Docker AI Stack
liveSelf-hosted AI stack with LLM, STT, TTS, and MCP in one Docker Compose file
Details
Deploys a complete AI stack on your server through Docker, including services for local LLM inference, speech-to-text, text-to-speech, embeddings for semantic search, and MCP gateway. All services are automatically configured upon first startup. It supports GPU acceleration via NVIDIA CUDA and offers lightweight stack variations for lower resource usage.
Best fit users
- •Developers
- •AI enthusiasts
- •Local AI users
Why this one made the cut
Provides a self-hosted, private AI solution without depending on external APIs, ensuring data sovereignty and reducing privacy concerns. It simplifies deployment with pre-configured Docker Compose files and offers flexibility to choose from full or lightweight setups based on use case.
What makes it different
Zero-config deployment with automatic API key generation and modular stack configurations for different use cases. Unlike external AI solutions, the Docker AI Stack keeps all processing local.