QueryLake Backend is a production-oriented backend for self-hosted AI and RAG systems, offering OpenAI-compatible endpoints and a function-style platform API for authentication, collections, ingestion, toolchains, and search. It features a hybrid retrieval stack (BM25 + dense + sparse lanes) and Ray Serve orchestration with GPU/VRAM-aware scheduling, designed for research-friendly rapid iteration and developer-friendly stable APIs.
How the donated funds are distributed
Kivach works on the Obyte network, and therefore you can track all donations.