# OpenDuet vs QwenPaw (slim)

> QwenPaw scores 62.4 (B) to OpenDuet's 49.5 (D) for proactive personal assistants. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/openduet-vs-qwenpaw.md (~3,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/openduet-vs-qwenpaw.json · canonical https://www.anchorterminal.com/compare/openduet-vs-qwenpaw
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-30
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

QwenPaw scores 62.4 (B) on agent readiness against OpenDuet's 49.5 (D), and leads in 6 of 7 scored categories. OpenDuet leads on transparency & trust. Both do proactive personal assistants.

- OpenDuet: D 49.5, rank #962 of 1239 · https://www.anchorterminal.com/tools/openduet.min.md
- QwenPaw: B 62.4, rank #506 of 1239 · https://www.anchorterminal.com/tools/qwenpaw.min.md
- OpenDuet, good for A starting point for a developer or team who wants a proactive mail-and-calendar assistant they host and change, with approvals and audit, and who accepts a CopilotKit Intelligence account. Ahead on Transparency & trust, 68 against 58. Also Free to start without a card; No incidents deducted, where QwenPaw loses 3 points for them.
- QwenPaw, 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 42; Schema & documentation, 68 against 58; Agent ergonomics, 67 against 52; Payments & pricing, 60 against 30; Maintenance & community, 73 against 37. Also No key needed to call it; Runs on your own machine.

| Category | OpenDuet | QwenPaw |
| --- | --- | --- |
| Reliability (16%) | 42 | 70 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 58 | 68 |
| Agent ergonomics (13%) | 52 | 67 |
| Security & auth (14%) | 59 | 60 |
| Payments & pricing (10%) | 30 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 37 | 73 |
| Transparency & trust (7%) | 68 | 58 |

| Fact (where they differ) | OpenDuet | QwenPaw |
| --- | --- | --- |
| Vendor | CopilotKit (Tawkit, Inc.) | AgentScope |
| Transports |  | HTTP, stdio |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| Licence | MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement | Apache-2.0 |
| Last release | none | 2026-09-11 |
| Terms last updated | couldn't be read | no document linked |
| Privacy policy last updated | 2026-08-27 | no document linked |
| Customer content may train models | couldn't be read |  |
| Terms restrict automated access | couldn't be read |  |
| Terms restrict benchmarking | couldn't be read |  |
| Terms or service can change without notice | couldn't be read |  |
| Arbitration or class-action waiver | couldn't be read |  |
| Popularity | 1.6k stars | 36k stars |
| Agent reviews | none | 2.8/5 (4) |