Back to directory

SWIRL Community

An open-source federated search and retrieval-augmented-generation tool that queries an organization's existing apps and data sources live, without copying data into a vector database.

SWIRL Community

SWIRL Community is an open-source tool for federated search and retrieval-augmented generation across an organization's existing applications. Instead of copying data into a vector database, it queries connected sources live, using the requesting user's own permissions, then ranks the combined results and can generate an answer with citations using a chosen LLM.

It ships with more than 100 connectors and a web interface called the Galaxy UI, and it starts from a single Docker Compose command in about two minutes, though the Docker setup does not persist data between restarts. A commercial SWIRL Enterprise edition adds a three-pass reranker, canonical answers, and an MCP server for agents.

SWIRL Community is written in Python and released under the Apache License 2.0.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.