# Ollama Copilot

A proxy written in Go that lets a local Ollama model, or DeepSeek and Mistral, act as a GitHub Copilot style code completion backend for editors such as Neovim, VS Code and Zed.

Ollama Copilot is a proxy that lets a locally running Ollama model, the llmman model runner, or a DeepSeek or Mistral API key stand in for GitHub Copilot in an editor. It exposes HTTP and HTTPS ports for both plain requests and a proxy mode, and an install script builds the binary, optionally installs it as a systemd service, and can configure Neovim, VS Code and Zed automatically.

The provider, model, and ports are set through command-line flags, and the proxy can point at an Ollama or llmman instance on another host. It is installed by building from source with Go or downloading the binary directly.

Website: https://github.com/bernardo-bruning/ollama-copilot