Qwen Qode lets developers chat with a Qwen2.5-coder model to read, edit, and run code in any project folder via a sleek web UI or a terminal CLI. It works with cloud OpenRouter or offline Ollama/LM Studio, handling tool calls through a ReAct loop. Ideal for developers who want AI‑driven code assistance without needing a GPU, offering a self‑hosted alternative to commercial copilots.
View on GitHub →baberparweez/Qwen-Qode