A proxy that allows you to use Ollama as a coding assistant similar to GitHub Copilot.

• Features
• Requirements
• Installation
  • Install Go
  • Install Ollama
  • Install ollama-copilot
• Usage
  • Basic Usage
  • Command Line Options
  • Environment Variables
• IDE Configuration
  • Neovim
  • VSCode
  • Zed
  • Emacs
• Troubleshooting

• Works as a drop-in replacement for GitHub Copilot
• Compatible with multiple IDEs
• Uses local LLMs through Ollama for privacy and control
• Customizable model selection

• Go 1.20 or higher
• Ollama installed and running
• At least 16GB RAM (depending on the LLM model used)

1. Download Go from the official website:

# For Linux (adjust version as needed)
wget https://go.dev/dl/go1.25.0.linux-amd64.tar.gz
sudo tar -C /usr/local -xzf go1.25.0.linux-amd64.tar.gz

# For macOS (using Homebrew)
brew install go

2. Add Go to your PATH in ~/.bashrc, ~/.zshrc, or equivalent:

export PATH=$PATH:/usr/local/go/bin
export GOPATH=$HOME/go
export PATH=$PATH:$GOPATH/bin

# Apply the changes
source ~/.bashrc  # or source ~/.zshrc

3. Verify the installation:

go version

Ensure Ollama is installed:

curl -fsSL https://ollama.com/install.sh | sh

# For macOS (using Homebrew)
brew install ollama

ollama pull qwen3-coder:30b

You can use other models as well, but qwen3-coder:30b is the default expected by ollama-copilot.

go install github.com/josuemontano/ollama-copilot@latest

1. Make sure Ollama is running:

ollama serve

2. In a separate terminal, start ollama-copilot:

ollama-copilot

3. Configure your IDE to use the proxy (see IDE Configuration below)

Example with custom options:

ollama-copilot --model qwen2.5-coder:7b --num-predict 300 --verbose

You can configure the Ollama host using environment variables:

OLLAMA_HOST="http://192.168.133.7:11434" ollama-copilot

1. Install copilot.vim
2. Configure variables in your Neovim config:

let g:copilot_proxy = 'http://localhost:11435'
let g:copilot_proxy_strict_ssl = v:false

1. Install the GitHub Copilot extension
2. Configure settings (File > Preferences > Settings or Ctrl+,):

{
  "github.copilot.advanced": {
    "debug.overrideProxyUrl": "http://localhost:11437"
  },
  "http.proxy": "http://localhost:11435",
  "http.proxyStrictSSL": false
}

1. Open settings (Ctrl+,)
2. Set up edit completion proxying:

{
  "features": {
    "edit_prediction_provider": "copilot"
  },
  "show_completions_on_input": true,
  "edit_predictions": {
    "copilot": {
      "proxy": "http://localhost:11435",
      "proxy_no_verify": true
    }
  }
}

(Experimental)

1. Install copilot-emacs
2. Configure the proxy in your Emacs config:

(use-package copilot
  :straight (:host github :repo "copilot-emacs/copilot.el" :files ("*.el"))  ;; if you don't use "straight", install otherwise
  :ensure t
  ;; :hook (prog-mode . copilot-mode)
  :bind (
         ("C-<tab>" . copilot-accept-completion)
         )
  :config
  (setq copilot-network-proxy '(:host "127.0.0.1" :port 11434 :rejectUnauthorized :json-false))
  )

• If you encounter connection issues, make sure Ollama is running
• Verify that the correct ports are accessible
• Check logs by running with the -verbose flag
• Ensure your Go path is correctly set up in your environment