- feat(agent): extract third-party agent into plugins
- feat(console): quote response selections in follow-up drafts
- fix(console): restore Safari message queue action icons
- fix(cron): track scheduled agent runs
- fix(console): gate terminal status checks on auth
- feat(shell): add intent titles to command cards
QwenPaw by AgentScope team (Alibaba)
A self-hosted personal assistant built on AgentScope that runs locally, in Docker or in the cloud, with skills, plugins, MCP, multi-agent support, layered memory and scheduled tasks, and connects to chat channels such as DingTalk, Lark, Discord and Telegram. Its desktop app is in beta, the README says.
Use it in: Desktop app Web app CLI Slack, Teams, Telegram Self-hosted Works with: MCP Local models Own API key Multi-agent Headless / CI
On this page
Usage data: latest readings Nov 19 to Nov 21, 2026, last checked Nov 21, 06:27 UTC. Date of each number
What QwenPaw does
QwenPaw is an open-source personal AI assistant (formerly CoPaw) from AgentScope team, first released in February 2026. You use it through a desktop app, a web app, a command-line tool, messaging apps and self-hosted. Its documentation covers MCP servers, subagents or parallel agents, a non-interactive mode for scripts and CI, your own API key and local models. It can run models from Qwen, OpenAI, Anthropic, Google, DeepSeek and Moonshot (Kimi) and others. It is free and open source (Apache-2.0); you pay only for the models it calls.
Key facts
| Maker | AgentScope team (Alibaba) |
|---|---|
| Type | Open-source personal AI assistant (formerly CoPaw) |
| First released | February 2026 |
| License | Apache-2.0 |
| Interfaces | Desktop app, Web app, CLI, Messaging apps, Self-hosted |
| Main language | Python |
| Open issues and PRs | 1,152 |
| Docker Hub pulls | 595,215 |
Pricing
Free Apache-2.0 software that runs local QwenPaw models or your own cloud provider keys.
Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itDesktop app, Web app, CLI, Messaging apps, Self-hosted
- Supports MCP?Yes
- Model providersqwen, openai, anthropic, google, deepseek, moonshot, openrouter, local
- Subagents / multi-agent?Yes
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativeOpenClaw · all alternatives
What's new in QwenPaw: September 2026
September brought major infrastructure and integration improvements to QwenPaw, including multi-user Hub hosting, new model providers, and enhanced memory systems. The month focused on making deployment easier, routing more intelligent, and agent behavior more secure.
- Self-host a multi-user QwenPaw Hub locally or in Docker with workspace access controls and credential management.
- New Mail assistant with real-time monitoring, search, and sender rules, bundled into the desktop app.
- Configure model routing separately per Agent with provider preferences and intelligent fallback policies.
- One-click detection and installation of plugin and PawApp updates.
2 releases this month · summarised from the official release notes · all months
Get started with QwenPaw
| PyPI | pip install qwenpaw |
|---|---|
| Docker | docker pull agentscope/qwenpaw |
These commands use the packages tracked on this page. The vendor may recommend a different installer.
QwenPaw alternatives
Best QwenPaw alternatives compared · All general-purpose AI agents
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 8 |
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger |
70 | 2.8M | down 8.7% | down 27.1% | 395K+123/day | 2026.11.62d ago | Free (OSS) | |||
| 11 |
DeepSeek HarnessDeepSeek |
67 | 676K | down 14.9% | up 59.0% | 285K+622/day | — | Free | |||
| 14 |
Hermes AgentNous Research |
63 | 56.8K | down 26.1% | — | 265K+297/day | 0.23.3yesterday | Free (OSS) | |||
| 42 |
ManusButterfly Effect Pte. Ltd. (Manus AI), Singapore |
50 | — | — | — | — | — | $20/mo | |||
| 58 |
Cloudflare OSCloudflare |
46 | — | — | — | 11.8K+9/day | — | Free (OSS) | |||
| 63 |
|
452/4 | — | — | — | — | — | Free | |||
Head to head: QwenPaw vs DeepSeek Harness · QwenPaw vs Hermes Agent · QwenPaw vs Manus · QwenPaw vs OpenClaw
Ratings from people who use QwenPaw
No ratings yet. Used QwenPaw? Rate it and say what it is good and bad at.
QwenPaw news
-
QwenPaw 2.3.0.post1 released
feat(agent): extract third-party agent into plugins; feat(console): quote response selections in follow-up drafts; fix(console): restore Safari message queue action icons
-
QwenPaw 2.3.0 released
Add Piccolo 4B, 9B, and 27B as local decision models for tool review and context compaction, with BF16 and Q8_0 recommendations, runtime installation and updates, and Hugging Face or ModelScope…; Browse, sort, and comment on QwenPaw Community posts from the…
What changed: recent QwenPaw releases
6 stable releases in the last 90 days · Monthly summary · Full changelog
- Add Piccolo 4B, 9B, and 27B as local decision models for tool review and context compaction, with BF16 and Q8_0 recommendations, runtime installation and updates, and Hugging Face or ModelScope…
- Browse, sort, and comment on QwenPaw Community posts from the Console, draft resource-linked issue reports with model assistance, and open the community editor.
- Add the optional OpenUI plugin to display interactive forms and components within replies, preserve their state during streaming, and submit actions to the originating conversation
- Add an unread-only filter to Inbox push messages so older unread messages are easier to find
- Let desktop windows share one background service, keep tasks running after closing the last window, and coordinate updates across windows; preserve unsent drafts when the service reconnects
- Receive browser and desktop notifications for approvals, completed replies, and background tasks, including when the desktop is minimized to the tray.
Earlier releases
- chore: bump the version to v2.2.2post1
- fix(security): remediate emSign CA trust across dependencies, installers, and builds
- fix(security): update Node.js to 22.23.4
- Add six theme palettes and custom colors and corner radii, with live preview and saved preferences
- Add an authenticated, multi-tab terminal inside Chat, with a working directory for each conversation
- Allow Console font size to be adjusted from 12 to 20 pixels across chat and settings
- Save multi-folder workspaces as an Agent’s default for future tasks
- Show files delivered by the Agent directly below its reply for easier preview and download
- Recommend QwenPaw-Flash 9B, 27B, and 35B-A3B locally: update the 9B recommendation and add 27B and 35B-A3B options
- Configure model routing separately for each Agent, including provider preferences and fallback behavior
- Add Auto Fin proactive memory review and upgrade ReMe for more reliable long-term-memory processing
- Add PowerContext as an optional long-term-memory backend with configuration in the Console
- Strengthen built-in Agent behavior around request scope, untrusted content, confirmations, tool use, and completion
- Add a blueprint workbench, multi-timeline comparison, reusable video templates, MiniMax H3 support, project snapshot rollback, clearer Agent progress, and Docker deployment in Creator 1.2.0
- Manage environment variables in a unified settings page shared by Agents, MCP services, tools, and local models
- Self-host a multi-user QwenPaw Hub with local-process or Docker runtimes, workspace-level access controls, credential management, and reverse-proxy support
- Deploy QwenPaw Data as a native PawApp with a durable analysis workspace, packaged runtime, and one-command Docker Compose example
- Add an intelligent mail assistant with real-time monitoring, search, thread-aware actions, sender allow/deny rules, and human approval for unknown recipients
- Bundle and launch the Mail MCP with the desktop app
- Keep Mail tool responses readable in Chinese conversations
- Make model setup and selection more consistent with unified provider discovery, capability-aware routing, fallback policies, and thinking controls
QwenPaw popularity and usage data
QwenPaw was downloaded 12.4K times from PyPI in the week ending Nov 19, 2026, down 28.1% on the week before and down 6.1% over the last 30 days compared with the 30 before. The GitHub repository has 38.1K stars, 2,323 of them added in the last 30 days. The latest stable release is 2.3.0.post1, published Nov 18, 2026; there were 3 stable releases in the past 30 days.
Download the raw daily series: qwenpaw.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 19, 2026 | Nov 21, 06:24 UTC |
| GitHub stars | Nov 21, 2026 | Nov 21, 06:26 UTC |
| Docker pulls | Nov 21, 2026 | Nov 21, 06:27 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
QwenPaw FAQ
How much does QwenPaw cost?
Free Apache-2.0 software that runs local QwenPaw models or your own cloud provider keys.
Is QwenPaw open source?
Yes. QwenPaw is open source, released under the Apache-2.0 license.
How popular is QwenPaw?
QwenPaw was downloaded 12.4K times from PyPI in the week ending Nov 19, 2026, down 28.1% on the week before and down 6.1% over the last 30 days compared with the 30 before. The GitHub repository has 38.1K stars, 2,323 of them added in the last 30 days. The latest stable release is 2.3.0.post1, published Nov 18, 2026; there were 3 stable releases in the past 30 days.
What is the latest version of QwenPaw?
The latest stable release we track is 2.3.0.post1, published on Nov 18, 2026.
What are the alternatives to QwenPaw?
The closest alternatives in the same category by Gid Score are OpenClaw, DeepSeek Harness, Hermes Agent, Manus.
For the makers of QwenPaw badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/qwenpaw/)
[](https://agentgid.com/agents/qwenpaw/)
[](https://agentgid.com/agents/qwenpaw/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: qwenpaw. GitHub: agentscope-ai/qwenpaw. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, hub.docker.com.