agentscope-ai/QwenPawPublic

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

AI summary: A highly extensible personal AI assistant featuring three-layer memory and multi-channel integration.

Stars
37.9K
+160 today
Forks
3.3K
Watchers
112
Open issues
719
Open PRs
453
Contributors
~265
Commits
2.7K
Branches
4

TypeScriptApache-2.0Created Feb 24, 2026Last push 2d agoLatest release v2.3.0+311 stars this week+2K this month

Quick answers

What is QwenPaw?
A highly extensible personal AI assistant featuring three-layer memory and multi-channel integration.
What does QwenPaw do?
QwenPaw is a versatile personal AI assistant built on the AgentScope OS architecture, designed for deployment across local machines or cloud environments. It utilizes specialized QwenPaw-Flash models trained specifically for complex agentic tasks. The system features a unique three-layer memory architecture that preserves live working context, verbatim history, and distilled knowledge, ensuring details are never arbitrarily summarized away. Furthermore, it supports extensibility through an active plugin marketplace, kernel-level sandboxing for security, and seamless multi-channel integration across platforms like DingTalk, Discord, and Telegram.
Who is QwenPaw for?
AI researchers and developers focused on building multi-agent systems and evaluating their performance in complex scenarios. It provides essential tools for modeling and simulating multi-agent interactions.
How do I get started with QwenPaw?
pip install qwenpaw && qwenpaw init --defaults && qwenpaw app
How popular is QwenPaw on GitHub?
agentscope-ai/QwenPaw has 37,898 stars and 3,292 forks on GitHub, and gained 311 stars in the last 7 days.
What license does QwenPaw use?
agentscope-ai/QwenPaw is released under the Apache-2.0 license.

Star history

since Jul 28, 2026
010K20K30KJul 2026Sep 2026Oct 2026Nov 2026
37.9K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

5 recorded
  • Nov 14, 2026New release v2.3.0 (previously v2.2.2.post1).
  • Oct 27, 2026Primary language changed from Python to TypeScript.
  • Oct 25, 2026New release v2.2.2.post1 (previously v2.2.1).
  • Oct 22, 2026Primary language changed from TypeScript to Python.
  • Oct 4, 2026Previously tracked as agentscope-ai/CoPaw; its 1 daily snapshot and 5 trending appearances were merged into this profile. Stars: 29,700 on 2026-07-28 under the old name, 35,440 on 2026-10-04 (+5,740).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 30 commits2026-02-28: 21 commits2026-03-01: 0 commits2026-03-02: 26 commits2026-03-03: 20 commits2026-03-04: 27 commits2026-03-05: 28 commits2026-03-06: 23 commits2026-03-07: 1 commit2026-03-08: 12 commits2026-03-09: 21 commits2026-03-10: 27 commits2026-03-11: 22 commits2026-03-12: 17 commits2026-03-13: 12 commits2026-03-14: 3 commits2026-03-15: 5 commits2026-03-16: 22 commits2026-03-17: 34 commits2026-03-18: 35 commits2026-03-19: 34 commits2026-03-20: 22 commits2026-03-21: 2 commits2026-03-22: 1 commit2026-03-23: 29 commits2026-03-24: 28 commits2026-03-25: 21 commits2026-03-26: 12 commits2026-03-27: 17 commits2026-03-28: 11 commits2026-03-29: 15 commits2026-03-30: 48 commits2026-03-31: 41 commits2026-04-01: 16 commits2026-04-02: 18 commits2026-04-03: 11 commits2026-04-04: 4 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 10 commits2026-04-08: 23 commits2026-04-09: 21 commits2026-04-10: 2 commits2026-04-11: 0 commits2026-04-12: 4 commits2026-04-13: 27 commits2026-04-14: 16 commits2026-04-15: 22 commits2026-04-16: 25 commits2026-04-17: 18 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 28 commits2026-04-21: 17 commits2026-04-22: 24 commits2026-04-23: 23 commits2026-04-24: 26 commits2026-04-25: 2 commits2026-04-26: 0 commits2026-04-27: 16 commits2026-04-28: 15 commits2026-04-29: 6 commits2026-04-30: 8 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 2 commits2026-05-04: 1 commit2026-05-05: 0 commits2026-05-06: 13 commits2026-05-07: 13 commits2026-05-08: 15 commits2026-05-09: 19 commits2026-05-10: 0 commits2026-05-11: 12 commits2026-05-12: 16 commits2026-05-13: 14 commits2026-05-14: 14 commits2026-05-15: 12 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 5 commits2026-05-19: 29 commits2026-05-20: 13 commits2026-05-21: 15 commits2026-05-22: 7 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 12 commits2026-05-26: 6 commits2026-05-27: 12 commits2026-05-28: 8 commits2026-05-29: 15 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 7 commits2026-06-02: 6 commits2026-06-03: 12 commits2026-06-04: 12 commits2026-06-05: 4 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 8 commits2026-06-09: 13 commits2026-06-10: 24 commits2026-06-11: 12 commits2026-06-12: 8 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 11 commits2026-06-16: 18 commits2026-06-17: 18 commits2026-06-18: 10 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 6 commits2026-06-23: 24 commits2026-06-24: 9 commits2026-06-25: 40 commits2026-06-26: 14 commits2026-06-27: 0 commits2026-06-28: 3 commits2026-06-29: 22 commits2026-06-30: 30 commits2026-07-01: 16 commits2026-07-02: 22 commits2026-07-03: 10 commits2026-07-04: 1 commit2026-07-05: 1 commit2026-07-06: 13 commits2026-07-07: 13 commits2026-07-08: 13 commits2026-07-09: 26 commits2026-07-10: 23 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 30 commits2026-07-14: 18 commits2026-07-15: 12 commits2026-07-16: 18 commits2026-07-17: 20 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 7 commits2026-07-21: 19 commits2026-07-22: 10 commits2026-07-23: 15 commits2026-07-24: 9 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 14 commits2026-07-28: 9 commits2026-07-29: 10 commits2026-07-30: 16 commits2026-07-31: 12 commits2026-08-01: 0 commits2026-08-02: 1 commit2026-08-03: 11 commits2026-08-04: 16 commits2026-08-05: 8 commits2026-08-06: 32 commits2026-08-07: 11 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 14 commits2026-08-11: 21 commits2026-08-12: 12 commits2026-08-13: 22 commits2026-08-14: 5 commits2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 8 commits2026-08-18: 16 commits2026-08-19: 13 commits2026-08-20: 27 commits2026-08-21: 6 commits2026-08-22: 0 commits2026-08-23: 2 commits2026-08-24: 18 commits2026-08-25: 12 commits2026-08-26: 23 commits2026-08-27: 12 commits2026-08-28: 18 commits2026-08-29: 0 commits2026-08-30: 0 commits2026-08-31: 9 commits2026-09-01: 14 commits2026-09-02: 4 commits2026-09-03: 6 commits2026-09-04: 9 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 13 commits2026-09-08: 14 commits2026-09-09: 6 commits2026-09-10: 9 commits2026-09-11: 9 commits2026-09-12: 0 commits2026-09-13: 0 commits2026-09-14: 8 commits2026-09-15: 19 commits2026-09-16: 8 commits2026-09-17: 14 commits2026-09-18: 12 commits2026-09-19: 0 commits2026-09-20: 9 commits2026-09-21: 11 commits2026-09-22: 7 commits2026-09-23: 5 commits2026-09-24: 3 commits2026-09-25: 0 commits2026-09-26: 0 commits2026-09-27: 0 commits2026-09-28: 4 commits2026-09-29: 13 commits2026-09-30: 7 commits2026-10-01: 0 commits2026-10-02: 0 commits2026-10-03: 0 commits2026-10-04: 0 commits2026-10-05: 0 commits2026-10-06: 0 commits2026-10-07: 0 commits2026-10-08: 6 commits2026-10-09: 7 commits2026-10-10: 7 commits2026-10-11: 0 commits2026-10-12: 2 commits2026-10-13: 13 commits2026-10-14: 6 commits2026-10-15: 2 commits2026-10-16: 9 commits2026-10-17: 0 commits2026-10-18: 0 commits2026-10-19: 7 commits2026-10-20: 5 commits2026-10-21: 8 commits2026-10-22: 2 commits2026-10-23: 12 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 9 commits2026-10-27: 3 commits2026-10-28: 18 commits2026-10-29: 10 commits2026-10-30: 5 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 10 commits2026-11-03: 7 commits2026-11-04: 13 commits2026-11-05: 8 commits2026-11-06: 16 commits2026-11-07: 0 commits2026-11-08: 0 commits2026-11-09: 8 commits2026-11-10: 4 commits2026-11-11: 5 commits2026-11-12: 11 commits2026-11-13: 4 commits2026-11-14: 0 commits
2,708 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    37,898 stars

  • Very active

    2,708 commits in 52 weeks

  • Community-driven

    ~265 contributors

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    9 trending appearances

What QwenPaw does

QwenPaw is a versatile personal AI assistant built on the AgentScope OS architecture, designed for deployment across local machines or cloud environments. It utilizes specialized QwenPaw-Flash models trained specifically for complex agentic tasks. The system features a unique three-layer memory architecture that preserves live working context, verbatim history, and distilled knowledge, ensuring details are never arbitrarily summarized away. Furthermore, it supports extensibility through an active plugin marketplace, kernel-level sandboxing for security, and seamless multi-channel integration across platforms like DingTalk, Discord, and Telegram.

AI researchers and developers focused on building multi-agent systems and evaluating their performance in complex scenarios. It provides essential tools for modeling and simulating multi-agent interactions.

  • Three-Layer Memory Architecture: Employs ReMe v0.4.0 to maintain a live working context, full verbatim history, and distilled knowledge with on-demand recall.
  • Flexible Deployment: Supports execution via a built-in local runtime without API keys, as well as integration with Ollama and numerous cloud providers.
  • Kernel-Level Security: Incorporates rigorous Sandboxing, Tool Guards, and Skill Scanners to block dangerous commands before execution.
  • Multi-Channel Support: Designed to connect and operate simultaneously across various communication channels via a unified backend instance.
  • Integrated Coding Mode: Features a three-panel Web IDE with file trees, diff previews, and structural code search capabilities.

Where teams use it

Persistent Personal Assistance

Users rely on the assistant for long-term projects, utilizing its three-layer memory to accurately recall specific details from months prior.

Local Agent Deployment

Privacy-conscious teams deploy the assistant entirely on local hardware using the built-in runtime to safely process sensitive company data.

Multi-Platform Operations

Developers configure the assistant to push alerts, summaries, or AI-generated content to Discord, Telegram, and internal tools simultaneously.

Custom Workflow Automation

Engineers combine built-in capabilities, marketplace plugins, and scheduled tasks into complex workflows tailored to their specific operational needs.

Getting started: pip install qwenpaw && qwenpaw init --defaults && qwenpaw app

README

main branch

QwenPaw

GitHub Repo PyPI Documentation Python Version Last Commit License Code Style GitHub Stars GitHub Forks DeepWiki Discord X DingTalk AgentScope Platform

agentscope-ai%2FQwenPaw | Trendshift

[Documentation] [中文] [日本語] [Русский]

QwenPaw Logo

Works for you, grows with you.

Your personal AI assistant — deploy locally or in the cloud, extend with Skills & Plugins, connect across every channel.

Never forgets Three-layer memory — live working context, full verbatim history, and a self-evolving personal knowledge base powered by ReMe. Conversations and resources continuously become readable, editable, searchable, and linked Markdown memory.
Local or cloud, runs free QwenPaw-Flash models (2B / 4B / 9B / 35B-A3B / 27B) trained for agent tasks. Built-in QwenPaw Local runtime — no API key, no cloud dependency. Also works with Ollama, LM Studio, or 14+ cloud providers.
Security built in Kernel-level Sandbox, Tool Guard, File Guard, Skill Scanner, and Access Policy. Dangerous commands are blocked before they run.
Multi-agent & parallel Spawn independent agents with their own memory and skills. Sub-agents at runtime. Agent Communication Protocol (ACP) for cross-system orchestration.
File workspace Unified file navigation, preview, editing, diffs, upload, and download across project and Agent files.
Extensible Skills for scheduling, documents, browser, news, and more. Plugin architecture with a marketplace. MCP integration for external tools. Combine them into purpose-built workflows.
Reachable anywhere DingTalk, Lark, WeChat, Discord, Telegram, iMessage, QQ — one instance, all channels. Console, TUI, and desktop app for direct access.
Yours, not ours Deploy locally — data stays on your machine. No third-party hosting, no data upload.
What you can do with QwenPaw
  • Automation & scheduling: Set up recurring tasks — news digests, report generation, multi-channel broadcasting — all on your schedule.
  • Code & development: Read, edit, review, and test code in your projects with the unified file workspace.
  • Document processing: Read, write, and convert PDF, Word, Excel, and PowerPoint files.
  • Information gathering: Search the web, follow subscriptions, summarize videos, and find what you need in your personal knowledge base.
  • Multi-channel ops: Push alerts, summaries, or AI-generated content to DingTalk, Lark, Discord, Telegram, and more — simultaneously or per channel.
  • Custom workflows: Combine built-in capabilities, plugins, and scheduled tasks into workflows tailored to your needs.

News

  • [2026-11-11] v2.3.0 | Piccolo local decision models, QwenPaw Community integration, Advisor Mode for collaboration between larger and smaller models, Code Mode; plugin-system refactoring, the plugin SDK, and channels as plugins; image memory, tag browsing, and Console and desktop multi-window improvements. v2.3.0 Release Notes →

  • [2026-10-15] v2.2.2 | Console updates, new QwenPaw-Flash models covering 9B/27B/35B-A3B, PawPort for importing Codex/Qoder data, Creator 2.0.1, and Data 0.3.0. v2.2.2 Release Notes →

  • [2026-09-10] v2.2.1 | Creator 1.2 blueprint workbench, per-Agent model routing, and unified environment management. v2.2.1 Release Notes →

  • [2026-09-03] v2.2.0 | Self-hosted multi-user QwenPaw Hub, QwenPaw Mail, native QwenPaw Data, unified model routing, Creator 1.1, a unified marketplace, and major Console, Skills, channel, and reliability improvements. v2.2.0 Release Notes →

  • [2026-08-13] v2.1.0 | QwenPaw OS Shell, unified Files workspace, QwenPaw Creator, Codex/Qoder Agent integration, Browser-use, Computer-use, workspace checkpoints, and long-running conversation continuity. v2.1.0 Release Notes →

All release notes →


Table of Contents


Quick Start

Option 1: Pip Install

If you prefer managing Python yourself (requires Python >= 3.11, < 3.14):

pip install qwenpaw
qwenpaw init --defaults
qwenpaw app

Then open the Console in your browser at http://127.0.0.1:8088/ to configure your model. To chat in DingTalk, Lark, WeChat, etc., see the Channel setup documentation.

Codex and Qoder backends are optional plugins installed separately in Settings → Plugins. The full extra excludes their SDKs; transitional codex/qoder extras only prepare dependencies. Existing users should follow the prepared migration instructions before restarting an upgraded host.

Console


Option 2: Script Install

No Python setup required, one command installs everything. The script will automatically download uv (Python package manager), create a virtual environment, and install QwenPaw with all dependencies (including Node.js and frontend assets). Note: May not work in restricted network environments or corporate firewalls.

macOS / Linux:

curl -fsSL https://qwenpaw.agentscope.io/install.sh | bash

Windows (CMD):

curl -fsSL https://qwenpaw.agentscope.io/install.bat -o install.bat && install.bat

Windows (PowerShell):

irm https://qwenpaw.agentscope.io/install.ps1 | iex

Note: The installer will automatically check the status of uv. If it is not installed, it will attempt to download and configure it automatically. If the automatic installation fails, please follow the on-screen prompts or execute python -m pip install -U uv, then rerun the installer.

⚠️ Special Notice for Windows Enterprise LTSC Users

If you are using Windows LTSC or an enterprise environment governed by strict security policies, PowerShell may run in Constrained Language Mode, potentially causing the following issue:

  1. If using CMD (.bat): Script executes successfully but fails to write to Path

    The script completes file installation. Due to Constrained Language Mode, it cannot automatically update environment variables. Manually configure as follows:

    • Locate the installation directory:
      • Check if uv is available: Enter uv --version in CMD. If a version number appears, only configure the QwenPaw path. If you receive the prompt 'uv' is not recognized as an internal or external command, operable program or batch file, configure both paths.
      • uv path (choose one based on installation location; use if uv fails): Typically %USERPROFILE%\.local\bin, %USERPROFILE%\AppData\Local\uv, or the Scripts folder within your Python installation directory
      • QwenPaw path: Typically located at %USERPROFILE%\.qwenpaw\bin.
    • Manually add to the system's Path environment variable:
      • Press Win + R, type sysdm.cpl and press Enter to open System Properties.
      • Click “Advanced” -> “Environment Variables”.
      • Under “System variables”, locate and select Path, then click “Edit”.
      • Click “New”, enter both directory paths sequentially, then click OK to save.
  2. If using PowerShell (.ps1): Script execution interrupted

Due to Constrained Language Mode, the script may fail to automatically download uv.

  • Manually install uv: Refer to the GitHub Release to download uv.exe and place it in %USERPROFILE%\.local\bin or %USERPROFILE%\AppData\Local\uv; or ensure Python is installed and run python -m pip install -U uv.
  • Configure uv environment variables: Add the uv directory and %USERPROFILE%\.qwenpaw\bin to your system's Path variable.
  • Re-run the installation: Open a new terminal and execute the installation script again to complete the QwenPaw installation.
  • Configure the QwenPaw environment variable: Add %USERPROFILE%\.qwenpaw\bin to your system's Path variable.

Once installed, open a new terminal and run:

qwenpaw init --defaults   # or: qwenpaw init (interactive)
qwenpaw app
Install options

macOS / Linux:

# Install a specific version
curl -fsSL ... | bash -s -- --version 1.1.0

# Install from source (dev/testing)
curl -fsSL ... | bash -s -- --from-source

# Upgrade — just re-run the installer
curl -fsSL ... | bash

# Uninstall
qwenpaw uninstall          # keeps config and data
qwenpaw uninstall --purge  # removes everything

Windows (PowerShell):

# Install a specific version
irm ... | iex; .\install.ps1 -Version 1.1.12

# Install from source (dev/testing)
.\install.ps1 -FromSource

# Upgrade — just re-run the installer
irm ... | iex

# Uninstall
qwenpaw uninstall          # keeps config and data
qwenpaw uninstall --purge  # removes everything

Option 3: Docker

Images are on Docker Hub (agentscope/qwenpaw). Image tags: latest (stable); pre (PyPI pre-release).

docker pull agentscope/qwenpaw:latest
docker run -p 127.0.0.1:8088:8088 \
  -v qwenpaw-data:/app/working \
  -v qwenpaw-secrets:/app/working.secret \
  -v qwenpaw-backups:/app/working.backups \
  agentscope/qwenpaw:latest

Also available on Alibaba Cloud Container Registry (ACR) for users in China: agentscope-registry.ap-southeast-1.cr.aliyuncs.com/agentscope/qwenpaw (same tags).

Then open http://127.0.0.1:8088/ for the Console. Config, memory, and skills are stored in the qwenpaw-data volume; model provider settings and API keys are in the qwenpaw-secrets volume; backup archives are stored in the qwenpaw-backups volume. To pass API keys (e.g. DASHSCOPE_API_KEY), add -e VAR=value or --env-file .env to docker run.

Connecting to Ollama or other services on the host machine

Inside a Docker container, localhost refers to the container itself, not your host machine. If you run Ollama (or other model services) on the host and want QwenPaw in Docker to reach them, use one of these approaches:

Option A — Explicit host binding (all platforms):

docker run -p 127.0.0.1:8088:8088 \
  --add-host=host.docker.internal:host-gateway \
  -v qwenpaw-data:/app/working \
  -v qwenpaw-secrets:/app/working.secret \
  -v qwenpaw-backups:/app/working.backups \
  agentscope/qwenpaw:latest

Then in QwenPaw Settings → Models, change the Base URL to http://host.docker.internal:<port> — for example, http://host.docker.internal:11434 for Ollama, or http://host.docker.internal:1234/v1 for LM Studio.

Option B — Host networking (Linux only):

docker run --network=host \
  -v qwenpaw-data:/app/working \
  -v qwenpaw-secrets:/app/working.secret \
  -v qwenpaw-backups:/app/working.backups \
  agentscope/qwenpaw:latest

No port mapping (-p) is needed; the container shares the host network directly. Note that all container ports are exposed on the host, which may cause conflicts if the port is already in use.

The image is built from scratch. To build the image yourself, please refer to the Build Docker image section in scripts/README.md, and then push to your registry.


Option 4: Deploy on Alibaba Cloud ECS

To run QwenPaw on Alibaba Cloud (ECS), use the one-click deployment: open the QwenPaw on Alibaba Cloud (ECS) deployment link and follow the prompts. For step-by-step instructions, see Alibaba Cloud Developer: Deploy your AI assistant in 3 minutes.


Option 5: AgentScope Platform

AgentScope Platform provides one-click cloud QwenPaw deployment, plugin sharing, and a Skill marketplace. Free, 7/24 online.


Option 6: Using ModelScope

ModelScope Studio also supports cloud QwenPaw deployment. Note: set your Studio to non-public so others cannot control your QwenPaw.


Option 7: Desktop Application (Beta)

Beta Notice: The desktop application is currently in Beta testing phase with the following known limitations:

  • Incomplete compatibility testing: Not fully tested across all system versions and hardware configurations
  • Potential performance issues: Startup time, memory usage, and other performance aspects may need further optimization
  • Features under development: Some features may be unstable or missing

If you're not comfortable with command-line tools, you can download and use QwenPaw's desktop application without manually configuring Python environments or running commands.

Download

Download the desktop app (Tauri build) from the official download page:

  • Windows: QwenPaw-Tauri-<version>-Windows-setup.exe
  • macOS: QwenPaw-Tauri-<version>-macOS.zip (Apple Silicon recommended)
Features
  • ✅ Zero configuration: Download and double-click to run, no need to install Python or configure environment variables
  • ✅ Cross-platform: Supports Windows 10+ and macOS 14+
  • ✅ Visual interface: Automatically opens the app window, no need to manually enter addresses
  • ⚠️ Beta stage: Features are continuously being improved, feedback welcome
First Launch

Important: The first launch may take 10-60 seconds (depending on your system configuration). The application needs to initialize the Python environment and load dependencies. Please wait patiently for the window to open automatically.

macOS: Bypass System Security Restrictions

When you download the QwenPaw macOS app from Releases, macOS may show: "Apple cannot verify that 'QwenPaw' contains no malicious software". This happens because the app is not notarized. You can still open it as follows:

  • Right-click to open (recommended) Right-click (or Control+click) the QwenPaw app → Open → in the dialog click Open again. This tells Gatekeeper you trust the app; after that you can double-click to launch as usual.

  • Allow in System Settings If it is still blocked, go to System Settings → Privacy & Security, scroll to the message like "QwenPaw was blocked because it is from an unidentified developer", and click Open Anyway or Allow.

  • Remove quarantine attribute (not recommended for most users) In Terminal run: xattr -cr "/Applications/QwenPaw Desktop.app" (or use the path to the .app after unzipping). This clears the "downloaded from the internet" quarantine flag so the warning usually does not appear, but is less safe and controllable than using Right-click → Open.

For detailed usage instructions, troubleshooting, and common issues, see the Desktop Application Guide.


What's Next?

After installation, configure your model in Console → Settings → Models, then explore:


Terminal UI (TUI)

Prefer to stay in the terminal? Run qwenpaw to open a full-screen chat TUI that drives the same agent as the Console and the IM Channels — same memory, skills, MCP tools, and sessions — without leaving your keyboard.

qwenpaw                     # open a chat with the active agent
qwenpaw tui --resume <id>   # resume a previous session
qwenpaw .                   # start in the current repo (Coding Mode)

It supports streaming replies, slash commands (/help, /resume, /theme, plus the agent's own /model, /clear, …), pasting files/long text as attachments, and inline tool-permission prompts. See the Terminal UI guide for details.

QwenPaw TUI


API Key

If you use a cloud LLM API (e.g., DashScope / Qwen, OpenAI, Anthropic, Google Gemini, DeepSeek, Kimi, OpenRouter, and more), you must configure an API key before chatting. QwenPaw will not work until a valid key is set. See the official docs for details.

How to configure:

  1. Console (recommended) — After running qwenpaw app, open http://127.0.0.1:8088/ → Settings → Models. Choose a provider, enter the API Key, and enable that provider and model.
  2. qwenpaw init — When you run qwenpaw init, it will guide you through configuring the LLM provider and API key. Follow the prompts to choose a provider and enter your key.
  3. Environment variable — For DashScope you can set DASHSCOPE_API_KEY in your shell or in a .env file in the working directory.

Tools that need extra keys (e.g. TAVILY_API_KEY for web search) can be set in Console Settings → Environment variables, see Config for details.

Using local models only? If you use Local Models (QwenPaw Local / Ollama / LM Studio), you do not need any API key.

Local Models

QwenPaw can run LLMs entirely on your machine — no API keys or cloud services required. See the official docs for details.

QwenPaw also provides the QwenPaw-Flash series — purpose-trained 2B / 4B / 9B / 35B-A3B / 27B models for agent scenarios, with Q4 and Q8 quantizations. Available on ModelScope and Hugging Face.

Backend Best for Install
QwenPaw Local (llama.cpp) Cross-platform (macOS / Linux / Windows) Built-in; click "Download" in the web UI. Supports QwenPaw-Flash with hardware-aware recommendations.
Ollama Cross-platform (requires Ollama service) Install and start Ollama; set context length ≥ 32k.
LM Studio Cross-platform (requires LM Studio) Install and start LM Studio; enable Local Server.

Security Features

QwenPaw includes five core security layers:

  • Sandbox — Kernel-level execution isolation using Seatbelt (macOS), Bubblewrap / Landlock (Linux), and AppContainer (Windows). Shell commands run inside a restricted filesystem view.
  • Tool Guard — YAML rule engine with ShellEvasionGuardian inspects every tool call before execution, detecting command injection, path traversal, reverse shells, and obfuscated attacks. Configurable approval levels: STRICT / SMART / AUTO / OFF.
  • File Guard — Independent of Tool Guard; blocks agent access to sensitive files and directories (default-protects ~/.qwenpaw.secret/, ~/.ssh, etc.).
  • Skill Scanner — Pre-activation scanning with block / warn / off modes and whitelist support. Detects prompt injection, hardcoded secrets, data exfiltration, and more.
  • Access Policy — Declarative access rules that allow, deny, or request human approval for each capability call, with tool-level granularity and source-aware matching.

See Security for details.


Documentation

Topic Description
Introduction What QwenPaw is and how to use it
Quick start Install and run (local or ModelScope Studio)
Console Web UI: chat and agent configuration
Terminal UI (TUI) Full-screen terminal chat, same agent as Console
Desktop App Desktop application installation and usage
Models Configure cloud, local, and custom providers
Channels DingTalk, Lark, QQ, Discord, iMessage, and more
Skills Extend and customize capabilities
Plugins Plugin system and Plugin Market
MCP Manage MCP clients
Persona Agent personality customization (SOUL / PROFILE)
Memory Self-evolving personal knowledge base built on local, editable, searchable, and linked Markdown memory, powered by ReMe
ReMe Documentation Official ReMe overview and documentation
Memory-Evolving & Proactive Agent memory evolution and proactive interaction
Context Scroll-based context management
Magic commands Control conversation state without waiting for the AI
Heartbeat Scheduled check-in and digest
Cron / Scheduled Tasks Scheduled tasks and automation
Multi-Agent Create multiple agents and enable collaboration
Security Sandbox, tool guard, file guard, skill scanner, access policy
Backup & Restore Data backup and recovery
Config & working dir Working directory and config file
REST API HTTP API for integration and automation
ACP Integration Agent Communication Protocol integration
CLI Init, cron jobs, skills, clean
Agent Team Practice Multi-agent team deployment guide
FAQ Common questions and troubleshooting

In Console chat, select assistant response text and click Quote to follow-up to append an editable quote to your draft. See Console.

In the Console, /clear and a successful /new leave the chat empty when you reopen it or reload the page. See Magic commands.

Full documentation: qwenpaw.agentscope.io/docs


FAQ

For common questions, troubleshooting tips, and known issues, please visit the FAQ page.


Roadmap

Area Item Status
Release Evaluation Rankings Evaluate each release and update the public leaderboard. In Progress
Lightweight Codebase Split non-core components into plugins that can be installed and enabled on demand to reduce installation and runtime costs. In Progress
Decision Model Integration Integrate Jev and other decision models for collaborative decision-making. In Progress
Deep UI/UX Optimization Improve navigation, interactions, and visuals across screen sizes. In Progress

Status: In Progress — actively being worked on.


Contributing

QwenPaw evolves through open collaboration, and we welcome all forms of contribution! Check the Roadmap above to find areas that interest you, and read CONTRIBUTING to get started. We particularly welcome:

  • Horizontal expansion — new channels, model providers, skills, MCPs.
  • Existing feature extension & refinement — display and interaction improvements, download hints, Windows path compatibility, etc.

Join GitHub Discussions to discuss ideas or pick up tasks.


Install From Source

git clone https://github.com/agentscope-ai/QwenPaw.git
cd QwenPaw

# Build console frontend first (required for web UI)
cd console && npm ci && npm run build
cd ..

# Copy console build output to package directory
mkdir -p src/qwenpaw/console
cp -R console/dist/. src/qwenpaw/console/

# Install Python package
pip install -e .
  • Dev (tests, formatting): pip install -e ".[dev,test,full]"
  • Then: Run qwenpaw init --defaults, then qwenpaw app.

Note for updates: When updating to a new major version after git pull, please also rebuild the frontend, reinstall the package (pip install -e .), restart qwenpaw app, and clear your browser cache with Ctrl+Shift+R (or Cmd+Shift+R on macOS).


Why QwenPaw?

QwenPaw stands for Qwen Personal Agent Workstation, and also embodies the wisdom of Qwen and the warmth of a Paw. We hope it is not a cold tool, but an intelligent and warm "little paw" always ready to help—a most intuitive partner in your digital life.


Built By

AgentScope team · AgentScope · AgentScope Runtime · ReMe


Contact Us

Discord X (Twitter) DingTalk RedNote
Discord X DingTalk RedNote

Staying Ahead

Star QwenPaw

Star QwenPaw on GitHub and be instantly notified of new releases.


Telemetry

QwenPaw collects anonymous usage data during qwenpaw init to help us understand our user base and prioritize improvements. Data is sent once per version — when you upgrade QwenPaw, telemetry is re-collected so we can track version adoption.

What we collect:

  • QwenPaw version (e.g., 1.1.12)
  • Install method (pip, Docker, or desktop app)
  • OS and version (e.g., macOS 14.0, Ubuntu 22.04)
  • Python version (e.g., 3.13)
  • CPU architecture (e.g., x86_64, arm64)
  • GPU availability (yes/no)

What we do NOT collect: No personal data, no files, no credentials, no IP addresses, no identifiable information.

When running qwenpaw init interactively, you will be asked whether to opt in. If you choose --defaults, telemetry is accepted automatically. The prompt appears once per version and never affects QwenPaw's functionality.


License

QwenPaw is released under the Apache License 2.0.


Contributors

All thanks to our contributors:

Contributors
View on GitHub

Recent activity

commits and pull requests

Releases and announcements

133 total
  1. v2.3.0v2.3.0Nov 11, 2026704 downloads

    ## What's Changed ## ✨ Added **Piccolo Local Decision Models** - 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 downloads. Review and compaction remain opt-in; the local runtime serves one model at a time ([#8463](https://github.com/agentscope-ai/QwenPaw/pull/8463), [#8573](https://github.com/agentscope-ai/QwenPaw/pull/8573)) **QwenPaw Community** - Browse, sort, and comment on QwenPaw Community posts from the Console, draft resource-linked issue reports with model assistance, and open the community editor. Connect an account to sync selected message categories to the Inbox and desktop notifications ([#7903](https://github.com/agentscope-ai/QwenPaw/pull/7903)) **Console & Desktop** - 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 ([#8239](https://github.com/agentscope-ai/QwenPaw/pull/8239), [#8248](https://github.com/agentscope-ai/QwenPaw/pull/8248)) - Add an unread-only filter to Inb

  2. v2.3.0-beta.4v2.3.0-beta.4Nov 10, 2026pre-release100 downloads

    ## What's Changed * fix(channels): preserve plugin dependencies across updates and fix channel startup by @Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/8653 * fix(plugins): recover interrupted additive dependency installations by @Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/8659 * chore: bump the version to 2.3.0b4 by @lalaliat in https://github.com/agentscope-ai/QwenPaw/pull/8665 * feat(community): support remote password login with saved credentials by @Osier-Yi in https://github.com/agentscope-ai/QwenPaw/pull/8664 **Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.3.0-beta.3...v2.3.0-beta.4

  3. v2.3.0-beta.3v2.3.0-beta.3Nov 9, 2026pre-release57 downloads

    ## What's Changed * docs(memory): add separate bilingual blogs for multimodal memory and Memory Tags by @wang-qisen in https://github.com/agentscope-ai/QwenPaw/pull/8506 * fix(channels): resolve desktop plugin installation and repair failures by @Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/8509 * fix(agents): drop empty media blocks before formatting requests by @BeiMu-new in https://github.com/agentscope-ai/QwenPaw/pull/8066 * fix(creator): release 2.0.4 with media and probe hardening by @xuanrui-L in https://github.com/agentscope-ai/QwenPaw/pull/8529 * chore: bump the version to 2.3.0b3 by @cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8546 * fix(console): persist market install provenance so 'Update All' covers third-party plugins (#8176) by @RerankerGuo in https://github.com/agentscope-ai/QwenPaw/pull/8231 * feat(tools): use AnySearch as the default web search provider by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8536 * fix(sqlite): skip completed startup migrations and snapshot live backups by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8541 * fix(console): repair settings search navigation and indexing b

  4. v2.3.0-beta.2v2.3.0-beta.2Nov 2, 2026pre-release473 downloads

    ## What's Changed * fix(console): limit agent skill selection to creation by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8448 * fix(console): compact media preview error cards by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8451 * Fix/console browser usability by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8452 * fix(providers): honor declared thinking disable wire by @wuwenbo0626 in https://github.com/agentscope-ai/QwenPaw/pull/8436 * fix(plugins): remove SDK-specific dependency checks and simplify tests by @lalaliat in https://github.com/agentscope-ai/QwenPaw/pull/8462 * docs: remove duplicated pip install section from quickstart by @Heipa1 in https://github.com/agentscope-ai/QwenPaw/pull/8454 * fix(mail): do not append domain when account name is already a full address by @Frank-zhu2000 in https://github.com/agentscope-ai/QwenPaw/pull/8438 * fix(creator): keep review decisions publishable on long Windows paths by @JasonBuildAI in https://github.com/agentscope-ai/QwenPaw/pull/8167 * fix(creator): close project logging before directory delete by @Li-john1021 in https://github.com/agentscope-ai/QwenPaw/pull/8210 *

  5. v2.3.0-beta.1v2.3.0-beta.1Oct 27, 2026pre-release405 downloads

    ## What's Changed * fix(console): restore interactive HTML previews by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8245 * feat(tools): optional Tavily API key via credential store (#8174) by @Li-john1021 in https://github.com/agentscope-ai/QwenPaw/pull/8204 * fix(plugin): align hub plugin catalog and installed state by @Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/8261 * fix(console): clear chat input on submission by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8272 * refactor(console): polish web search config guards and error icon by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8271 * feat(chat): support inline UI plugins and scoped message submission by @Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/8239 * fix(console): unblock config editors and polish chat controls by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8263 * fix(console): update chat dependency for navigation by @zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8273 * feat(models): add TypeSafe decision model configuration by @jinglinpeng in https://github.com/agentscope-ai/QwenPaw/pull/8205 * f

Code frequency

additions and deletions
+684.6K-684.6KWeek of 2026-02-22: +613,094 linesWeek of 2026-02-22: -10,049 linesWeek of 2026-03-01: +21,028 linesWeek of 2026-03-01: -4,563 linesWeek of 2026-03-08: +30,426 linesWeek of 2026-03-08: -11,604 linesWeek of 2026-03-15: +37,860 linesWeek of 2026-03-15: -7,472 linesWeek of 2026-03-22: +48,475 linesWeek of 2026-03-22: -18,249 linesWeek of 2026-03-29: +56,777 linesWeek of 2026-03-29: -30,180 linesWeek of 2026-04-05: +18,973 linesWeek of 2026-04-05: -7,290 linesWeek of 2026-04-12: +684,600 linesWeek of 2026-04-12: -628,319 linesWeek of 2026-04-19: +198,722 linesWeek of 2026-04-19: -91,823 linesWeek of 2026-04-26: +3,507 linesWeek of 2026-04-26: -814 linesWeek of 2026-05-03: +22,482 linesWeek of 2026-05-03: -7,815 linesWeek of 2026-05-10: +62,979 linesWeek of 2026-05-10: -12,057 linesWeek of 2026-05-17: +28,330 linesWeek of 2026-05-17: -4,304 linesWeek of 2026-05-24: +70,359 linesWeek of 2026-05-24: -4,182 linesWeek of 2026-05-31: +20,375 linesWeek of 2026-05-31: -8,791 linesWeek of 2026-06-07: +56,603 linesWeek of 2026-06-07: -15,555 linesWeek of 2026-06-14: +39,042 linesWeek of 2026-06-14: -7,889 linesWeek of 2026-06-21: +37,896 linesWeek of 2026-06-21: -8,505 linesWeek of 2026-06-28: +54,538 linesWeek of 2026-06-28: -16,777 linesWeek of 2026-07-05: +30,132 linesWeek of 2026-07-05: -4,540 linesWeek of 2026-07-12: +31,202 linesWeek of 2026-07-12: -7,418 linesWeek of 2026-07-19: +48,470 linesWeek of 2026-07-19: -7,132 linesWeek of 2026-07-26: +252,104 linesWeek of 2026-07-26: -20,371 linesWeek of 2026-08-02: +149,860 linesWeek of 2026-08-02: -29,470 linesWeek of 2026-08-09: +67,531 linesWeek of 2026-08-09: -27,195 linesWeek of 2026-08-16: +138,882 linesWeek of 2026-08-16: -14,334 linesWeek of 2026-08-23: +141,223 linesWeek of 2026-08-23: -67,953 linesWeek of 2026-08-30: +32,055 linesWeek of 2026-08-30: -2,659 linesWeek of 2026-09-06: +165,018 linesWeek of 2026-09-06: -38,340 linesWeek of 2026-09-13: +71,068 linesWeek of 2026-09-13: -25,346 linesWeek of 2026-09-20: +104,307 linesWeek of 2026-09-20: -10,196 linesWeek of 2026-09-27: +46,049 linesWeek of 2026-09-27: -14,776 linesWeek of 2026-10-04: +6,808 linesWeek of 2026-10-04: -642 linesWeek of 2026-10-11: +26,460 linesWeek of 2026-10-11: -3,898 linesWeek of 2026-10-18: +112,270 linesWeek of 2026-10-18: -10,731 linesWeek of 2026-10-25: +206,378 linesWeek of 2026-10-25: -133,779 linesWeek of 2026-11-01: +45,515 linesWeek of 2026-11-01: -8,094 linesWeek of 2026-11-08: +54,560 linesWeek of 2026-11-08: -14,539 linesFeb 22, 2026Nov 8, 2026
+3.8M lines added, -1.3M removed over the last year.

Commits per week

last 52 weeks
1540Week of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 51 commitsWeek of 2026-03-01: 125 commitsWeek of 2026-03-08: 114 commitsWeek of 2026-03-15: 154 commitsWeek of 2026-03-22: 119 commitsWeek of 2026-03-29: 153 commitsWeek of 2026-04-05: 56 commitsWeek of 2026-04-12: 112 commitsWeek of 2026-04-19: 120 commitsWeek of 2026-04-26: 45 commitsWeek of 2026-05-03: 63 commitsWeek of 2026-05-10: 68 commitsWeek of 2026-05-17: 69 commitsWeek of 2026-05-24: 53 commitsWeek of 2026-05-31: 41 commitsWeek of 2026-06-07: 65 commitsWeek of 2026-06-14: 57 commitsWeek of 2026-06-21: 93 commitsWeek of 2026-06-28: 104 commitsWeek of 2026-07-05: 89 commitsWeek of 2026-07-12: 98 commitsWeek of 2026-07-19: 60 commitsWeek of 2026-07-26: 61 commitsWeek of 2026-08-02: 79 commitsWeek of 2026-08-09: 74 commitsWeek of 2026-08-16: 70 commitsWeek of 2026-08-23: 85 commitsWeek of 2026-08-30: 42 commitsWeek of 2026-09-06: 51 commitsWeek of 2026-09-13: 61 commitsWeek of 2026-09-20: 35 commitsWeek of 2026-09-27: 24 commitsWeek of 2026-10-04: 20 commitsWeek of 2026-10-11: 32 commitsWeek of 2026-10-18: 34 commitsWeek of 2026-10-25: 45 commitsWeek of 2026-11-01: 54 commitsWeek of 2026-11-08: 32 commitsNov 16, 2025Nov 8, 2026
2.7K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 1 commitsSun 1:00 — 0 commitsSun 2:00 — 0 commitsSun 3:00 — 0 commitsSun 4:00 — 0 commitsSun 5:00 — 0 commitsSun 6:00 — 0 commitsSun 7:00 — 2 commitsSun 8:00 — 0 commitsSun 9:00 — 1 commitsSun 10:00 — 4 commitsSun 11:00 — 4 commitsSun 12:00 — 2 commitsSun 13:00 — 5 commitsSun 14:00 — 4 commitsSun 15:00 — 5 commitsSun 16:00 — 2 commitsSun 17:00 — 3 commitsSun 18:00 — 2 commitsSun 19:00 — 4 commitsSun 20:00 — 5 commitsSun 21:00 — 4 commitsSun 22:00 — 3 commitsSun 23:00 — 4 commitsMon 0:00 — 1 commitsMon 1:00 — 0 commitsMon 2:00 — 2 commitsMon 3:00 — 1 commitsMon 4:00 — 2 commitsMon 5:00 — 0 commitsMon 6:00 — 0 commitsMon 7:00 — 0 commitsMon 8:00 — 1 commitsMon 9:00 — 5 commitsMon 10:00 — 38 commitsMon 11:00 — 37 commitsMon 12:00 — 24 commitsMon 13:00 — 23 commitsMon 14:00 — 41 commitsMon 15:00 — 51 commitsMon 16:00 — 57 commitsMon 17:00 — 62 commitsMon 18:00 — 31 commitsMon 19:00 — 36 commitsMon 20:00 — 36 commitsMon 21:00 — 21 commitsMon 22:00 — 20 commitsMon 23:00 — 11 commitsTue 0:00 — 11 commitsTue 1:00 — 5 commitsTue 2:00 — 2 commitsTue 3:00 — 0 commitsTue 4:00 — 1 commitsTue 5:00 — 0 commitsTue 6:00 — 0 commitsTue 7:00 — 0 commitsTue 8:00 — 3 commitsTue 9:00 — 3 commitsTue 10:00 — 46 commitsTue 11:00 — 55 commitsTue 12:00 — 17 commitsTue 13:00 — 16 commitsTue 14:00 — 99 commitsTue 15:00 — 63 commitsTue 16:00 — 52 commitsTue 17:00 — 70 commitsTue 18:00 — 36 commitsTue 19:00 — 31 commitsTue 20:00 — 23 commitsTue 21:00 — 17 commitsTue 22:00 — 19 commitsTue 23:00 — 6 commitsWed 0:00 — 10 commitsWed 1:00 — 1 commitsWed 2:00 — 1 commitsWed 3:00 — 0 commitsWed 4:00 — 1 commitsWed 5:00 — 0 commitsWed 6:00 — 1 commitsWed 7:00 — 2 commitsWed 8:00 — 1 commitsWed 9:00 — 10 commitsWed 10:00 — 29 commitsWed 11:00 — 31 commitsWed 12:00 — 14 commitsWed 13:00 — 20 commitsWed 14:00 — 62 commitsWed 15:00 — 52 commitsWed 16:00 — 77 commitsWed 17:00 — 51 commitsWed 18:00 — 46 commitsWed 19:00 — 35 commitsWed 20:00 — 20 commitsWed 21:00 — 15 commitsWed 22:00 — 18 commitsWed 23:00 — 12 commitsThu 0:00 — 3 commitsThu 1:00 — 2 commitsThu 2:00 — 1 commitsThu 3:00 — 1 commitsThu 4:00 — 1 commitsThu 5:00 — 0 commitsThu 6:00 — 1 commitsThu 7:00 — 1 commitsThu 8:00 — 0 commitsThu 9:00 — 12 commitsThu 10:00 — 50 commitsThu 11:00 — 60 commitsThu 12:00 — 25 commitsThu 13:00 — 18 commitsThu 14:00 — 40 commitsThu 15:00 — 73 commitsThu 16:00 — 71 commitsThu 17:00 — 82 commitsThu 18:00 — 41 commitsThu 19:00 — 28 commitsThu 20:00 — 28 commitsThu 21:00 — 19 commitsThu 22:00 — 10 commitsThu 23:00 — 5 commitsFri 0:00 — 4 commitsFri 1:00 — 2 commitsFri 2:00 — 2 commitsFri 3:00 — 1 commitsFri 4:00 — 2 commitsFri 5:00 — 0 commitsFri 6:00 — 0 commitsFri 7:00 — 1 commitsFri 8:00 — 1 commitsFri 9:00 — 6 commitsFri 10:00 — 34 commitsFri 11:00 — 35 commitsFri 12:00 — 23 commitsFri 13:00 — 20 commitsFri 14:00 — 41 commitsFri 15:00 — 44 commitsFri 16:00 — 46 commitsFri 17:00 — 79 commitsFri 18:00 — 47 commitsFri 19:00 — 14 commitsFri 20:00 — 12 commitsFri 21:00 — 14 commitsFri 22:00 — 5 commitsFri 23:00 — 2 commitsSat 0:00 — 2 commitsSat 1:00 — 4 commitsSat 2:00 — 1 commitsSat 3:00 — 0 commitsSat 4:00 — 0 commitsSat 5:00 — 0 commitsSat 6:00 — 0 commitsSat 7:00 — 0 commitsSat 8:00 — 1 commitsSat 9:00 — 1 commitsSat 10:00 — 5 commitsSat 11:00 — 5 commitsSat 12:00 — 5 commitsSat 13:00 — 5 commitsSat 14:00 — 8 commitsSat 15:00 — 3 commitsSat 16:00 — 2 commitsSat 17:00 — 5 commitsSat 18:00 — 9 commitsSat 19:00 — 1 commitsSat 20:00 — 3 commitsSat 21:00 — 1 commitsSat 22:00 — 3 commitsSat 23:00 — 7 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Jul 27, 2026daily#20+3
Jul 26, 2026daily#1+7
Jul 25, 2026daily#14+4
Jun 18, 2026daily#22+12
Mar 4, 2026daily#16+219
Mar 3, 2026daily#5+477
Mar 2, 2026daily#5+501
Mar 1, 2026daily#8+415
Feb 28, 2026daily#6+664
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • awesome-selfhosted/awesome-selfhosted

    A list of Free Software network services and web applications which can be hosted on your own servers

    339K stars

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript