Ollama

Ollama is a software tool founded in 2023 and headquartered in San Francisco, California, that enables developers and individuals to download and run open-source large language models directly on their local machines. The company was co-founded by Michael Chiang and Jeffrey Morgan with the goal of making local LLM inference accessible without requiring cloud infrastructure or sending data to third-party servers.

Ollama's primary product is an open-source command-line tool and API server that supports a wide range of models including Meta's Llama series, Mistral, Gemma, and others. Users can pull models from Ollama's model library and run inference locally via a REST API that mirrors the OpenAI API format, making it compatible with many existing tools and integrations. The platform is widely used by developers building local AI applications, researchers, and privacy-conscious users who prefer to keep data on-premises.

Ollama's GitHub repository has accumulated a substantial number of stars, reflecting broad adoption in the open-source developer community. The company operates with a small team and has raised early-stage funding, though specific funding amounts have not been publicly disclosed. The project is distributed as open-source software under a permissive license.