Tools/QwenLM/qwen-code

qwen-code

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

30.6k ★+1.5k/wkgrowthTypeScriptApache License 2.0 →trending

The Lens

By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.

Updated Nov 2026

Qwen Code is Alibaba's open-source coding agent: it reads your repo, writes code, and runs commands from the terminal, an editor plugin, a desktop app, or a chat app. It began as a fork of Google's Gemini CLI. Apache 2.0, and it drives Qwen, OpenAI, Anthropic, Gemini, or a local model through Ollama or vLLM.

Install is one line through npm, Homebrew, or a script. It ships subagents, auto-memory, skills like /review and /bugfix, MCP, hooks, and a headless mode for CI. One setting to know: the qwen serve daemon listens on localhost with no auth by default, so set a token on shared machines.

The free Qwen sign-in quota ended in April 2026. Signing in with a Qwen account now needs a paid Plus or Pro plan from chat.qwen.ai, and Alibaba's Coding Plan is $50 a month. Solo: free with a local model or your own key. Small teams: pay the provider you already use. Larger teams: point it at your own inference endpoint.

The catch: the agent is only as good as the model behind it. Free and local sounds great until a weaker model burns an afternoon on a task a frontier model finishes in one pass.

Free vs Self-Hosted vs Paid

fully free

Free: The whole agent is Apache 2.0: terminal, VS Code, Zed and JetBrains plugins, desktop app, web UI, chat channels, SDKs and daemon. Pointing it at a local model through Ollama or vLLM costs nothing. The old free Qwen OAuth quota was discontinued on 2026-04-15.

Self-hosted: No server is required; it runs on your machine. The optional qwen serve daemon can run as a long-lived service for browser, editor and SDK clients. Your cost is inference: zero with a local model.

Paid: Nothing goes to the project. Model access options from Alibaba: Qwen account sign-in requires a paid Plus or Pro subscription from chat.qwen.ai (price not published outside the signup flow); Alibaba Cloud Coding Plan Pro is $50/mo with request quotas per 5 hours, week and month (the Lite plan closed to new subscribers in March 2026); QwenCloud and Model Studio also sell a Token Plan subscription and pay-as-you-go API keys. Third-party keys (OpenAI, Anthropic, Gemini, OpenRouter, DeepSeek and others) bill at those providers' rates.

Free and open source. The free Qwen sign-in quota is gone, so your cost is whichever model you plug in: zero locally, a paid Qwen plan, Alibaba's $50/mo Coding Plan, or another provider's per-token rate.

What to do by team size

Solo
free with a local model or an API key you already pay for
Small team
free; your only bill is the model behind it
Medium team
free, but budget per-token spend or a Coding Plan once several people run it daily
Large team
free; most orgs this size will want their own inference endpoint behind it
Self-hosting ops:trivial

Get tools like this every Wednesday

One featured tool, three on the radar. No fluff.

Similar Tools

Score
92/100 · A+
Adoption27/30
Maintenance25/25
Community15/20
License15/15
Analysis10/10

A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores

Trust Signals

High adoption: 25,725 starsActive community: 2,590 forksCommunity discussions enabledOrganization account (49 public repos)Notable author: 17,764 followersAuthor also built: QwenLM/Qwen-AgentWorld (705 stars)

License: Apache License 2.0

Use freely. Patent grant included.

Commercial use: ✓ Yes

About

Owner
Qwen (Organization)
Stars
30,574
Forks
3,541

Also by Qwen

Explore Further

More tools in the directory