Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your machine.
-
Updated
Jul 17, 2026 - TypeScript
Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your machine.
Ollama Code is a CLI tool for AI-powered programming assistance using local Ollama models. The project provides full control over code and data, working completely offline.
Ollama pulls local models on a gpu. ollama library, cli run, privacy, open weights, modelfile, gpu layers, metal cuda, quantize, prompt window, keep alive, manifest, digest, numa, rocblas.
To associate your repository with the ollama-code-agent topic, visit your repo's landing page and select "manage topics."