AI Hub
Codingopen-source

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. GitHub stars:

githubRAG ToolsCodingaiai-stackcuda

Discover 5 new AI tools every week

Join our free newsletter and stay ahead of the curve.

Similar Tools in Coding