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.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
47,133 repositories indexed
1–24 of 56 · Most stars
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.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
Developer-first error tracking and performance monitoring
Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Transparent proxy server that works as a poor man's VPN. Forwards over ssh. Doesn't require admin. Works with Linux and MacOS. Supports DNS tunneling.
Static site generator that supports Markdown and reST syntax. Powered by Python.
a small, expressive orm -- supports postgresql, mysql, sqlite, now with asyncio
Tool for real-time visualization, monitoring and collaborative analysis of AI/ML experiments and live data. Supports Python, PyTorch/Torch, NumPy, TensorFlow/Keras https://visdom.dev
~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.
A Python utility / library to sort imports.
A flexible package manager that supports multiple versions, configurations, platforms, and compilers.
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
This tool lets you search your gadgets on your binaries to facilitate your ROP exploitation. ROPgadget supports ELF, PE and Mach-O format on x86, x64, ARM, ARM64, PowerPC, SPARC, MIPS, RISC-V 64, and RISC-V Compressed architectures.
Network recon framework. Build your own, self-hosted and fully-controlled alternatives to Shodan / ZoomEye / Censys and GreyNoise, run your Passive DNS service, build your taylor-made EASM tool, collect and analyse network intelligence from your sensors, and much more! Uses Nmap, Masscan, Zeek, p0f, ProjectDiscovery tools, etc.
Rated, auto-refreshed list of decompiled, recompiled & reverse-engineered games: decomps, static recomps, source ports, engine remakes, browser ports.
A WeeChat script for Slack.com. Supports threads and reactions, synchronizes read markers, provides typing notification, etc..
A Minecraft world editor and converter that supports all versions since Java 1.12 and Bedrock 1.7.
A fast, user friendly ORM and query builder which supports asyncio.
Self hosted file converter and compression tool for images, video, audio, json, excel and more. Supports over 3,000 conversions!
Audit AI chat exports locally before sharing or migration. Find possible secrets, personal-data patterns, broken JSON/JSONL, SQLite issues, and scan gaps—without uploading the archive.