Qwen Code

Free plan AndroidAPIExtensioniPhoneLinuxMac+3

What Qwen Code is

Qwen Code is a free, open-source coding agent that runs in a terminal. It can plan, write, debug and refactor code; read and modify local files; run shell commands; fetch web content; and use those results in coding requests. Skills, SubAgents, Plan Mode and approval controls support agent workflows. It works with OpenAI-compatible, Anthropic, Google Gemini, Vertex AI, Alibaba Cloud, custom and self-hosted model endpoints, with runtime model switching. MCP connects external tools, databases, APIs and workflows through local stdio, SSE or streamable HTTP. Integrations include VS Code-compatible editors, Google Drive, Figma, Slack, Jira and messaging channels such as Telegram, WeChat, DingTalk and Feishu. Extensions can package prompts, MCP servers, subagents, skills and commands. Headless mode supports CI/CD tasks. The project uses an Apache-2.0 license and offers self-hosting. Node.js 22 or later is required for npm installation. Usage statistics are enabled by default but can be disabled.

Who it suits

Qwen Code suits developers who want an open-source terminal agent with multiple model providers, MCP connections, editor integrations and self-hosting. It also fits CI/CD workflows that need headless coding tasks.

What it does well

Plans, writes, debugs and refactors code
Supports multiple model and self-hosted endpoints
MCP connects tools, databases and workflows
Headless mode supports CI/CD tasks
Apache-2.0 open-source project

What to know first

Qwen OAuth free tier ended 2026-04-15
npm installation requires Node.js 22 or later
Linux sandbox enforcement is partial
Usage statistics are enabled by default

Verdict

Qwen Code offers broad agent, provider and integration support without a listed subscription price. Developers should review authentication changes, sandbox limits and privacy settings before deploying it.

Facts from Qwen Code's own pages

Agent features: Its listed capabilities include subagents, agent teams, dynamic workflows, automatic memory and skills, hooks, code review, plan mode, and sandboxing. · github.com, 7 Oct 2026
Authentication availability: The documentation says the Qwen OAuth free tier was discontinued on 2026-04-15 and recommends using a currently supported authentication provider for new setups. · qwenlm.github.io, 7 Oct 2026
Automation: Qwen Code can run in headless mode for CI/CD workflows, including GitHub Actions tasks such as replying to issues, reviewing code, and submitting pull requests. · qwenlm.github.io, 7 Oct 2026
Browser support: Browser Use requires macOS or Linux, Chrome 125 or later, Qwen Code 0.24.2 or later, and a separately installed Chrome extension. · qwenlm.github.io, 7 Oct 2026
Coding tasks: It can read and modify local files, run shell commands, fetch web content, and use those results to answer coding requests. · qwenlm.github.io, 7 Oct 2026
Editor and chat integrations: The project lists integrations for VS Code, JetBrains, Zed, Telegram, DingTalk, WeChat, and Feishu. · github.com, 7 Oct 2026
Extensions: Extensions can package prompts, MCP servers, subagents, skills, and custom commands, and the docs say compatible extensions can be installed from several other ecosystems. · qwenlm.github.io, 7 Oct 2026
IDE support: The IDE integration documentation supports Visual Studio Code and editors that support VS Code extensions, with workspace context and native diff review. · qwenlm.github.io, 7 Oct 2026
Installation requirement: The npm installation requires Node.js 22 or later. · github.com, 7 Oct 2026
Installation requirements: The overview provides installers for Windows, macOS, and Linux and says the npm fallback requires Node.js 22 or later. · qwenlm.github.io, 7 Oct 2026
Integrations: The overview describes integrations with Google Drive, Figma, Slack, and Jira through MCP, and the documentation lists messaging channels including Telegram, WeChat, QQ, DingTalk, WeCom, and Feishu. · qwenlm.github.io, 7 Oct 2026
License and pricing: The repository identifies the project as open source and lists an Apache-2.0 license; the opened pages did not state a Qwen Code subscription price. · github.com, 7 Oct 2026
MCP integrations: It connects to external tools, databases, APIs, and workflows through MCP using local stdio, SSE, or streamable HTTP transports. · qwenlm.github.io, 7 Oct 2026
Model providers: It supports OpenAI-compatible providers, Anthropic, Google Gemini, Vertex AI, Alibaba Cloud, and custom or self-hosted endpoints, with model switching at runtime. · qwenlm.github.io, 7 Oct 2026
Platforms: The official repository offers desktop downloads for macOS, Windows, and Linux, a browser Web UI, and a VS Code extension. · github.com, 7 Oct 2026
Pricing: The product overview describes Qwen Code as open-source and free, but the documentation does not list a current product plan or price. · qwenlm.github.io, 7 Oct 2026
Privacy: Optional usage statistics may include command, performance, error, and feature data; Qwen Code says it does not collect code, prompts, or model responses as usage statistics. · qwenlm.github.io, 7 Oct 2026
Privacy controls: Usage statistics are enabled by default in the documented settings and can be disabled through settings or an environment variable. · qwenlm.github.io, 7 Oct 2026
Provider data handling: Qwen Code says it does not use prompts, code, or responses for model training; data handling depends on the selected AI provider’s policies. · qwenlm.github.io, 7 Oct 2026
Purpose: Qwen Code is an open-source AI coding agent available through terminal, editor, desktop, browser, and chat interfaces. · github.com, 7 Oct 2026
Safety controls: Qwen Code typically requests confirmation before sensitive file or shell actions and supports sandboxing tool execution. · qwenlm.github.io, 7 Oct 2026
Sandbox limits: The Linux sandbox documentation warns that Landlock provides partial enforcement and cannot enforce closed networking or hide explicit masked paths. · qwenlm.github.io, 7 Oct 2026
Security controls: The tool documentation says potentially sensitive actions typically require confirmation and describes sandboxing for tool execution. · qwenlm.github.io, 7 Oct 2026
Support: The documentation directs users to the Qwen Code issue tracker for questions and feedback. · qwenlm.github.io, 7 Oct 2026

Where Qwen Code stands on Freedom251

AI Code Generators#40 of 54
AI Code Generation Software#20 of 27