$ buildwith info qwen-code

Qwen Code

#10 in Coding Agents · Free / OSS

sources differ by section

Qwen Code is an open-source AI coding agent from the Qwen team (QwenLM on GitHub), released under the Apache-2.0 license. The README calls it the open-source AI coding agent for your terminal, editor, desktop, browser, and chat: it runs as the qwen command in a terminal, as integrations for VS Code, Zed and JetBrains, as a desktop app for macOS, Windows and Linux, as an experimental web UI through qwen serve, and through chat channels such as Telegram, DingTalk, WeChat and Feishu. A separate Qwen Code 1.0 Preview, tagged v1.0.0-preview on 2026-11-11, brings the agent harness capabilities of Qoder together with Qwen Code.

for Developers who want an open-source agent they can point at a Qwen Plus or Pro subscription, a QwenCloud or Alibaba ModelStudio plan or API key, a built-in third-party provider such as DeepSeek, Kimi or OpenRouter, or a custom OpenAI-, Anthropic- or Gemini-compatible endpoint, including a local server.

use this if you want an Apache-2.0 coding agent that runs in the terminal, your editor, a desktop app, a browser and chat apps, and can use Qwen, OpenAI, Anthropic, Gemini or local models.

open qwenlm.github.io ↗

Features

$ features --list

  • ›SubAgents for focused subtasks, plus experimental Agent Teams and Agent Arena, which runs the same task on several models in separate Git worktrees
  • ›Auto-Memory, built-in Skills such as /review, /batch and /bugfix, and session resume
  • ›MCP, lifecycle hooks, opt-in LSP integration, and Computer Use and Browser Use through native MCP tools
  • ›Plan mode and approval modes from per-call confirmation to auto-edit, a classifier-driven Auto Mode, or YOLO, with sandboxing and Git worktrees
  • ›Headless qwen -p for scripts and CI, TypeScript, Python and Java SDKs, and an experimental qwen serve daemon over HTTP + SSE
  • ›Goals (/goal) that keep working until a verifier accepts the result, and scheduled tasks with /loop and cron tools

Pricing

$ pricing --tiers

Open source

Free

Apache-2.0. No Qwen Code fee is listed; you pay for whichever model access you connect.

Model access

Provider rates

The /auth menu offers a Qwen account with a Plus or Pro subscription from chat.qwen.ai, QwenCloud (a Token Plan subscription or a pay-as-you-go API key), Alibaba ModelStudio (Coding Plan, Token Plan or API key), built-in third-party providers, or a custom provider. The auth docs do not list prices, and Qwen account sign-in requires an active Plus or Pro subscription.

Why this rank

$ diff --rank 10

Ranked #10 in coding agents, new to the list this week. Qwen Code has 30,746 GitHub stars on 2026-11-18, in the same range as Kilo Code and Crush, and it shipped 17 stable releases between 2026-10-19 and 2026-11-17. It sits below Kilo Code, which adds paid team plans and a managed model gateway, above Crush because Qwen Code is Apache-2.0 and covers editors, a desktop app and chat as well as the terminal, and above Aider because it is still shipping. These ranks are editorial; the scores are unmeasured placeholders and are not shown.

Strengths

$ strengths

  • ›30,746 GitHub stars and 3,554 forks on 2026-11-18. The repository was created 2025-06-26.
  • ›Fast release pace: 17 stable GitHub releases from 2026-10-19 to 2026-11-17, the latest v0.28.0.
  • ›Multi-protocol: OpenAI, Anthropic, Gemini and Qwen APIs, third-party providers, and local models through Ollama or vLLM, switchable at runtime.
  • ›Apache-2.0 license.

Limitations

$ limits

  • ›Several headline features are experimental or opt-in, including Agent Teams, Agent Arena, the web UI, the daemon and LSP integration.
  • ›The daemon listens on loopback without bearer authentication by default, so any local process that can reach it can use the full API, including code execution. The README says to set QWEN_SERVER_TOKEN and use --require-auth on shared or untrusted hosts.
  • ›Qwen Code 1.0 Preview lives on its own tag, separate from the main v0.x line the install instructions cover, so there are two versions to choose between.

Sources

$ sources --verified

$ buildwith alternatives qwen-code

  • #1 Claude CodePaid

    use this if you live in the terminal and want an agent that works across your whole repo.

  • #2 OpenAI CodexPaid

    use this if you want to hand off tasks to a cloud agent or run one locally via CLI.

  • #3 DevinPaid

    use this if you want an autonomous engineer that picks up tickets and opens PRs.

  • #4 FactoryPaid

    use this if you want a paid coding agent, Droid, that can run in the terminal, the IDE, the desktop app, or Slack, with team plans when you need them.

  • #5 Grok BuildFreemium

    use this if you want a full-screen terminal agent with plan mode, parallel subagents in their own worktrees and a headless mode for CI, included in the X Subscription plans, with Apache-2.0 source you can read.

  • #6 OpenCodeFree / OSS

    use this if you want an open-source coding agent in the terminal, desktop or IDE that runs on any model, including the Claude, ChatGPT or Copilot plan you already pay for.

  • #7 ClineFree / OSS

    use this if you want an open-source agent in the editor and the terminal, with plan-then-act approval, and you want to bring any model.

  • #8 gooseFree / OSS

    use this if you want an Apache-2.0 agent with a desktop app, a CLI and an API that runs on your machine, works with any model, and goes beyond code into research and automation.

  • #9 Kilo CodeFreemium

    use this if you want one open agent in VS Code, JetBrains, the terminal, and the cloud, and you want to choose the model or bring your own key.

  • #11 CrushUsage-based

    use this if you want Charm's terminal UI as a coding agent and you will bring Hyper or your own model key.

  • #12 AiderFree / OSS

    use this if you want an open-source, git-native pair programmer and bring your own model.

  • #13 Trail-codeFree / OSS

    use this if you already use Claude Code, Cursor or Codex and want it to find the right code faster and remember what your team decided.

sponsor this spot →