tau vs qwen-code

Terminal coding agents compared

tau and qwen-code help developers understand repositories, change code, and run commands through AI agents. tau is a Python-based, layered harness with session history and custom frontend support, while qwen-code is a TypeScript agent with a wider range of interfaces and integrations.

tauqwen-code
LanguagePythonTypeScript
LicenseMITApache-2.0
Stars3k28.6k
Forks3873.2k
Last analyzedOct 19, 2026Oct 19, 2026

Key differences

  • tau is written in Python and requires Python 3.12 or newer; qwen-code is written in TypeScript, and its npm installation requires Node.js 22 or later.
  • tau focuses on a terminal interface, prompt mode, and a reusable event-driven harness; qwen-code also connects to editors, desktop, web, and chat interfaces.
  • tau supports append-only JSONL session history with resume and branching; qwen-code highlights SubAgents, Agent Teams, Auto-Memory, Auto-Skills, and MCP.
  • tau lists OpenAI, Anthropic, OpenRouter, Hugging Face, Codex subscription auth, and compatible endpoints; qwen-code lists Qwen, OpenAI, Anthropic, Gemini, third-party providers, and local models.
  • tau uses the MIT license; qwen-code uses Apache-2.0.
  • tau describes its codebase as small and layered for developers studying agent systems; qwen-code covers more interface and integration types, with its web UI and daemon mode labeled experimental.

Choose tau if you…

  • want a Python-based agent harness with provider-neutral events for a custom frontend.
  • need append-only session history with resume and branching.
  • prefer a smaller, layered codebase for studying agent structure.
Read the tau analysis →

Choose qwen-code if you…

  • need integrations for editors, desktop, web, or chat workflows.
  • want to use Qwen, Gemini, third-party providers, or local models.
  • plan to invoke an agent from scripts or CI/CD, or build with TypeScript, Python, or Java SDKs.
Read the qwen-code analysis →

Compare the numbers side by side, or add more projects

This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.