txtai

txtai is an all-in-one AI framework for semantic search, LLM orchestration, and language model workflows. Its core component is an embeddings database that merges vector indexes, graph networks, and relational databases. This provides a robust knowledge source for RAG, autonomous agents, and multi-model workflows. Supporting text, audio, images, and video, txtai runs locally or scales with containers, featuring Web/MCP APIs and multi-language bindings.

• All-in-one embeddings database combining vector, graph, and SQL
• Multimodal semantic search and language model workflows
• Autonomous agents built on smolagents with skill.md support
• Web and Model Context Protocol (MCP) APIs
• RAG orchestration and lightweight local execution