Run open LLMs locally with a simple CLI, REST API, and model library
- Stars174.2k
- Forks16.6k
- Open Issues3.4k
MIT
- Go
- C
- TypeScript
About Ollama
Ollama gets you up and running with open large language models on your own machine. Pull a model from its library and chat with it in a single command, keeping inference and your data on hardware you control rather than a hosted service.
A REST API and official Python and JavaScript libraries make Ollama easy to wire into your own apps, and it connects to coding agents and assistants such as Claude Code, Codex, and Copilot CLI. Import your own model weights or customize behavior with a Modelfile.
Ollama installs natively on Windows, macOS, and Linux, with an official Docker image for containerized setups. Built in Go on the llama.cpp backend, it serves as the local runtime behind a wide range of community chat, desktop, mobile, and coding tools.
Key features
- Run and chat with open models from one CLI
- REST API plus Python and JavaScript libraries
- Connect coding agents like Claude Code and Codex
- Import custom weights and Modelfiles
- Built on the llama.cpp backend
Details
- First released
- 2023
- Platforms
- Windows · macOS · Linux
- Deployment
- self-hostable · docker · offline-first
- Language
- Go
- Backend
- llama.cpp
- Interface
- CLI · REST API