# Haven vs QwenPaw

> QwenPaw scores 62.2 (B) to Haven's 22.2 (F) for assistant proactive. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/haven-vs-qwenpaw
- Markdown: https://www.anchorterminal.com/compare/haven-vs-qwenpaw.md (~2,550 tokens)
- Slim: https://www.anchorterminal.com/compare/haven-vs-qwenpaw.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/haven-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

QwenPaw scores 62.2 (B) on agent readiness against Haven's 22.2 (F), and leads in every scored category. Both do assistant proactive.

- Haven: grade F, 22.2/100, rank #977 of 986. Markdown https://www.anchorterminal.com/tools/haven.md · JSON https://www.anchorterminal.com/api/v1/tools/haven.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

### Haven (F)

Good for: A consumer assistant for one person who wants to phone, text or email it and have it remember them.

Also in its favour:
- No incidents deducted, where QwenPaw loses 3 points for them

Watch for: No approval setting or list of actions that need confirmation was found on the public pages. The terms say it sends emails, SMS and calls following the user's instructions.

### 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.

Ahead on:
- Reliability, 70 against 35
- Schema & documentation, 68 against 4
- Agent ergonomics, 67 against 6
- Security & auth, 60 against 13
- Payments & pricing, 60 against 30
- Maintenance & community, 73 against 35
- Transparency & trust, 56 against 51

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source

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 | Haven | QwenPaw | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 35 | 70 | QwenPaw +35 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 4 | 68 | QwenPaw +64 |
| Agent ergonomics | 13% (16.2 this run) | 6 | 67 | QwenPaw +61 |
| Security & auth | 14% (17.5 this run) | 13 | 60 | QwenPaw +47 |
| Payments & pricing | 10% (12.5 this run) | 30 | 60 | QwenPaw +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 35 | 73 | QwenPaw +38 |
| Transparency & trust | 7% (8.8 this run) | 51 | 56 | QwenPaw +5 |
| Negative events | ≤15 | 0 | -3 | |
| **Total** | | **22.2 · F** | **62.2 · B** | |

## Facts side by side

| Fact | Haven | QwenPaw |
| --- | --- | --- |
| Kind | Platform | Agent harness |
| Vendor | Hello Haven, Inc. | AgentScope |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP, stdio |
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Proprietary service under Hello Haven's Terms of Service | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-09-17 | 2026-09-11 |
| Terms last updated | 2026-07-24 | no document linked |
| Privacy policy last updated | 2026-07-24 | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | none | 36k stars |

## Verdicts

**Haven.** Haven answers by phone call, text, email and app, is free in beta with no card, and publishes a status page with dated incidents. No public page read says which actions need approval, which accounts it connects or how their tokens are kept, and it names no model provider or sub-processor.

**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

### Haven

1. Haven has no documented API or MCP server. An outside agent can reach it only through the owner's channels (call, SMS, email, app).
2. Do not assume an approval step before Haven sends mail, texts or calls. None is documented on the public pages.
3. Email Haven sends to other people names Hello Haven as sender and says it was sent on the user's behalf, per the terms.
4. Chat messages, history, profile context and uploaded files go to third-party AI model providers that the vendor does not name.
5. Check status.hellohaven.ai before relying on phone or voice. All four published incidents affected those channels.

### 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, Haven or QwenPaw?

QwenPaw scores 62.2 (B) on agent readiness against Haven's 22.2 (F), and leads in every scored category.

### Are Haven and QwenPaw open source?

No open-source release is listed for Haven. QwenPaw is open source (Apache-2.0).


## For agents

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

## Other comparisons with Haven or QwenPaw

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