OCR & Documents
enoch3712/ExtractThinker
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
🧠 Natural Language Processing
PythonApache-2.0updated Sep 16, 2026
🏆 #1,442 overall#217 of 313 in OCR & Documents🔥 active this week
run-llama /ParseBench
ParseBench - A Document Parsing Benchmark for AI Agents
$ git clone https://github.com/run-llama/ParseBench.gitStars
592
592
Forks
109
109
Language
Python
License
Apache-2.0
Created
Apr 10, 2026
0.5 years old
Last push
Sep 23, 2026
🔥 this week
Categories
More in OCR & Documents
OCR & Documents
paperless-ngx/paperless-ngx🔥 active
A community-supported supercharged document management system: scan, index and archive all your documents
PythonGPL-3.0updated Sep 24, 2026
OCR & Documents
Zipstack/unstract🔥 active
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
PythonAGPL-3.0updated Sep 24, 2026
OCR & Documents
yobix-ai/extractous
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
🧠 Natural Language Processing
RustApache-2.0updated Dec 21, 2024
OCR & Documents
NanoNets/docstrange
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
PythonMITupdated Oct 31, 2025
OCR & Documents
aiptimizer/TurboOCR
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
C++MITupdated Sep 8, 2026
Data from GitHub · snapshot Sep 24, 2026