# OpenClaw vs QwenPaw

> OpenClaw scores 67.1 (B) 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/openclaw-vs-qwenpaw
- Markdown: https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.md (~2,550 tokens)
- Slim: https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.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

OpenClaw scores 67.1 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories. Both do assistant proactive.

- OpenClaw: grade B, 67.1/100, rank #270 of 986. Markdown https://www.anchorterminal.com/tools/openclaw.md · JSON https://www.anchorterminal.com/api/v1/tools/openclaw.json
- 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
- 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

### OpenClaw (B)

Good for: A technical owner who wants an assistant on their own machine across many chat apps, with their choice of model and files they can read and delete.

Ahead on:
- Reliability, 75 against 70
- Schema & documentation, 84 against 68
- Agent ergonomics, 77 against 67
- Security & auth, 74 against 60
- Maintenance & community, 86 against 73
- Transparency & trust, 68 against 56

Watch for: Without configuration the default is full access. Host exec runs with no approval and sandboxing is off

### 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:
- No key needed to call it
- 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


## Score by category

| Category | Weight | OpenClaw | QwenPaw | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 75 | 70 | OpenClaw +5 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 84 | 68 | OpenClaw +16 |
| Agent ergonomics | 13% (16.2 this run) | 77 | 67 | OpenClaw +10 |
| Security & auth | 14% (17.5 this run) | 74 | 60 | OpenClaw +14 |
| 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) | 86 | 73 | OpenClaw +13 |
| Transparency & trust | 7% (8.8 this run) | 68 | 56 | OpenClaw +12 |
| Negative events | ≤15 | -8 | -3 | |
| **Total** | | **67.1 · B** | **62.2 · B** | |

## Facts side by side

| Fact | OpenClaw | QwenPaw |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | OpenClaw Foundation | AgentScope |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  | HTTP, stdio |
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-10-12 | 2026-09-11 |
| 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 | 392k stars | 36k stars |

## Verdicts

**OpenClaw.** Self-hosted under the MIT licence, with state, memory and credentials kept on the owner's machine and no paid tier. A fresh install runs tools on the host with full access, no approval prompt and no sandbox, and the project has published 722 security advisories since January 2026, 14 of them critical.

**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.

## Before you call either

### OpenClaw

1. Set a session permission mode of `guarded` or `workspace`, or `tools.exec.mode`, before connecting mail. The default runs host commands without approval
2. Turn on `agents.defaults.sandbox` for any agent that reads mail, web pages or attachments. Sandboxing is off by default
3. Set `tools.message.crossContext.allowAcrossProviders` and `allowWithinProvider` to `false` to confine sends to the current conversation
4. Route incoming mail to a restricted reader agent, as the IMAP and Gmail guides show, and deny `gateway`, `cron`, `sessions_spawn` and `sessions_send` for it
5. Run `openclaw security audit` after setup, and treat the Gateway token as an owner credential. `POST /tools/invoke` accepts it with full operator access

### 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

## Questions

### Which is better for AI agents, OpenClaw or QwenPaw?

OpenClaw scores 67.1 (B) on agent readiness against QwenPaw's 62.2 (B), and leads in 6 of 7 scored categories.

### Are OpenClaw and QwenPaw open source?

Yes. OpenClaw is open source (MIT). QwenPaw is open source (Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.json, and with the fewest tokens: https://www.anchorterminal.com/compare/openclaw-vs-qwenpaw.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "openclaw", "b": "qwenpaw"}`. From a terminal: `anchor compare openclaw qwenpaw`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/openclaw.json and https://www.anchorterminal.com/api/v1/tools/qwenpaw.json

## Other comparisons with OpenClaw or QwenPaw

- [AstrBot vs OpenClaw](https://www.anchorterminal.com/compare/astrbot-vs-openclaw.md)
- [AstrBot vs QwenPaw](https://www.anchorterminal.com/compare/astrbot-vs-qwenpaw.md)
- [CowAgent vs OpenClaw](https://www.anchorterminal.com/compare/cowagent-vs-openclaw.md)
- [CowAgent vs QwenPaw](https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.md)
- [GAIA vs OpenClaw](https://www.anchorterminal.com/compare/gaia-vs-openclaw.md)
- [GAIA vs QwenPaw](https://www.anchorterminal.com/compare/gaia-vs-qwenpaw.md)
- [Gemini Spark vs OpenClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-openclaw.md)
- [Gemini Spark vs QwenPaw](https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.md)
- [Grok Bot vs OpenClaw](https://www.anchorterminal.com/compare/grok-bot-vs-openclaw.md)
- [Grok Bot vs QwenPaw](https://www.anchorterminal.com/compare/grok-bot-vs-qwenpaw.md)
- [Haven vs OpenClaw](https://www.anchorterminal.com/compare/haven-vs-openclaw.md)
- [Haven vs QwenPaw](https://www.anchorterminal.com/compare/haven-vs-qwenpaw.md)
- [Hermes Agent vs OpenClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-openclaw.md)
- [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md)
- [Instinct vs OpenClaw](https://www.anchorterminal.com/compare/instinct-vs-openclaw.md)
- [Instinct vs QwenPaw](https://www.anchorterminal.com/compare/instinct-vs-qwenpaw.md)
- [IronClaw vs OpenClaw](https://www.anchorterminal.com/compare/ironclaw-vs-openclaw.md)
- [IronClaw vs QwenPaw](https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.md)
- [Leon vs OpenClaw](https://www.anchorterminal.com/compare/leon-vs-openclaw.md)
- [Leon vs QwenPaw](https://www.anchorterminal.com/compare/leon-vs-qwenpaw.md)
- [Lindy vs OpenClaw](https://www.anchorterminal.com/compare/lindy-vs-openclaw.md)
- [Lindy vs QwenPaw](https://www.anchorterminal.com/compare/lindy-vs-qwenpaw.md)
- [nanobot vs OpenClaw](https://www.anchorterminal.com/compare/nanobot-vs-openclaw.md)
- [nanobot vs QwenPaw](https://www.anchorterminal.com/compare/nanobot-vs-qwenpaw.md)
- [NanoClaw vs OpenClaw](https://www.anchorterminal.com/compare/nanoclaw-vs-openclaw.md)
- [NanoClaw vs QwenPaw](https://www.anchorterminal.com/compare/nanoclaw-vs-qwenpaw.md)
- [Dots vs OpenClaw](https://www.anchorterminal.com/compare/openai-dots-vs-openclaw.md)
- [Dots vs QwenPaw](https://www.anchorterminal.com/compare/openai-dots-vs-qwenpaw.md)
- [OpenClaw vs PicoClaw](https://www.anchorterminal.com/compare/openclaw-vs-picoclaw.md)
- [OpenClaw vs Poke](https://www.anchorterminal.com/compare/openclaw-vs-poke.md)
- [OpenClaw vs ZeroClaw](https://www.anchorterminal.com/compare/openclaw-vs-zeroclaw.md)
- [OpenClaw vs Zo Computer](https://www.anchorterminal.com/compare/openclaw-vs-zo-computer.md)
- [PicoClaw vs QwenPaw](https://www.anchorterminal.com/compare/picoclaw-vs-qwenpaw.md)
- [Poke vs QwenPaw](https://www.anchorterminal.com/compare/poke-vs-qwenpaw.md)
- [QwenPaw vs ZeroClaw](https://www.anchorterminal.com/compare/qwenpaw-vs-zeroclaw.md)
- [QwenPaw vs Zo Computer](https://www.anchorterminal.com/compare/qwenpaw-vs-zo-computer.md)