QwenPaw：可本地或云端部署的个人 AI 助手

你的个人 AI 助手——可在本地或云端部署，通过 Skills 和 Plugins 扩展能力，并连接到所有渠道。

|
---|---
永不遗忘 | 三层记忆体系——实时工作上下文、完整逐字历史记录，以及由 ReMe 驱动的自我演进个人知识库。对话和资源会持续转化为可阅读、可编辑、可搜索、可关联的 Markdown 记忆。
本地或云端，免费运行 | 面向 Agent 任务训练的 QwenPaw-Flash 模型（2B / 4B / 9B）。内置 QwenPaw Local 本地运行时——无需 API key，也不依赖云端。还支持 Ollama、LM Studio 或超过 14 家云端服务商。
内置安全机制 | 内核级 Sandbox、Tool Guard、File Guard、Skill Scanner 和 Access Policy。危险命令会在执行前被拦截。
多 Agent 与并行执行 | 可创建拥有独立记忆和技能的 Agent。支持运行时子 Agent，以及用于跨系统编排的 Agent Communication Protocol（ACP）。
Coding Mode | 三栏式 Web IDE，包含文件树、差异预览和聊天功能。内置跳转至定义、查找引用和结构化代码搜索。
可扩展 | 提供日程安排、文档、浏览器、新闻等 Skills。采用带有市场的插件架构，并支持通过 MCP 集成外部工具。可将这些能力组合为面向特定用途的工作流。
随处可达 | 钉钉、飞书、微信、Discord、Telegram、iMessage、QQ——一个实例，覆盖所有渠道。还可通过 Console、TUI 和桌面应用直接访问。
属于你，而非我们 | 可本地部署——数据留在你的机器上。无需第三方托管，也不会上传数据。
你可以使用 QwenPaw 做什么

• 自动化与调度：设置周期性任务——新闻摘要、报告生成、多渠道广播——均可按你的计划执行。
• 代码与开发：读取、编辑、审查和测试项目代码；Coding Mode 可帮助你快速定位和理解代码。
• 文档处理：读取、编写和转换 PDF、Word、Excel 和 PowerPoint 文件。
• 信息收集：搜索网页、追踪订阅、总结视频内容，并在个人知识库中找到所需信息。
• 多渠道运营：将告警、摘要或 AI 生成内容推送至钉钉、飞书、Discord、Telegram 等渠道——可同时推送，也可按渠道分别推送。
• 自定义工作流：将内置能力、插件和定时任务组合为满足你需求的工作流。

---

• [2026-07-24] v2.0.1 | PawApp 小程序平台、用户可编辑的 Agent Modes、Oh-My-Paw 插件、ReMe 记忆增强、桌面端 UX 改进等。v2.0.1 发布说明 →

• [2026-07-10] v2.0.0 — QwenPaw 2.0 正式发布 🎉 | 基于 AgentScope 2.0 彻底重写，引入 Agent OS 架构、Loop Engineering、Scroll Context、ReMe v0.4 自我演进个人知识库，以及内置 Terminal UI。

亮点	新增内容
Agent OS — Workspace	每个 Agent 包含三大支柱：Resources（磁盘上透明可见）、Governance（允许/拒绝/询问/沙箱）、Sandbox（macOS / Linux / Windows）。
Agent OS — Drivers	协议无关的 MCP / A2A / ACP 连接器层，具备加密凭据和逐调用策略闸门。
Loop Engineering	高级 Agent 循环模板（Coding Mode、Mission Mode，未来将推出更多），支持可组合的审批闸门。
Scroll Context	每一轮对话均会持久化；被逐出的轮次会建立索引并支持按需召回——不会因摘要而丢失信息。
ReMe v0.4 自我演进个人知识库	持续将对话和资源转化为可阅读、可编辑、可搜索、可关联的 Markdown 记忆。
Terminal UI（TUI）	全屏终端聊天——与 Console 和各渠道使用相同的 Agent、记忆和会话。

基于 Agent OS，我们将推出开箱即用的 QwenPaw 应用——例如 QwenPaw Creator 和 QwenPaw Insight——敬请期待。v2.0.0 发布说明 →

• [2026-06-17] v1.1.12 — Models 页面改版与 Simple Mode | 重新设计的 Models 页面支持服务商聚合；新增 Simple Mode，提供更简洁的导航体验。v1.1.12 发布说明 →

• [2026-06-11] AgentScope Platform 已上线——提供免费的 QwenPaw 部署、插件分享和 Skill 市场。立即体验 →

• [2026-06-10] v1.1.11 ——免费模型 OAuth、Plugin Market、MCP 工具白名单。v1.1.11 发布说明 →

全部发布说明 →

---

---

如果你希望自行管理 Python（要求 Python >= 3.11，< 3.14）：

pip install qwenpaw
qwenpaw init --defaults
qwenpaw app

随后在浏览器中打开 Console：http://127.0.0.1:8088/，以配置模型。如需在钉钉、飞书、微信等渠道聊天，请参阅 渠道设置 文档。

---

无需配置 Python，一条命令即可安装全部内容。该脚本会自动下载 uv（Python 包管理器）、创建虚拟环境，并安装 QwenPaw 及其全部依赖项（包括 Node.js 和前端资源）。注意：在受限网络环境或企业防火墙下可能无法正常运行。

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

注意：安装程序会自动检查 uv 的状态。如果尚未安装，它将尝试自动下载和配置 uv。若自动安装失败，请遵循屏幕提示，或执行 python -m pip install -U uv，然后重新运行安装程序。

⚠️ Windows Enterprise LTSC 用户特别说明

如果你使用 Windows LTSC，或处于采用严格安全策略管理的企业环境中，PowerShell 可能运行在 Constrained Language Mode 下，从而可能导致以下问题：

1. 使用 CMD（.bat）时：脚本可成功执行，但无法写入 Path

该脚本会完成文件安装，但由于 Constrained Language Mode，无法自动更新环境变量。请按以下步骤手动配置：

 * **定位安装目录**：
   * 检查 `uv` 是否可用：在 CMD 中输入 `uv --version`。如果显示版本号，**仅需配置 QwenPaw 路径**。如果收到提示 `'uv' is not recognized as an internal or external command, operable program or batch file,`，则需配置两个路径。
   * uv 路径（根据安装位置选择其一；若 `uv` 无法运行则使用）：通常为 `%USERPROFILE%\.local\bin`、`%USERPROFILE%\AppData\Local\uv`，或 Python 安装目录中的 `Scripts` 文件夹。
   * QwenPaw 路径：通常位于 `%USERPROFILE%\.qwenpaw\bin`。
 * **手动添加至系统的 Path 环境变量**：
   * 按下 `Win + R`，输入 `sysdm.cpl` 并按 Enter，打开“系统属性”。
   * 点击“高级” -> “环境变量”。
   * 在“系统变量”中找到并选中 `Path`，然后点击“编辑”。
   * 点击“新建”，依次输入两个目录路径，然后点击“确定”保存。

2. 使用 PowerShell（.ps1）时：脚本执行中断

由于 Constrained Language Mode，脚本可能无法自动下载 uv。

• 手动安装 uv：参阅 GitHub Release 下载 uv.exe，并将其放入 %USERPROFILE%\.local\bin 或 %USERPROFILE%\AppData\Local\uv；或者确保已安装 Python，并运行 python -m pip install -U uv。
• 配置 uv 环境变量：将 uv 所在目录和 %USERPROFILE%\.qwenpaw\bin 添加至系统的 Path 变量。
• 重新运行安装程序：打开新的终端，再次执行安装脚本以完成 QwenPaw 安装。
• 配置 QwenPaw 环境变量：将 %USERPROFILE%\.qwenpaw\bin 添加至系统的 Path 变量。

安装完成后，打开一个新终端并运行：

qwenpaw init --defaults   # 或者：qwenpaw init（交互式）
qwenpaw app

安装选项

macOS / Linux：

# 安装指定版本
curl -fsSL ... | bash -s -- --version 1.1.0

# 从源代码安装（开发/测试）
curl -fsSL ... | bash -s -- --from-source

# 升级——只需重新运行安装程序
curl -fsSL ... | bash

# 卸载
qwenpaw uninstall          # 保留配置和数据
qwenpaw uninstall --purge  # 删除全部内容

Windows（PowerShell）：

# 安装指定版本
irm ... | iex; .\install.ps1 -Version 1.1.12

# 从源代码安装（开发/测试）
.\install.ps1 -FromSource

# 升级——只需重新运行安装程序
irm ... | iex

# 卸载
qwenpaw uninstall          # 保留配置和数据
qwenpaw uninstall --purge  # 删除全部内容

---

镜像发布在 Docker Hub（agentscope/qwenpaw）。镜像标签：latest（稳定版）；pre（PyPI 预发布版）。

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

面向中国用户，阿里云容器镜像服务（ACR）也提供镜像：agentscope-registry.ap-southeast-1.cr.aliyuncs.com/agentscope/qwenpaw（使用相同标签）。

随后打开 http://127.0.0.1:8088/ 进入 Console。配置、记忆和 Skills 存储在 qwenpaw-data 卷中；模型服务商设置和 API keys 存储在 qwenpaw-secrets 卷中；备份归档存储在 qwenpaw-backups 卷中。如需传入 API keys（例如 DASHSCOPE_API_KEY），请向 docker run 添加 -e VAR=value 或 --env-file .env。

连接到宿主机上的 Ollama 或其他服务

在 Docker 容器内，localhost 指向容器自身，而不是宿主机。如果你在宿主机上运行 Ollama（或其他模型服务），并希望 Docker 中的 QwenPaw 访问它们，可采用以下方式之一：

选项 A ——显式绑定宿主机（所有平台）：

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

随后在 QwenPaw Settings → Models 中，将 Base URL 改为 http://host.docker.internal:<port>——例如，Ollama 使用 http://host.docker.internal:11434，LM Studio 使用 http://host.docker.internal:1234/v1。

选项 B ——宿主机网络模式（仅限 Linux）：

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

无需端口映射（-p）；容器会直接共享宿主机网络。请注意，所有容器端口都会暴露在宿主机上，如果端口已被占用，可能会造成冲突。

该镜像从零构建。如需自行构建镜像，请参阅 scripts/README.md 中的 构建 Docker 镜像 部分，然后推送至你的镜像仓库。

---

选项 4：部署至阿里云 ECS

如需在阿里云（ECS）上运行 QwenPaw，请使用一键部署：打开 QwenPaw 阿里云（ECS）部署链接，然后按提示操作。有关分步说明，请参阅 阿里云开发者：3 分钟部署你的 AI 助手。

---

选项 5：AgentScope Platform

AgentScope Platform 提供 QwenPaw 一键云端部署、插件分享和 Skill 市场。免费，7×24 小时在线。

---

选项 6：使用 ModelScope

ModelScope Studio 同样支持云端部署 QwenPaw。注意：请将你的 Studio 设为非公开，以避免其他人控制你的 QwenPaw。

---

选项 7：桌面应用（Beta）

Beta 提示：桌面应用目前处于 Beta 测试阶段，存在以下已知限制：

• 兼容性测试尚不完整：尚未在全部系统版本和硬件配置上完成充分测试。
• 可能存在性能问题：启动时间、内存占用及其他性能表现可能仍需进一步优化。
• 功能仍在开发中：部分功能可能不稳定或尚未提供。

如果你不习惯使用命令行工具，可以下载并使用 QwenPaw 的桌面应用。

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) 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.
Coding Mode | Three-panel Web IDE with file tree, diff preview, and chat. Jump-to-definition, find-references, and structural code search built in.
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; Coding Mode helps you quickly find and understand code.
• 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.

---

• [2026-07-24] v2.0.1 | PawApp mini-app platform, user-editable Agent Modes, Oh-My-Paw plugins, ReMe memory enhancements, desktop UX improvements, and more. v2.0.1 Release Notes →

• [2026-07-10] v2.0.0 — QwenPaw 2.0 Official Release 🎉 | An AgentScope 2.0 based ground-up rewrite delivering the Agent OS architecture, Loop Engineering, Scroll Context, ReMe v0.4 Self-evolving Personal Knowledge Base, and a bundled Terminal UI.

Highlight	What's new
Agent OS — Workspace	Three pillars per agent: Resources (transparent on disk), Governance (allow/deny/ask/sandbox), Sandbox (macOS / Linux / Windows).
Agent OS — Drivers	Protocol-neutral MCP / A2A / ACP connector layer with encrypted credentials and per-call policy gate.
Loop Engineering	Advanced agent loop templates (Coding Mode, Mission Mode, more to come) with composable approval gates.
Scroll Context	Every turn persisted; evicted turns indexed with on-demand recall — nothing summarized away.
ReMe v0.4 Self-evolving Personal Knowledge Base	Continuously turns conversations and resources into readable, editable, searchable, and linked Markdown memory.
Terminal UI (TUI)	Full-screen terminal chat — same agent, memory, and sessions as Console and channels.

Built on Agent OS, we will be launching out-of-box QwenPaw applications — such as QwenPaw Creator and QwenPaw Insight — stay tuned. v2.0.0 Release Notes →

• [2026-06-17] v1.1.12 — Models Page Overhaul & Simple Mode | Redesigned Models page with provider aggregation; new Simple Mode for streamlined navigation. v1.1.12 Release Notes →

• [2026-06-11] AgentScope Platform is live — Free QwenPaw deployment, plugin sharing, and Skill marketplace. Try it now →

• [2026-06-10] v1.1.11 — Free Model OAuth, Plugin Market, MCP Tool Whitelisting. v1.1.11 Release Notes →

All release notes →

---

---

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.

---

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 toPath

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.
• Configureuv 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 theQwenPaw 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

---

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 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)

• ✅ 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

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.

---

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

---

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.

---

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.

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 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.

---

QwenPaw includes four 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.

See Security for details.

---

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
Coding Mode	Three-panel Web IDE for code-centric tasks
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

Full documentation: qwenpaw.agentscope.io/docs

---

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

---

Area	Item	Status
Horizontal Expansion	More channels, models, skills, MCPs — community contributions welcome	Seeking Contributors
Existing Feature Extension	Display optimization, download hints, Windows path compatibility, etc. — community contributions welcome	Seeking Contributors
Models	Multi-model switching	In Progress
Browser-use	Support Chrome extension	In Progress
Long-term Memory	Personal knowledge base	In Progress
QwenPaw Application	QwenPaw Creator	In Progress
QwenPaw Insight	In Progress
Multi-agent	Compatibility with existing agents (e.g. Claude Code)	Planned
Group chat	Planned
Subagent visualization	Planned

Status: In Progress — actively being worked on; Planned — queued or under design, also welcome contributions; Seeking Contributors — we strongly encourage community contributions.

---

QwenPaw evolves through open collaboration, and we welcome all forms of contribution! Check the Roadmap above (especially items marked Seeking Contributors) 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.

---

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).

---

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.

---

AgentScope team · AgentScope · AgentScope Runtime · ReMe

---

---

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

---

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.

---

QwenPaw is released under the Apache License 2.0.

---

All thanks to our contributors: