# QwenLM/qwen-code

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

Repository: https://github.com/QwenLM/qwen-code
Canonical: https://ross.abutalabs.com/products/qwen-code
Homepage: https://qwenlm.github.io/qwen-code-docs/en/users/overview
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: agentic, ai, ai-agent, ai-coding, cli, coding-agent, developer-tools, llm, mcp, qwen, terminal, typescript
Last push: 2026-08-27T00:30:55+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 31
- inputs: {"age_days": 434, "days_push": 7, "days_rel": 7, "gap_med": 0, "n_releases_24m": 366}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 27405, forks 2947 (observed 2026-08-28T04:11:47.692094+00:00)

## What it is
Qwen Code is an open-source AI coding agent that runs in the terminal, providing agentic code editing, review, and automation powered by Qwen and other LLM providers. It supports MCP, subagents, skills, IDE plugins, SDKs, and messaging-channel integrations.

## Use cases
- refactor code from the terminal with an AI agent
- automated code review in CI
- connect local models like Ollama to a coding agent
- run multi-agent coding workflows with MCP tools
- generate and apply code changes across a repo
- chat with a coding assistant from Telegram or DingTalk

## When to choose
- you want an open-source, vendor-neutral terminal coding agent
- you need multi-provider support including local models
- you want MCP, subagents, and IDE integrations out of the box

## When to avoid
- you need a fully GUI-based AI IDE experience
- you require a commercially supported product with SLAs
- you don't want to manage API keys or model providers yourself

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, cli, mcp, llm-inference, developer-tools, chatbot
- domain: developer-tools, large-language-models
- platform: cli, windows, cross-platform
- tags: coding-agent, terminal-ui, agentic-coding, code-review, multi-provider, subagents, ide-plugin, sdk, command-line, ai-agents, automation, nodejs, linux, macos

## Member repositories
- QwenLM/qwen-code (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:47.692094+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:32.608785+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/qwen-code (fetched 2026-08-28T04:11:47.692094+00:00, sha ef0b8a1b0c19)
  - homepage: https://qwenlm.github.io/qwen-code-docs/en/users/overview (fetched 2026-08-29T07:51:57.793452+00:00, sha d9f1a51836b0)
  - registry_npm: https://registry.npmjs.org/qwen-code (fetched 2026-08-29T07:51:57.825770+00:00, sha 08bdad755f9c)
- Data as of 2026-08-30T08:39:29.467469+00:00.