The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
- text-extraction
- document-intelligence
- metadata-extraction
- pdf-extraction
47,133 repositories indexed
1,105–1,128 of 6,303 · Most stars
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
📱 objection - runtime mobile exploration
Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.
A terminal spreadsheet multitool for discovering and arranging data
AutoML library for deep learning
A powerful and user-friendly binary analysis platform!
TensorFlow Tutorials with YouTube Videos
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
💨 Fast, Async-ready, Openapi, type hints based framework for building APIs
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
OctoPrint is the snappy web interface for your 3D printer!
Chisel is a collection of LLDB commands to assist debugging iOS apps.
Supervisor process control system for Unix (supervisord)
Prevent cloud misconfigurations and find vulnerabilities during build-time in infrastructure as code, container images and open source packages with Checkov by Bridgecrew.
The property-based testing library for Python
An interactive command-line HTTP and API testing client built on top of HTTPie featuring autocomplete, syntax highlighting, and more. https://twitter.com/httpie
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Deep universal probabilistic programming with Python and PyTorch
Run Windows software and games on Linux
Open Source HR and Payroll Software
Beautifier for javascript
🐍🎮 pygame (the library) is a Free and Open Source python programming language library for making multimedia applications like games built on top of the excellent SDL library. C, Python, Native, OpenGL.
Speech recognition module for Python, supporting several engines and APIs, online and offline.