Qwen Code

Qwen Code — Apache-2.0 Gemini CLI fork tuned for Qwen3-Coder, with a large free daily quota. Qwen Code is a fork of Gemini CLI re-targeted at the Qwen3-Coder models, which means it inherits a mature harness — MCP, custom commands, checkpointing — without having to build one. A Qwen sign-in grants a substantial free daily request quota, and because it speaks OpenAI-compatible endpoints it also works against any compatible provider or a local server. The obvious choice if you want strong open-weight models in a familiar loop. Built by Alibaba. Founded 2025. Open source under Apache-2.0.

We track it in 1 comparison — Coding agents — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 16 other tools, and what follows is where it visibly separates from them.

Where it gives ground.

• Background agents — No. Claude Code records Yes.
• GitHub stars — 13,000, 8th of 9. Gemini CLI records 75,000.
• Opens PRs — No. Claude Code records Yes.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 22 of 26 tracked fields carry a value for Qwen Code, and 3 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Aider. Qwen Code is ahead on MCP (Yes against No) and Skills / commands (Yes against Partial). Aider takes Model breadth (any provider / router against one vendor + custom endpoint) and GitHub stars (37,000 against 13,000). That pattern repeats across the rest of the roster — see Qwen Code alternatives for the other rivals, each compared the same way.

Company

Alibaba

Founded

2025

Licence

Apache-2.0 (open source)

Fields we track

22 of 26

Last verified

2026-01-15

Forking Gemini CLI was the right call — it inherits a mature harness for free and spends its effort on model integration. The clearest route to strong open-weight models in an agent loop, and the free quota makes daily use viable outside US and EU price brackets.

Background agents

○No12th of 16

Inferred

GitHub stars

13,0008th of 9

Community-reported

Opens PRs

○No10th of 16

Inferred

BYOK

●Yes1st of 16

Inferredverified 2026-01-15

Headless / CI

●Yes1st of 16

Inferredverified 2026-01-15

MCP

●Yes1st of 15

Inferred

Entry price

$0 /seat/mo1st of 16

Inferredverified 2026-01-15

Checkpoint & undo

●Yes1st of 16

Inferred

Qwen Code is the right call in these situations, each one drawn from a field we actually record:

• Running open-weight coding models without building a harness.
• Regions or budgets where frontier API pricing is the blocker.
• Air-gapped or self-hosted inference behind an OpenAI-compatible endpoint.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• Background agents. Qwen Code records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• GitHub stars. Qwen Code records 13,000, 8th of 9 in the Coding agents roster. Gemini CLI records 75,000 on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Opens PRs. Qwen Code records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 4 of the 26 fields we track for Qwen Code are still blank: Subagents, Hooks, Terminal-Bench and Bench model. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.