2,002 offers
Free Data Extraction — open-source & self-hostable
Document parsing, OCR, and structured extraction
Scores rate free-tier value on a 1–10 scale. How scores work →
-
PaddleOCR Data Extraction 7.7 Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. 84.6k★60/90d19 devs/90d -
Tesseract Data Extraction 7.6 Tesseract Open Source OCR Engine (main repository) 75.1k★61/90d6 devs/90d -
MinerU Data Extraction 7.6 Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. 73.2k★590/90d1 devs/90d -
PyMuPDF Data Extraction 6.8 PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents. 10.1k★91/90d6 devs/90d -
Unstract Data Extraction 6.7 LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows 6.7k★128/90d14 devs/90d -
Marker Data Extraction 6.6 Convert PDF to markdown + JSON quickly with high accuracy 37.1k★13/90d2 devs/90d -
LangExtract Data Extraction 6.6 A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization. 37k★30/90d6 devs/90d -
Unstructured Data Extraction 6.6 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. 15.1k★24/90d8 devs/90d -
Surya Data Extraction 6.4 OCR, layout analysis, reading order, table recognition in 90+ languages 21k★28/90d4 devs/90d -
Instructor Data Extraction 6.4 structured outputs for llms 13.4k★17/90d7 devs/90d -
Sparrow Data Extraction 6.3 Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM 5.2k★97/90d1 devs/90d -
Chandra Data Extraction 5.8 OCR model that handles complex tables, forms, handwriting with full layout. 11.4k★7/90d3 devs/90d -
DocETL Data Extraction 5.8 A system for agentic LLM-powered data processing and ETL 3.9k★25/90d2 devs/90d -
MonkeyOCR Data Extraction 5.1 A lightweight LMM-based Document Parsing Model 6.6k★3/90d1 devs/90d -
olmOCR Data Extraction 4.9 Toolkit for linearizing PDFs for LLM datasets/training 18.6k★0/90d0 devs/90d -
LlamaParse (LlamaCloud Services) Data Extraction 4.7 Knowledge Agents and Management in the Cloud 4.3k★0/90d0 devs/90d -
Dolphin Data Extraction 4.6 The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025. 9k★0/90d0 devs/90d -
dots.ocr Data Extraction 4.5 Multilingual Document Layout Parsing in a Single Vision-Language Model 9k★0/90d0 devs/90d -
OmniParse Data Extraction 4.3 Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks 7.6k★0/90d0 devs/90d -
Zerox Data Extraction 4.1 OCR & Document Extraction using vision models 12.2k★0/90d0 devs/90d -
Nougat Data Extraction 4.1 Implementation of Nougat Neural Optical Understanding for Academic Documents 10k★0/90d0 devs/90d -
PDF-Extract-Kit Data Extraction 4.0 A Comprehensive Toolkit for High-Quality PDF Content Extraction 9.8k★0/90d0 devs/90d -
GOT-OCR2.0 Data Extraction 4.0 Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model 8.1k★0/90d0 devs/90d -
Layout Parser Data Extraction 4.0 A Unified Toolkit for Deep Learning Based Document Image Analysis 5.8k★0/90d0 devs/90d -
docext Data Extraction 4.0 An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/) 2k★0/90d0 devs/90d -
MegaParse Data Extraction 3.9 File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs. 7.4k★0/90d0 devs/90d -
Camelot Data Extraction 3.8 Camelot: PDF Table Extraction for Humans 3.7k★0/90d0 devs/90d -
ExtractThinker Data Extraction 3.7 ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows. 1.6k★0/90d0 devs/90d -
Spacy-Layout Data Extraction 3.7 📚 Process PDFs, Word documents and more with spaCy 907★0/90d0 devs/90d -
gmft Data Extraction 3.6 Lightweight, performant, deep table extraction 537★0/90d0 devs/90d -
Extractous Data Extraction 3.3 Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages. 1.8k★0/90d0 devs/90d