DocHarvest
DocHarvest is an open-source tool for downloading documentation sites such as GitBook, Docusaurus, Read the Docs, Mintlify, and Nextra. It produces Markdown, vector RAG JSONL, llms.txt, styled offline PDFs, and provides CLI, desktop GUI, and FastMCP server interfaces.
Overview
8 featuresDocHarvest sits in PulseGate's CLI tools & terminal category. It focuses on extracting documentation into clean, reusable formats for offline reading, search, RAG pipelines, and LLM workflows. It is built as an open-source project for developers and AI engineers working with documentation and retrieval systems. The project is open source (MIT). DocHarvest is available on the command line, macOS, Windows, and Linux, and it can be self-hosted.
Behind DocHarvest is Rohann Shetty, and it first shipped in 2026. The project is developed in the open on GitHub with 52 commits in the last 90 days. Key capabilities include documentation crawling, markdown export, and RAG JSONL export. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
- Documentation crawling
- Markdown export
- RAG JSONL export
- llms.txt generation
- Offline PDF generation
- Desktop GUI
- MCP server
- Multi-site support
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed5 Sept · 17:11 UTCgitbook-downloader verified via PyPI Bulk EnumeratorSource: PyPI Bulk Enumerator · Open
Frequently asked questions about DocHarvest
- What is DocHarvest?
- DocHarvest focuses on extracting documentation into clean, reusable formats for offline reading, search, RAG pipelines, and LLM workflows. It is catalogued under CLI tools & terminal on PulseGate.
- Who should use DocHarvest?
- DocHarvest is an open-source project built for developers and AI engineers working with documentation and retrieval systems.
- Does DocHarvest have a free plan?
- Yes — DocHarvest is open source under the MIT license and free to use.
- What platforms does DocHarvest run on?
- DocHarvest runs on the command line, macOS, Windows, and Linux. It can also be self-hosted.
- Is DocHarvest still active?
- The GitHub repository shows 52 commits in the last 90 days.
- Who develops DocHarvest?
- DocHarvest is developed by Rohann Shetty.
- When did DocHarvest launch?
- DocHarvest first shipped in 2026.
- Is DocHarvest open source?
- Yes — DocHarvest is open source under the MIT license, developed on GitHub.
Similar projects
Closest matches by what these projects do