TOON-Native Auto-Embedding & RAG Toolkit for MariaDB — VECTOR(N), HNSW, VEC_DISTANCE_COSINE, with TOON tabular output that saves 10-55% LLM tokens vs JSON.
seamless-rag is a RAG, search & retrieval product. It focuses on enabling efficient retrieval-augmented generation and vector search with MariaDB using open-source embeddings. seamless-rag is an open-source project aimed at developers working with MariaDB and RAG pipelines. The project is open source (Apache-2.0). The product ships for the web and the command line.
It is developed by MariaDB Hackathon MY 2026, and the product first shipped in 2026. The project is developed in the open on GitHub with 86 commits in the last 90 days. Across PulseGate's embedding index, seamless-rag has few near neighbours, marking it as relatively distinct. Among its 6 catalogued features are auto-embedding, RAG toolkit, and HNSW support.
Latest indexed changes and source events
Other apps tracked under the same category.
