the catalog · ✨ AI assistants

Ollama

★ 178k

One-command local runner for Llama, Qwen, DeepSeek, Gemma and other open models with an API

Ollama does the job of OpenAI and Anthropic API usage, self-hosted. It is MIT-licensed, so you can do essentially what you like with it, and it installs in about one command. OpenAI bills $20+ for it. 178k stars on GitHub.

Open-source replacement for OpenAI, Anthropic API usage.

Licence
MIT
Self-hosting
Easy
The paid one costs
$20+
GitHub stars
178k
view the code →official site →

Is it actually a replacement?

We have not written a verdict on OpenAI or Anthropic API usage yet, so this page says what Ollama is rather than judging what you would give up. When that product gets a page, this one will link to it.

How Ollama runs

Where it runs

Ollama runs on your server.

What setup takes

not verified by us yet — check the repo README.

Ollama questions

Is Ollama open source?

Yes — it is released under MIT.

Can I self-host Ollama?

Yes — we rate it easy to self-host, and it runs on your server.

More local model runner tools