Local AI model runtime that lets you run LLMs like GPT, Llama, Gemma, Qwen, and DeepSeek privately on your own hardware. Includes GUI app, headless deployment, SDKs, and OpenAI-compatible API for developers.
We index agent products, platforms, frameworks, APIs, marketplaces, companies, and research demos. L0 means supporting infrastructure. L1–L5 describe increasing agent autonomy. About these classes →