Back to directory

citelocal-agent

A local research agent that answers questions over a folder of PDFs with page-accurate citations, checking each one against the retrieved text before answering.

citelocal-agent

citelocal-agent answers questions about a collection of local papers or documents with citations checked to the page level, running entirely on the user's machine: embeddings are computed locally, papers stay in a gitignored folder, and the answering model can also run locally through Ollama.

Every citation is verified against the content actually retrieved, and citations that cannot be supported are dropped rather than left in the answer; questions outside the loaded documents are refused instead of answered from general knowledge. Cross-paper questions are handled by an agent that retrieves, lists sources, rewrites and re-retrieves, then synthesizes an answer with page numbers from multiple papers.

Retrieval combines dense embeddings and BM25 through reciprocal rank fusion with a cross-encoder reranker. It ships a CLI, a small FastAPI and Tailwind web UI with a streaming API, source citations and a collapsible retrieval trace, and a Docker deployment, and accepts PDF, Markdown, RST and plain text input.

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.