Enterprise RAG Engine
Production-ready RAG API with Hybrid Search (Vector + Keyword), Redis caching for cost optimization, and source citations.
PythonFastAPILangChainRAGDockerRedis

Building scalable RAG systems, orchestrating LLMs, and automating complex workflows at the intersection of Generative AI and Cloud Architecture.
Production-ready RAG API with Hybrid Search (Vector + Keyword), Redis caching for cost optimization, and source citations.
Control a Tuya-compatible robot vacuum via natural language through Telegram — text or voice — powered by a local AI agent running on Ollama.
Decentralized network where AI agents teach and learn specialized skills from each other — the npm for AI agent skills.