Repository Index

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

• extract-data
• layout-analysis
• ocr
• parser

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

• agent
• ai
• anthropic
• compression

Get your documents ready for gen AI

• ai
• convert
• documents
• pdf

Convert PDF to markdown + JSON quickly with high accuracy

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

• json
• markdown
• pdf
• ai

The Generative UI framework

Structured Outputs

• generative-ai
• llms
• prompt-engineering
• symbolic-ai

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

• deep-learning
• document-parsing
• machine-learning
• nlp

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

• ai-agents
• browser-automation
• data-extraction
• firecrawl

Ruby library for defining, generating and validating JSON Schema

• anthropic-api
• json-api
• json-schema
• openai-api

PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.

• llm
• mcp
• ocr
• pdf

Fast lossless JSON parse event streaming, in JavaScript.

• json
• streaming
• parser
• lossless

Inline review tool for MDXG markdown — capture highlighted comments and export them as structured JSON for LLM agents.

• annotations
• feedback
• human-in-the-loop
• inline-comments

Conflict-free merge for DataFrames, JSON, ML models & distributed agents — powered by CRDTs. The first merge library where every operation is mathematically guaranteed to converge.

• collaborative-editing
• conflict-resolution
• crdt
• data-engineering

Lightweight PHP library for encoding/decoding TOON (Token-Oriented Object Notation). A human-readable, LLM-friendly alternative to JSON.

• decoder
• encoder
• json
• llm