Back to browse
GitHub Repository

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.

88 starsShell

Docker AI Stack, self-hosted LLM/STT/TTS/MCP in one compose file

by hwdsl2·May 6, 2026·1 point·0 comments

AI Analysis

●●SolidShip ItCozy

One-command local AI stack bundling Ollama, Whisper, and MCP Gateway.

Strengths
  • Zero-config setup generates API keys automatically for secure local deployment.
  • Lightweight mode drops RAM requirements to 2.5GB for smaller server instances.
  • Includes MCP Gateway out of the box for immediate agent tool integration.
Weaknesses
  • Just orchestrates existing containers without novel architecture or engineering.
  • Heavy reliance on external providers via LiteLLM undermines the 'local' claim.
Category
Target Audience

Developers self-hosting local AI infrastructure

Similar To

Docker Ollama · Open WebUI · AnythingLLM

Similar Projects

AI/MLMid

Docker AI Stack – Deploy 8 self-hosted AI services with one command

Yet another one-command AI stack when Ollama and Jan already exist.

Ship It
hwdsl2
101mo ago
AI/MLMid

WordPress for Voice Agents – Unpod.ai

Voice agent orchestration with no-code studio, but orchestrates off-the-shelf APIs like everyone else.

Ship It
parvbhullar
11103mo ago