Qwen Code vs. zerostack

Feature	Qwen Code	zerostack

Tagline	An open-source AI agent that lives in your terminal	Minimal Rust coding agent optimized for memory footprint
Website	https://qwen.ai/qwencode	https://gi-dellav.github.io/zerostack/
Language	typescript	rust
Release Date	August 1, 2025	May 12, 2026
Last Updated	August 19, 2026	September 4, 2026
Provider Type	AI Lab	Independent
MCP Support	Yes	Yes
Multi-Agent Support	Yes	Yes
Git Integration	basic	deep
Multi-File Editing	Yes	Yes
Auto Test Running	Yes	Yes
Sandbox / Permissions	Yes	Yes
Image / Multimodal Input	Yes	Yes
Voice Mode	No	No
IDE Integration	VS Code, Zed, JetBrains IDEs	Zed (via ACP), Neovim (via CodeCompanion.nvim + ACP)
Hooks / Extensions	Yes	Yes
Web Search	Yes	Yes
Local Model Support	Yes	Yes
Context Window	Model-dependent	Model-dependent; auto-compaction
Supported Models	Qwen series models, compatible with OpenAI, Anthropic, Gemini APIs, including models from OpenRouter.	OpenRouter (default), OpenAI, Anthropic, Gemini, Ollama, plus unlimited custom OpenAI-compatible endpoints (vLLM, LiteLLM, enterprise gateways)
Pricing Model	Free	Free, BYOK
Free Tier	Yes	Yes
Price Range	Free (1,000 req/day)	Free (BYOK)
Source Code Availability	Open Source (Apache-2.0)	Open Source (GPL-3.0)
Source Code	https://github.com/QwenLM/qwen-code	https://github.com/gi-dellav/zerostack
Development State	active	active