hwdsl2/self-hosted-ai-stack
Deploy a complete self-hosted AI stack with Docker Compose: Ollama, LiteLLM, AnythingLLM, Whisper, WhisperLive, Kokoro, Embeddings, Docling and MCP Gateway. Local-first, private by default, with lightweight stacks, optional HTTPS and NVIDIA CUDA acceleration. Multi-arch: amd64, arm64.
Commercial license
β Commercial OKMIT
ε―εη¨οΌιεΈΈεͺιδΏηθδ½ζ¬θ²ζ/ζζ¬ζ’ζ¬Ύ
Topics
aiai-stackcudadockerdocker-composedoclingembeddingslinuxlitellmllmlocal-aimcp
Ad