登录

qwen-code

QwenLMApache-2.0活跃维护

跑在终端里的开源 AI 编码 Agent，能理解代码库、执行命令并自动完成改代码、修 bug 等开发任务。

An open-source AI coding agent that lives in your terminal.

v0.27.1发布于 2026-11-09 13:30 UTC29,158star +84 / 7 天3,337fork同步于 2026-11-10 11:21 UTC
编码 Agent终端工具AI 编程命令行MCP
对比 GitHub 官网agenticaiai-agentai-codingcli

怎么上手

由 README 提炼，执行前请确认
原文 
curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash
npm install -g @qwen-code/qwen-code@latest
硬件要求按 README 说明

README 未说明显存或 GPU 要求；可通过 Ollama、vLLM 接入本地模型，但未列出具体型号。

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

开源终端 AI 编码代理，支持多模型协议与多端接入

跑在终端里的开源 AI 编码 Agent，能理解代码库、执行命令并自动完成改代码、修 bug 等开发任务。

核心能力

  • 内置 SubAgents、Agent Teams 与动态工作流
  • 支持 OpenAI、Anthropic、Gemini、Qwen 及本地模型运行时切换
  • 提供 Auto-Memory、Auto-Skills、Hooks 与内置 Skills
  • 可用 qwen serve 启动守护进程，多客户端共享会话
  • 提供 VS Code、JetBrains、Zed 插件与 IM 渠道集成

容易踩的坑

NPM 安装需 Node.js 22 及以上；安装后需重启终端使环境变量生效；守护进程默认监听 127.0.0.1:4170 且无鉴权，共享主机需设 QWEN_SERVER_TOKEN 并加 --require-auth。

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本v0.27.1
全部 release
  1. sdk-typescript-v0.1.31SDK TypeScript Release v0.1.312026-11-09 · 2026-11-09 14:50 UTC
    查看更新说明

    Bundled CLI Version

    This SDK release bundles CLI version: 0.27.1

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.27.0

    Source: CLI built from source (same branch/ref as SDK)

    See commit history for changes.

  2. desktop-v0.27.1Qwen Code Desktop v0.27.12026-11-09 · 2026-11-09 14:24 UTC
    查看更新说明

    What's Changed

  3. v0.27.1Release v0.27.1最新正式版2026-11-09 · 2026-11-09 13:30 UTC

    Highlights

    See the complete change list below.

    Breaking Changes

    No known breaking changes.

    Complete Change List

    Features

    • feat(core): name the active shell in the startup context (#16491) by @2SinceJuly
    • feat(qqbot): add opt-in forwardBotMessages for bot-authored messages (#15904) by @Eric-GoodBoy-Tech
    • feat(agents): make default background execution configurable (#15178) by @ZedingZhang
    • feat(cli): enable LSP through a user-scoped setting and env pair (#14613) by @BigDaddy1337
    • feat(channels): give bound sessions role guidance without operator templates (#16576) by @wenshao
    • feat(ci): switch review runner day pool to a numeric count over hz runners (#16544) by @yiliang114
    • feat(ci): support HTTP proxy in ephemeral runner containers (#16592) by @yiliang114
    • feat(serve): add the daemon PR watch store foundation (#16590) by @wenshao
    • feat(acp-bridge): expose replay projection watermark (#16538) by @chiga0
    • feat(web-shell): expose Channel delivery targets in Scheduled Tasks (#16524) by @jkxiao
    • feat(web-shell): add workspace collapse controls and drag sorting (#16197) by @ytahdn
    • feat(web-shell): label rendered artifact cards Preview and strengthen the details UI-language prompt (#16587) by @wenshao
    • feat(daemon): expose last user prompt time and session sorting (#14654) by @samuelhsin
    • feat(serve): observe bound PRs and detect state transitions behind an off switch (#16611) by @wenshao
    • feat(managed-agent): add Session resource and agent-trace diagnostics (#16640) by @doudouOUC
    • feat(ci): give the autofix address agent failed-check evidence (#16659) by @wenshao
    • feat(serve): drain bound-PR watch pending transitions behind an off switch (#16656) by @wenshao
    • feat(managed-agent): persist Session model statistics and request context (#16641) by @doudouOUC
    • feat(managed-agent): add archive and MCP self-service installation (#16500) by @doudouOUC
    • feat(channels): protect the GitHub mention lane from watch budget spend (#16701) by @wenshao
    • feat(managed-agent): persist Session execution diagnostics (#16642) by @doudouOUC
    • feat(channels): deliver bound-PR comments to every session that did not post them (#16602) by @wenshao
    • feat(web-shell): show scheduled task workspace when the picker is hidden (#16630) by @jkxiao
    • feat(mods): run the prompts a Mod submits in the OpenTUI terminal (#16426) by @qqqys
    • feat(web-shell): add sidebar multi-select with bulk pin and archive (#16702) by @deggs7
    • feat(managed-agent): add opt-in personal memory backed by Mem0 (#16488) by @doudouOUC

    Bug Fixes

    • fix(core): share one gh runner and name an unusable view directory ([#16545](https://github.co
  4. sdk-typescript-v0.1.29SDK TypeScript Release v0.1.292026-11-09 · 2026-11-09 02:08 UTC
    查看更新说明

    Backfilled release for npm-published version 0.1.29 (original workflow run 42249484215 failed at the release-branch push step after npm publish succeeded; see #16490).

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.9

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.8

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.6

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.4

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.3

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.2

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.1

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.26.0

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.25.3

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.25.2

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.25.1

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.25.0

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.24.7

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.24.6

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.24.5

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.24.3

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.24.1

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.23.3

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.23.2

    Source: CLI built from source (same branch/ref as SDK)

    Bundled CLI Version

    This SDK release bundles CLI version: 0.23.1

    Source: CLI built from source (same branch/ref as SDK)

    Highlights

    The bundled CLI 0.23.0 includes two fixes requested in #11022:

    • Managed memory availability now respects the memory.enableManagedAutoMemory setting (#6941). Hosts that disable managed auto memory no longer see remember/dream requests admitted or managed-memory instructions in the system prompt; local patches can be removed.
    • Size-triggered microcompaction now clears old tool results toward a low watermark (#8464), so it no longer rewrites another part of the conversation prefix on every subsequent turn. Provider prompt-cache reuse is preserved across long tool-heavy sessions, reducing cached-input cost.

    Bundled CLI Version

    This SDK release bundles CLI version: 0.23.0

    Source: latest stable CLI from npm

    Bundled CLI Version

    This SDK release bundles CLI version: 0.19.10

    Source: latest stable CLI from npm

    Bundled CLI Version

    This SDK release bundles CLI version: 0.15.3

    Source: latest stable CLI from npm

    Bundled CLI Version

    This SDK release bundles CLI version: 0.13.1

    Source: latest stable CLI from npm

    Backfilled release for npm-published version 0.1.5 (original workflow failed before GitHub release creation).

    What's Changed

  5. v0.26.9-nightly.20261107.65e1f1aeaaRelease v0.26.9-nightly.20261107.65e1f1aeaapre-release2026-11-08 · 2026-11-08 01:39 UTC
    查看更新说明

    What's Changed

    New Contributors

    Full Changelog: https://github.com/QwenLM/qwen-code/compare/v0.27.0...v0.26.9-nightly.20261107.65e1f1aeaa

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    npm version License Node.js Version Downloads

    The open-source AI coding agent for your terminal, editor, desktop, browser, and chat.

    中文 | Deutsch | français | 日本語 | Русский | Português (Brasil) | 한국어

    Qwen Code in the terminal, desktop app, browser, editor, and chat, with VS Code, Zed, JetBrains, Telegram, DingTalk, WeChat, and Feishu integrations

    Why Qwen Code?

    • Agentic out of the box — Auto-Memory, Auto-Skills, SubAgents, Agent Teams, and MCP. Dynamic workflows, zero setup.
    • Open-source, inside and out — The framework and the Qwen models are open-source. They evolve together. No vendor lock-in.
    • Multi-protocol — Supports OpenAI, Anthropic, Gemini, and Qwen APIs. Any third-party provider or local model (Ollama / vLLM). Switch at runtime.
    • Beyond the terminal — IDE plugins, Desktop app, Web UI, SDKs, and chat integrations (Telegram / DingTalk / WeChat / Feishu).

    [!TIP] Qwen Code is actively iterating on itself — using its own agent and models to file issues, submit PRs, review code, and run tests. Powered by the community, driven by AI.

    Installation

    Linux / macOS:

    curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash

    Windows:

    irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex

    Restart your terminal after installation to ensure environment variables take effect.

    NPM (requires Node.js 22+):

    npm install -g @qwen-code/qwen-code@latest

    Homebrew (macOS / Linux):

    brew install qwen-code

    Quick Start

    Open a terminal in your project and start Qwen Code:

    cd /path/to/your-project
qwen

    Inside the session, run /auth and choose Qwen Account with Subscription to sign in with your Plus or Pro subscription, or configure a provider with an API key. Then try:

    Explain this repository and show me where to start.

    See the Authentication Guide and Settings Reference for detailed setup.

    Qwen Code terminal interface

    How to Use Qwen Code

    Choose the interface that fits your workflow:

    InterfaceGet started
    TerminalRun qwen in your project — see Quick Start.
    DesktopDownload Qwen Code Desktop for macOS, Windows, and Linux.
    WebRun qwen serve --open to open the Web UI in your browser. (experimental)
    EditorSet up VS Code, Zed, or JetBrains.
    ChatConnect Telegram, DingTalk, WeChat, or Feishu, then run qwen channel start.

    For automation and custom integrations:

    import asyncio

from qwen_code_sdk import is_sdk_result_message, query


async def main() -> None:
    result = query(
        "Summarize the repository layout.",
        {
            "cwd": "/path/to/project",
            "path_to_qwen_executable": "qwen",
        },
    )

    async for message in result:
        if is_sdk_result_message(message):
            print(message["result"])


asyncio.run(main())

    Daemon Mode

    Run Qwen Code as a long-lived service when you want browser, editor, SDK, and automation clients to share agent sessions without each starting a separate process. The daemon provides the built-in Web Shell and an HTTP + SSE API, supports multiple workspaces, and lets clients reconnect to active sessions.

    Start it in the foreground and open the Web Shell:

    qwen serve --open

    The default address is http://127.0.0.1:4170. To run and manage it in the background instead:

    qwen daemon start
qwen daemon status
qwen daemon logs -f
qwen daemon stop

    By default, the daemon listens on loopback without bearer authentication; any local process that can reach it can use the full API, including code execution. On shared or untrusted hosts, set QWEN_SERVER_TOKEN and use --require-auth. See the Daemon guide for workspaces, authentication, remote access, and the API.

    Capabilities

    If you know Claude Code, you already know Qwen Code — and then some. We've put significant effort into bringing Qwen Code to feature parity with Claude Code, improving both breadth and reliability across the board.

    FeatureQwen CodeClaude Code
    SubAgents, Agent Teams, Dynamic Workflows✓✓
    Auto-Memory, Auto-Skills, Hooks✓✓
    Built-in Skills (/review, /batch, /loop, /bugfix…)✓✓
    MCP, Plan Mode, LSP Integration✓✓
    Auto Mode, Sandbox, Git Worktrees✓✓
    Computer Use (desktop automation)✓✓
    IDE Plugins (VS Code / JetBrains / Zed)✓✓
    SDK✓✓
    Headless Mode, Session Management✓✓
    Open-source — model and framework✓—
    Multi-protocol (OpenAI / Anthropic / Gemini / Qwen + any provider)✓—
    Agent Arena (multi-model head-to-head on same task)✓—
    Daemon Mode — qwen serve (multi-client shared agent)✓—
    IM Channels (Telegram / DingTalk / WeChat / Feishu)✓—

    Qwen Code Evaluation

    On SWE-bench Verified, seven Qwen Code versions scored 76.40%–77.80% on average using the same Qwen 3.7 Max model (500 tasks, three trials per version).

    Average SWE-bench Verified scores by Qwen Code version: 0.0.14, 77.80%; 0.1.0, 76.73%; 0.5.0, 76.60%; 0.10.0, 76.47%; 0.15.0, 77.67%; 0.19.0, 76.40%; 0.22.0, 77.33%.

    Full results and evaluation configuration →

    Ecosystem

    • Qwen Code Desktop — Official desktop app for macOS, Windows, and Linux

    • AionUi — A modern GUI for command-line AI tools including Qwen Code

    • Gemini CLI Desktop — A cross-platform desktop/web/mobile UI for Qwen Code

    • qwen-audio-agent — Realtime full-duplex voice frontend for Qwen Code over ACP — talk hands-free with barge-in and a local wake word

    • 🦞 Qwen Code Claw — Let other agents (Claude, Codex, etc.) delegate coding tasks to Qwen Code via ACP. Paste this prompt into your agent:

    Use Qwen Code as a coding agent. First, fetch and read this skill reference:
https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/.qwen/skills/qwen-code-claw/SKILL.md
Then follow the instructions inside to install, authenticate, and use Qwen Code via acpx for all coding tasks.
    • Aliyun Model Studio CLI — Official CLI for Aliyun's AI platform (bailian-cli). Extends Qwen Code with image/video generation, knowledge retrieval, app orchestration, and model deployment

    Privacy

    See the Terms of Service and Privacy Notice, including Chrome extension and Browser Use data handling.

    Contributing

    Contributions are welcome! See CONTRIBUTING.md for guidelines.

    Acknowledgments

    This project was originally based on Google Gemini CLI v0.8.2. We gratefully acknowledge the Gemini CLI team's excellent work. Starting from Qwen Code v0.1, we stopped syncing with upstream and began independent development as a multi-protocol, multi-platform agent framework with deep integrations for Qwen models and beyond.

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    claude-code
    anthropics·TypeScript

    终端里的智能编码助手，能理解你的代码库，用自然语言帮你执行日常任务、解释复杂代码、处理 git 工作流，让写代码更快。

    编码助手+4编码 Agent
    155154+32725kv2.1.3212026-11-10 08:39 UTC
    cc-switch
    farion1231·Rust

    跨平台桌面客户端，把 Claude Code、Codex、OpenCode、DeepSeek Harness 等多个 AI 编程助手集中到一个界面里统一管理和切换，省去来回折腾配置。

    AI 编程助手+4编码 Agent
    153244+78810kv4.0.282026-11-10 02:19 UTC
    caveman
    JuliusBrussee·Go

    给编码 Agent 用的代理和技能，让模型用「原始人式」极简表达回答，砍掉约 65% 的 token 消耗。

    token 压缩+4编码 Agent
    118770+7196.9kv4.1.02026-11-09 01:48 UTC
    OpenHands
    OpenHands·TypeScript

    一个能自主写代码、改 bug、跑命令的 AI 开发代理，把大模型接入真实开发环境，让编码任务从对话直接落到执行。

    编码代理+4编码 Agent
    93107+25412kv1.37.02026-11-10 10:48 UTC