document-ai

doc7

Go

73

Turn documents into AI-ready Markdown with visual understanding

mdflux

Svelte

77

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

ragflow

Go

90

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

RealReplicaBench

HTML

82

RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services

Token-Saver

Python

77

A local Claude Desktop extension to query large PDFs with 92–98% fewer tokens. Performs local hybrid search, cites exact page numbers, and keeps your documents private on your machine

PixelRAG

Python

90

The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

lift

Python

77

Extract structured data from documents quickly and accurately.

markitdown

Python

95

Python tool for converting files and office documents to Markdown.

docmost

TypeScript

90

Docmost is an open-source collaborative wiki and documentation software. It is an open-source alternative to Confluence and Notion.

openwiki

TypeScript

90

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

blume

TypeScript

87

World-class docs for everything you ship. Fast, AI-ready, and zero-config.

nimbus

TypeScript

82

Docs for humans and agents, built on Astro

tensorflow

C++

90

An Open Source Machine Learning Framework for Everyone

unity-ui-document-design-system

C#

82

Drop-in design system for Unity 6 UI Toolkit (UIDocument + PanelRenderer, UXML + USS): tokens, fx shader material support, 42 components, 120 icons, mobile-responsive, dark-themed. One stylesheet, zero dependencies. Battle-tested in a shipping cross-play game.

papra

TypeScript

85

The minimalistic document archiving platform.

letsseal

JavaScript

77

The open standard for proving any file is real, unaltered and sealed

compdf-self-hosted

TypeScript

72

Edit, convert, and transform documents across PDFs, Office formats, HTML, TXT, CSV, RTF, JSON, and images with ComPDF Self-hosted, an open-source PDF platform.

HomeBox

Go

85

A continuation of HomeBox the inventory and organization system built for the Home User

anydoc

Rust

90

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

pdfx

TypeScript

82

A free-floating 2D Canvas for processing multiple PDF files simultaneously

CodexQB

Python

77

CodexQB is a Codex plugin for evidence-backed repo comprehension, planning, QA audit, and gated implementation handoffs.

binky

Swift

77

Binky sorts your files.