documents
Projects tagged with documents on GitHub.
16 projects
lift
PythonExtract structured data from documents quickly and accurately.
markitdown
PythonPython tool for converting files and office documents to Markdown.
compdf-self-hosted
TypeScriptEdit, convert, and transform documents across PDFs, Office formats, HTML, TXT, CSV, RTF, JSON, and images with ComPDF Self-hosted, an open-source PDF platform.
PixelRAG
PythonThe end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
pdfx
TypeScriptAn extension of the traditional PDF standard, allowing multiple files to be stored in a single file via metadata
ragflow
GoRAGFlow 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
CodexQB
PythonCodexQB is a Codex plugin for evidence-backed repo comprehension, planning, QA audit, and gated implementation handoffs.
binky
SwiftBinky sorts your files.
papra
TypeScriptThe minimalistic document archiving platform.
unity-ui-document-design-system
C#Drop-in design system for Unity 6 UI Toolkit (UIDocument + PanelRenderer, UXML + USS): tokens, 24 components, 63 icons, mobile-responsive, dark-themed. One stylesheet, zero dependencies. Battle-tested in a shipping cross-play game.
mdflux
SvelteTurn 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.
docmost
TypeScriptDocmost is an open-source collaborative wiki and documentation software. It is an open-source alternative to Confluence and Notion.
openwiki
TypeScriptOpenWiki is a CLI that writes and maintains agent documentation for your codebase.
blume
TypeScriptWorld-class docs for everything you ship. Fast, AI-ready, and zero-config.
tensorflow
C++An Open Source Machine Learning Framework for Everyone
HomeBox
GoA continuation of HomeBox the inventory and organization system built for the Home User