librarian-cli is an open-source CLI tool that converts ebooks (epub, fb2) into markdown format for deterministic ingestion by LLMs and RAG pipelines. It streamlines data preparation for AI and retrieval-augmented generation workflows.
In the RAG, search & retrieval space, librarian-cli takes a focused approach. It focuses on automating the conversion of ebooks to markdown for use in LLM and retrieval-augmented generation workflows. librarian-cli is an open-source project aimed at LLM developers and data engineers. The project is open source (MIT). It runs on the command line.
It is developed by Terobyte, and the product first shipped in 2026. The project is developed in the open on GitHub with 74 commits in the last 90 days. Across PulseGate's embedding index, librarian-cli has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are book to markdown conversion, LLM pipeline integration, and epub/fb2 support. It exposes integrations via an MCP server.
Latest indexed changes and source events
librarian-cli discovered by the PulseGate indexer
Other apps tracked under the same category.