanoClaw vs PicoClaw", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-picoclaw" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-poke.json", "title": "NanoClaw vs Poke", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-zeroclaw.json", "title": "NanoClaw vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-zo-computer.json", "title": "NanoClaw vs Zo Computer", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-zo-computer" }, { "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" } ], "scores": [ { "by": 8, "edge": "nanoclaw", "key": "reliability", "name": "Reliability", "nanoclaw": 78, "qwenpaw": 70, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "edge": "nanoclaw", "key": "schema", "name": "Schema \u0026 documentation", "nanoclaw": 82, "qwenpaw": 68, "weight": 13 }, { "by": 3, "edge": "nanoclaw", "key": "ergonomics", "name": "Agent ergonomics", "nanoclaw": 70, "qwenpaw": 67, "weight": 13 }, { "by": 14, "edge": "nanoclaw", "key": "security", "name": "Security \u0026 auth", "nanoclaw": 74, "qwenpaw": 60, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "nanoclaw": 60, "qwenpaw": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "edge": "nanoclaw", "key": "maintenance", "name": "Maintenance \u0026 community", "nanoclaw": 78, "qwenpaw": 73, "weight": 7 }, { "by": 9, "edge": "nanoclaw", "key": "transparency", "name": "Transparency \u0026 trust", "nanoclaw": 65, "qwenpaw": 56, "weight": 7 } ], "summary": "NanoClaw scores 68.3 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories. Both do assistant proactive.", "verdicts": { "nanoclaw": "Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw", "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.md", "slim": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.min.md" }, "markdown": "NanoClaw scores 68.3 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories. Both do assistant proactive.\n\n- NanoClaw: grade B, 68.3/100, rank #229 of 986. Markdown https://www.anchorterminal.com/tools/nanoclaw.md · JSON https://www.anchorterminal.com/api/v1/tools/nanoclaw.json\n- QwenPaw: grade B, 62.2/100, rank #454 of 986. Markdown https://www.anchorterminal.com/tools/qwenpaw.md · JSON https://www.anchorterminal.com/api/v1/tools/qwenpaw.json\n- Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 190 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md\n\n## Which one, for what\n\n### NanoClaw (B)\n\nGood for: A technical owner who wants an assistant on their own machine, reachable from chat apps, with container isolation and scheduled tasks, and who is willing to keep a fork.\n\nAhead on:\n- Reliability, 78 against 70\n- Schema \u0026 documentation, 82 against 68\n- Security \u0026 auth, 74 against 60\n- Maintenance \u0026 community, 78 against 73\n- Transparency \u0026 trust, 65 against 56\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: The Claude provider runs with `permissionMode: 'bypassPermissions'`, so shell, file and web tools run inside the container with no prompt\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\nAlso in its favour:\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\n## Score by category\n\n| Category | Weight | NanoClaw | QwenPaw | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 78 | 70 | NanoClaw +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 82 | 68 | NanoClaw +14 |\n| Agent ergonomics | 13% (16.2 this run) | 70 | 67 | NanoClaw +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 74 | 60 | NanoClaw +14 |\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) | 78 | 73 | NanoClaw +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 65 | 56 | NanoClaw +9 |\n| Negative events | ≤15 | -5 | -3 | |\n| **Total** | | **68.3 · B** | **62.2 · B** | |\n\n## Facts side by side\n\n| Fact | NanoClaw | QwenPaw |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | NanoCo, Inc. | AgentScope |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | HTTP, stdio |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-09 | 2026-09-11 |\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 | 31k stars | 36k stars |\n\n## Verdicts\n\n**NanoClaw.** Each session runs in an unprivileged Docker container and API keys stay in a credential gateway on the host, so a manipulated agent cannot read them. Inside the container the agent runs with permission prompts off, network egress is open by default, and it can message any chat it is wired to without approval.\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## Before you call either\n\n### NanoClaw\n\n1. Install with `git clone` and `bash nanoclaw.sh`. There is no registry package, and setup needs Docker, Node 22 or later and a Claude or Codex credential\n2. Set `NANOCLAW_EGRESS_LOCKDOWN=true` before giving an agent credentials or an audience of strangers. The default leaves egress open\n3. Put chats with different audiences in separate agent groups. Every session of a group shares one read-write workspace and memory tree\n4. Turn on per-request approval for a secret in the gateway when its use should wait for a person. It is off unless configured\n5. On OneCLI installs, move the gateway to 1.42.0 by the upgrade guide before updating to 2026.10.0. The updater stops until that is done\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## Questions\n\n### Which is better for AI agents, NanoClaw or QwenPaw?\n\nNanoClaw scores 68.3 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories.\n\n### Are NanoClaw and QwenPaw open source?\n\nYes. NanoClaw is open source (MIT). QwenPaw is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.json, and with the fewest tokens: https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"nanoclaw\", \"b\": \"qwenpaw\"}`. From a terminal: `anchor compare nanoclaw qwenpaw`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/nanoclaw.json and https://www.anchorterminal.com/api/v1/tools/qwenpaw.json\n\n## Other comparisons with NanoClaw or QwenPaw\n\n- [AstrBot vs NanoClaw](https://www.anchorterminal.com/compare/astrbot-vs-nanoclaw.md)\n- [AstrBot vs QwenPaw](https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw.md)\n- [CowAgent vs NanoClaw](https://www.anchorterminal.com/compare/cowagent-vs-nanoclaw.md)\n- [CowAgent vs QwenPaw](https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.md)\n- [GAIA vs NanoClaw](https://www.anchorterminal.com/compare/gaia-vs-nanoclaw.md)\n- [GAIA vs QwenPaw](https://www.anchorterminal.com/compare/gaia-vs-qwenpaw.md)\n- [Gemini Spark vs NanoClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-nanoclaw.md)\n- [Gemini Spark vs QwenPaw](https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.md)\n- [Grok Bot vs NanoClaw](https://www.anchorterminal.com/compare/grok-bot-vs-nanoclaw.md)\n- [Grok Bot vs QwenPaw](https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.md)\n- [Haven vs NanoClaw](https://www.anchorterminal.com/compare/haven-vs-nanoclaw.md)\n- [Haven vs QwenPaw](https://www.anchorterminal.com/compare/haven-vs-qwenpaw.md)\n- [Hermes Agent vs NanoClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw.md)\n- [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md)\n- [Instinct vs NanoClaw](https://www.anchorterminal.com/compare/instinct-vs-nanoclaw.md)\n- [Instinct vs QwenPaw](https://www.anchorterminal.com/compare/instinct-vs-qwenpaw.md)\n- [IronClaw vs NanoClaw](https://www.anchorterminal.com/compare/ironclaw-vs-nanoclaw.md)\n- [IronClaw vs QwenPaw](https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.md)\n- [Leon vs NanoClaw](https://www.anchorterminal.com/compare/leon-vs-nanoclaw.md)\n- [Leon vs QwenPaw](https://www.anchorterminal.com/compare/leon-vs-qwenpaw.md)\n- [Lindy vs NanoClaw](https://www.anchorterminal.com/compare/lindy-vs-nanoclaw.md)\n- [Lindy vs QwenPaw](https://www.anchorterminal.com/compare/lindy-vs-qwenpaw.md)\n- [nanobot vs NanoClaw](https://www.anchorterminal.com/compare/nanobot-vs-nanoclaw.md)\n- [nanobot vs QwenPaw](https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw.md)\n- [NanoClaw vs Dots](https://www.anchorterminal.com/compare/nanoclaw-vs-openai-dots.md)\n- [NanoClaw vs OpenClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-openclaw.md)\n- [NanoClaw vs PicoClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-picoclaw.md)\n- [NanoClaw vs Poke](https://www.anchorterminal.com/compare/nanoclaw-vs-poke.md)\n- [NanoClaw vs ZeroClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-zeroclaw.md)\n- [NanoClaw vs Zo Computer](https://www.anchorterminal.com/compare/nanoclaw-vs-zo-computer.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", "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": "NanoClaw vs QwenPaw", "url": "" } ], "description": "NanoClaw scores 68.3 (B) to QwenPaw's 62.2 (B) for assistant proactive. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "NanoClaw B 68.3", "QwenPaw B 62.2", "scores" ], "h1": "NanoClaw vs QwenPaw", "image": "https://www.anchorterminal.com/assets/og/compare-nanoclaw-vs-qwenpaw.png", "path": "/compare/nanoclaw-vs-qwenpaw", "published": "2026-10-01", "section": "tools", "title": "NanoClaw vs QwenPaw for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw" }, "tokens": { "markdown": 2550, "slim": 530 }, "version": 1 }