Ollama

Run open-weight models (Llama, Qwen, Gemma, Mistral, and more) locally with one command. The easiest way to give agents a private, offline model.

Local Models

GoCLILocal Models

Repository

ollama/ollamaLIVE FROM GITHUB

★174,835stars

🍴16,717forks

Updated today

Installation

Download from ollama.com, then: ollama run llama3.3

How to Use

Ollama is a production-grade tool used by many agent builders. Start with the official installation command above, then follow the official documentation for configuration and advanced usage.

Most tools in this directory work great alongside agent skills and MCP servers across Claude Code, Codex, Grok Build, Gemini CLI, and Cursor.

View full documentation and source

Quick Links

GitHub Repository

Install with the command shown on the left.

Related Tools

Claude Code

Anthropic's agentic coding CLI. Reads your repo, edits files, runs commands, and ships features end-to-end from the terminal. Supports skills, MCP servers, hooks, and subagents.

OpenAI Codex CLI

OpenAI's open-source coding agent for the terminal. Plans, edits, and runs code in a sandbox with configurable approval modes. Reads AGENTS.md natively.

Grok Build

xAI's terminal coding agent. Plan Mode writes a file-by-file plan before editing, runs up to 8 parallel subagents in isolated git worktrees, and has native MCP support. Reads AGENTS.md and runs headless in CI. Powered by grok-build-0.1.