{"id":"localai","name":"LocalAI","maker":"LocalAI","url":"https://localai.io","repo":"mudler/LocalAI","docs":"https://localai.io/docs/","summary":"A self-hosted server that runs language, image, speech and embedding models behind OpenAI-compatible APIs.","details":"LocalAI runs on CPUs and GPUs with several back ends such as llama.cpp and vLLM, in Docker or as a binary. It also offers agent and MCP features. It is MIT licensed.","open_source":true,"hosted":false,"speaks":["openai-api","mcp"],"verified":"2026-11-15","category":"runtimes","category_name":"Local and self-hosted model runtimes","page":"https://modelmoot.com/tools/localai","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}