Reach more potential users and drive product growth and revenue.
AdvertiseData & Retrieval
Vector retrieval and document understanding infrastructure.
MarkItDown
Free ListingStars: 191.8KConvert documents and media to Markdown for LLMs
MarkItDown is a lightweight Python utility that converts PDFs, Office documents, images, audio, HTML, text-based formats, ZIP files, YouTube URLs, and EPubs to Markdown for LLMs and text analysis pipelines.
Scrapling
Free ListingStars: 93.2KEffortless web scraping for the modern web
Scrapling is a Python web scraping framework for fast HTTP requests, stealth browsers, powerful parsing, and concurrent crawling, from a single request to a full-scale crawl.
PaddleOCR
Free ListingStars: 90.2KGlobal Leading OCR Toolkit & Document AI Engine
PaddleOCR is a powerful, lightweight OCR and document parsing toolkit that turns PDFs and images into structured, LLM-ready data. It supports 100+ languages, JSON and Markdown output, and helps build RAG and Agentic applications.
Docling
Free ListingStars: 68KGet your documents ready for gen AI
Docling is an open-source document processing library that parses diverse formats, including advanced PDF understanding, and integrates with generative AI workflows. It supports structured representations and local execution.
PPT Master
Free ListingStars: 56.6KAI generates natively editable PPTX from any document
PPT Master turns documents or topics into native PowerPoint decks with real shapes, transitions, animations, data-backed charts and tables. Drop in a PDF, DOCX, URL, or Markdown to get a natively editable PPTX, not images.
OpenViking
Free ListingStars: 38.7KOpen-source context database for AI agents
OpenViking is an open-source context database for AI agents. It unifies agent memory, knowledge RAG, and skills, organizing context as a navigable filesystem for retrieval and reuse.
PDFMathTranslate
Free ListingStars: 38.1KScientific PDF translation with preserved layouts
PDFMathTranslate is an open-source tool for translating scientific PDF documents while preserving layouts, formulas, charts, tables, and annotations. It supports multiple translation services and CLI, GUI, Docker, and Zotero workflows.
Qdrant
Free ListingStars: 34.8KHigh-performance vector database and vector search engine
Qdrant is a high-performance, massive-scale vector database and vector similarity search engine for next-generation AI applications. It stores, searches, and manages vectors with payload filtering. Also available as managed Qdrant Cloud.
Graphiti
Free ListingStars: 31.2KA Framework for Building Temporal Knowledge Graphs
Graphiti is an open-source framework for building and querying temporal knowledge graphs for AI agents. It tracks how facts change over time, maintains provenance to source data, and supports hybrid retrieval for evolving real-world data.
Chroma
Free ListingStars: 29.4KOpen-source search infrastructure for AI
Chroma is open-source search infrastructure for AI. It provides fast, serverless, scalable infrastructure for vector, sparse vector, full-text, regex, and metadata search, built on object storage for multi-tenant indexes.
anydoc
Free ListingStars: 22.1KConvert documents to GitHub-Flavored Markdown in Rust.
anydoc is an open-source Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF documents into clean GitHub-Flavored Markdown, with Node.js, Python, browser, WebAssembly, and CLI bindings.
XERJ
Free ListingStars: 6.9KSearch built for AI agents.
XERJ is an AI-native search engine that indexes code, documents, and data, then answers agent questions from the index instead of the context window. It speaks the Elasticsearch API and ships as one Rust binary.
PDF Craft
Free ListingStars: 6.6KTurn scanned books into ebooks you can read comfortably
PDF Craft converts scanned PDF books into editable Markdown or reader-friendly EPUB, and translates PDF and EPUB documents, including bilingual output.
Marble Skill Taxonomy
Free ListingStars: 5KOpen taxonomy of primary learning topics and prerequisites
An open, structured taxonomy of 1,590 primary-school micro-topics across eight subjects, connected by 3,221 prerequisite edges and aligned to national curriculum standards.
WaterCrawl
Free ListingStars: 2.2KSelf-hosted web crawler, scraper, and search engine
WaterCrawl is an open-source, self-hosted web crawler, scraper, and search engine that turns web content into structured, LLM-ready data for AI pipelines and automation workflows.
Sand3D
Free ListingStars: 1.2K3D modeling in Python, built for LLMs.
Sand3D is an open-source 3D-as-code library and dataset of 3D objects written in an LLM-friendly language. Each object is a Python program describing its parts, shapes, holes, positions, and materials.
@office-kit/xlsx
Free ListingStars: 0.1KRead, edit, and write Excel files in TypeScript
A TypeScript library for reading, editing, and writing Excel .xlsx workbooks in Node 22+ and modern browsers. It preserves unmodeled parts byte for byte, supports streaming for large sheets, and validates output against ECMA-376 schemas.
@office-kit/pptx
Free ListingStars: 0KRead, edit, and write .pptx files in TypeScript
@office-kit/pptx is a TypeScript library for reading, editing, and writing PowerPoint (.pptx) files in Node and the browser. MIT licensed, no native modules, single ESM bundle.
@office-kit/docx
Free ListingStars: 0KRead, edit, and write Word documents in TypeScript
A TypeScript library for reading, editing, and writing Word .docx documents. It builds new files, edits existing templates, and runs in Node.js and browsers.

