Code Ollama Documentation

Code Ollama is an Ollama coding agent that runs in your terminal.

Quick Start

Set up Ollama, then run:

npx code-ollama

Getting Started

• Ollama — install the server, choose a model, and configure the host
• TUI — use modes, tools, commands, shortcuts, files, and images
• CLI — run one-off prompts, diagnostics, and saved sessions

Features

• MCP — connect external tools and resources
• Skills — add reusable instructions and workflows
• Memory — preserve global and project notes
• Sessions — resume, compact, and inspect conversations
• Web Search — configure SearXNG and DuckDuckGo fallback

Reference

• Configuration — review settings, precedence, validation, and security

Motivation

Why use Code Ollama?

• free (no per-token API cost)
• private (local inference)
• offline (run without internet)
• open models (Gemma, Qwen, DeepSeek, etc.)

Project

• README
• npm
• Releases