repoGitHubTrust 82 · PrimaryPublished 11d agoLive · 9d ago
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.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Covers
Covers (incoming)
Related across the graph
newsHow to Build Your Own Local AI Server in 2026 - JournalArtanewsX now offers an MCP server to make its platform easier for AI tools to usenewsOpenAI to acquire OnanewsTop Cost-Effective Enterprise GPU Cloud Platforms for AI Workloads with H100–GB200, Elastic Scaling and Pay-as-You-Go Compute - Scott Coop
