Document Search & Indexing

Converts PDF, Word, PowerPoint, Excel, HTML, images and audio into Markdown in one command.

It converts PDFs into clean Markdown or JSON, keeping headings, tables, equations and reading order.

A document parser that turns PDFs, office files, images and audio into clean structured text.

One program that reads your documents and answers questions about them, with the model running locally if you want.

It reads the words on scans and invoices so they can be searched like email.

A command-line converter that turns PDFs into Markdown or structured data with high accuracy.

A retrieval system that builds a network of things and relationships out of documents, then answers questions against it.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Saves links, notes, pictures and PDFs on a server you control, and adds labels on its own.

A self-hosted bookmark manager that keeps a copy of every page it saves.

It gathers the feeds you follow into one page you control.

It saves the readable text of any web article on a machine you control.

A self-hosted bookmark manager that installs with one Docker command and exports in the standard browser format.

Reads, edits and renders PDFs from Python, quickly.

Pulls text, tables and the exact position of every object out of a PDF, and draws the table it detected so a bad result can be fixed.

It extracts the main article from a web page and returns it as Markdown.

Focused text-chunking library — semantic and recursive splitters that respect message boundaries, so subtopics come out clean.

Open-source multimodal retrieval engine (Morphik Core)

A command-line assistant for a folder of plain text notes.

A shared document store with tags, permissions, full-text search and reading of scanned pages.

It reads incoming documents, works out who they are from, and makes the pile searchable.

A language server that gives a folder of Markdown notes links, backlinks, daily notes and completion inside an editor.

A command-line tool that loads JSON and CSV files into a SQLite database without designing a schema first.

Full-text search across everything said in a YouTube channel, with a link to the exact second.

A keyboard-driven library of papers kept as ordinary folders on disk.