← All projects
AI ToolsFeatured

Ollama

by ollama

Get up and running with LLMs locally — run Gemma, DeepSeek, Qwen, Llama, and more in a single command.

Stars

177,000

Forks

17,100

Language

Go

License

MIT

Ollama lets you run large language models locally — get up and running with Gemma, DeepSeek, Qwen, Llama, gpt-oss, GLM, and more in a single command. It exposes a REST API, Python and JavaScript SDKs, and one-command integrations with coding agents like Claude Code, Codex, Copilot CLI, and OpenCode. Built on llama.cpp with smart memory management so large models run on modest hardware. The de facto standard for running open models on your own machine.

llmlocal-llmllamaself-hostedopenai-compatiblellama-cpp