docker-compose

Bringing Generative AI to the way the Civil Service works

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.

🦙 echoOLlama: A real-time voice AI platform powered by local LLMs. Features WebSocket streaming, voice interactions, and OpenAI API compatibility. Built with FastAPI, Redis, and PostgreSQL. Perfect for private AI conversations and custom voice assistants.

Local-first Telegram AI bot with Ollama tool calling, voice transcription, MinIO storage, SearchApi web search, and readiness checks

Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64).

Precis is an extensible self-hosted AI-enabled RSS reader with a focus on notifications and support for theming

Open-source, self-hosted AI language learning platform with local or cloud LLMs, CEFR study plans, an AI tutor, voice conversations, flashcards, and spaced repetition.

This repository provides resources and guidelines to facilitate the integration of Open-WebUI and Langfuse, enabling seamless monitoring and management of AI model usage statistics.

🤖 Automated YouTube Shorts creation using n8n, AI script generation, and video processing. Full pipeline from topic to published video with AI images, TTS, transitions, and effects. Docker-based, self-hosted, and free to use.

DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance evidence (Strix Halo, DGX Spark, llama.cpp, vLLM): https://agmind.ai

Airflow Pipeline for Machine Learning

Claude Skills for connecting Claude.ai to local Weaviate vector databases - manage collections, ingest data, and query with RAG

Real-time performance metrics and statistics for your Nvidia GPU

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

Self-hosted multitenant platform for AI agents and Telegram bots with event-driven architecture

Prototyping a Machine Learning Application with Streamlit, FastAPI, Hugging Face and Docker

Run and manage both vLLM and llama.cpp model servers from one terminal UI + CLI — shared Docker Compose profiles, live tok/s, and cross-backend port/GPU conflict checks. NVIDIA + Linux.

The Ultimate Developer Experience Platform for the Container Era

ContextQA - The open-source tool for data-driven conversations