# QwenPaw vs ZeroClaw > ZeroClaw scores 70.2 (BB) to QwenPaw's 62.2 (B) for assistant proactive. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw - Markdown: https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.md (~2,550 tokens) - Slim: https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-12 ZeroClaw scores 70.2 (BB) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories. Both do assistant proactive. - 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 - ZeroClaw: grade BB, 70.2/100, rank #161 of 986. Markdown https://www.anchorterminal.com/tools/zeroclaw.md · JSON https://www.anchorterminal.com/api/v1/tools/zeroclaw.json - Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md - All 190 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md ## Which one, for what ### QwenPaw (B) Good 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. Also in its favour: - Runs on your own machine Watch 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 ### ZeroClaw (BB) Good for: One person who wants an assistant on their own hardware that answers on Telegram, Discord, Matrix or email, asks before it writes or runs commands, and works with a local model. Ahead on: - Schema & documentation, 82 against 68 - Agent ergonomics, 72 against 67 - Security & auth, 76 against 60 - Maintenance & community, 80 against 73 - Transparency & trust, 64 against 56 Also in its favour: - Agent-ready, a grade of BB or better - Free to start without a card Watch for: The docs state that command execution is not audited. `[security.audit]` records certificate events only, and tool receipts are opt-in and not durable ## Score by category | Category | Weight | QwenPaw | ZeroClaw | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 70 | 74 | ZeroClaw +4 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 68 | 82 | ZeroClaw +14 | | Agent ergonomics | 13% (16.2 this run) | 67 | 72 | ZeroClaw +5 | | Security & auth | 14% (17.5 this run) | 60 | 76 | ZeroClaw +16 | | Payments & pricing | 10% (12.5 this run) | 60 | 60 | even | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 73 | 80 | ZeroClaw +7 | | Transparency & trust | 7% (8.8 this run) | 56 | 64 | ZeroClaw +8 | | Negative events | ≤15 | -3 | -3 | | | **Total** | | **62.2 · B** | **70.2 · BB** | | ## Facts side by side | Fact | QwenPaw | ZeroClaw | | --- | --- | --- | | Kind | Agent harness | Agent harness | | Vendor | AgentScope | ZeroClaw Labs | | Hosted endpoint | no (local only) | no (local only) | | Transports | HTTP, stdio | | | Auth | None | None | | Pricing | Free | Free | | x402 | no | no | | Licence | Apache-2.0 | MIT OR Apache-2.0 | | Read-only variant documented | no | yes | | llms.txt | no | yes | | Last release | 2026-09-11 | 2026-09-05 | | Terms last updated | no document linked | no document linked | | Privacy policy last updated | no document linked | no document linked | | Customer content may train models | | | | Terms restrict automated access | | | | Terms restrict benchmarking | | | | Terms or service can change without notice | | | | Arbitration or class-action waiver | | | | Popularity | 36k stars | 33k stars | ## 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. **ZeroClaw.** Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms. ## Before you call either ### QwenPaw 1. Set `QWENPAW_TELEMETRY_DISABLED=true` before `qwenpaw init --defaults` or `qwenpaw app`. Both send usage data without asking 2. Set `approval_level` to `STRICT` or `SMART` in `agent.json`. The default `AUTO` runs every tool call no guard rule flags 3. Set `dm_policy` and `group_policy` to `allowlist` with `allow_from` on each channel. Both default to `open` 4. Set `QWENPAW_AUTH_ENABLED=true` before binding beyond 127.0.0.1. Requests from localhost skip login even then 5. Keep mail tools on `ask` for `send_message`, `delete_message` and `delete_thread`, and turn on Mail Access Control with automatic handling ### ZeroClaw 1. Keep `[risk_profiles.] level = "supervised"`. `full` runs every tool not listed in `always_ask`, and the YOLO preset removes the sandbox and path rules too 2. Add sending and account tools such as `send_via`, `google_workspace` and `http_request` to `always_ask` so a session-level Always grant cannot skip the prompt 3. List senders in `[peer_groups.] external_peers`. `["*"]` accepts anyone on that channel 4. Set `[web_fetch].allowed_domains` and `[http_request].allowed_domains`. Fetches run unprompted and the OS sandbox does not block egress 5. Run one-shot tasks with `zeroclaw agent -a -m ""`. A cron or webhook turn has no prompt, so shell calls fall to the command policy ## Questions ### Which is better for AI agents, QwenPaw or ZeroClaw? ZeroClaw scores 70.2 (BB) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories. ### Are QwenPaw and ZeroClaw open source? Yes. QwenPaw is open source (Apache-2.0). ZeroClaw is open source (MIT OR Apache-2.0). ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.json, and with the fewest tokens: https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "qwenpaw", "b": "zeroclaw"}`. From a terminal: `anchor compare qwenpaw zeroclaw` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/qwenpaw.json and https://www.anchorterminal.com/api/v1/tools/zeroclaw.json ## Other comparisons with QwenPaw or ZeroClaw - [AstrBot vs QwenPaw](https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw.md) - [AstrBot vs ZeroClaw](https://www.anchorterminal.com/compare/astrbot-vs-zeroclaw.md) - [CowAgent vs QwenPaw](https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.md) - [CowAgent vs ZeroClaw](https://www.anchorterminal.com/compare/cowagent-vs-zeroclaw.md) - [GAIA vs QwenPaw](https://www.anchorterminal.com/compare/gaia-vs-qwenpaw.md) - [GAIA vs ZeroClaw](https://www.anchorterminal.com/compare/gaia-vs-zeroclaw.md) - [Gemini Spark vs QwenPaw](https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.md) - [Gemini Spark vs ZeroClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-zeroclaw.md) - [Grok Bot vs QwenPaw](https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.md) - [Grok Bot vs ZeroClaw](https://www.anchorterminal.com/compare/grok-bot-vs-zeroclaw.md) - [Haven vs QwenPaw](https://www.anchorterminal.com/compare/haven-vs-qwenpaw.md) - [Haven vs ZeroClaw](https://www.anchorterminal.com/compare/haven-vs-zeroclaw.md) - [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md) - [Hermes Agent vs ZeroClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-zeroclaw.md) - [Instinct vs QwenPaw](https://www.anchorterminal.com/compare/instinct-vs-qwenpaw.md) - [Instinct vs ZeroClaw](https://www.anchorterminal.com/compare/instinct-vs-zeroclaw.md) - [IronClaw vs QwenPaw](https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.md) - [IronClaw vs ZeroClaw](https://www.anchorterminal.com/compare/ironclaw-vs-zeroclaw.md) - [Leon vs QwenPaw](https://www.anchorterminal.com/compare/leon-vs-qwenpaw.md) - [Leon vs ZeroClaw](https://www.anchorterminal.com/compare/leon-vs-zeroclaw.md) - [Lindy vs QwenPaw](https://www.anchorterminal.com/compare/lindy-vs-qwenpaw.md) - [Lindy vs ZeroClaw](https://www.anchorterminal.com/compare/lindy-vs-zeroclaw.md) - [nanobot vs QwenPaw](https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw.md) - [nanobot vs ZeroClaw](https://www.anchorterminal.com/compare/nanobot-vs-zeroclaw.md) - [NanoClaw vs QwenPaw](https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.md) - [NanoClaw vs ZeroClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-zeroclaw.md) - [Dots vs QwenPaw](https://www.anchorterminal.com/compare/openai-dots-vs-qwenpaw.md) - [Dots vs ZeroClaw](https://www.anchorterminal.com/compare/openai-dots-vs-zeroclaw.md) - [OpenClaw vs QwenPaw](https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.md) - [OpenClaw vs ZeroClaw](https://www.anchorterminal.com/compare/openclaw-vs-zeroclaw.md) - [PicoClaw vs QwenPaw](https://www.anchorterminal.com/compare/picoclaw-vs-qwenpaw.md) - [PicoClaw vs ZeroClaw](https://www.anchorterminal.com/compare/picoclaw-vs-zeroclaw.md) - [Poke vs QwenPaw](https://www.anchorterminal.com/compare/poke-vs-qwenpaw.md) - [Poke vs ZeroClaw](https://www.anchorterminal.com/compare/poke-vs-zeroclaw.md) - [QwenPaw vs Zo Computer](https://www.anchorterminal.com/compare/qwenpaw-vs-zo-computer.md) - [ZeroClaw vs Zo Computer](https://www.anchorterminal.com/compare/zeroclaw-vs-zo-computer.md)