Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
Repository Index
111,828 visible repositories in the index
2,017–2,040 of 7,616 · Most stars
splinter - python test framework for web applications
- python
- selenium
- automation
- webdriver
Webkit based scriptable web browser for python.
Security Scanner for Agent Skills
Control Any Computer Using LLMs.
Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
Shared starter template configuration and CLAUDE.md memory bank system for Claude Code
- claude
- claude-ai
- claude-code
- subagents
An Open-World Foundation Model for General-Purpose Embodied Intelligence.
- robotics
- vision-language-action
- vla
- embodied-ai
[SIGGRAPH Asia 2026] UniMate: One Unified Model to Animate Diverse Skeletons
High-speed downloader for multiple platforms
- api
- bark
- bilibili
- douyin
🎙️ A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
A CLI for Xiaohongshu (小红书) — search, read, interact via reverse-engineered API
Send email in Python conveniently for gmail using yagmail
Simple Tensorflow Cookbook for easy-to-use
- tensorflow
- tensorflow-cookbook
- tensorflow-examples
The easy way to send notifications
- python
- notifications
- notifier
- notification-service
Decompiler Explorer! Compare tools on the forefront of static analysis, now in your web browser!
- angr
- decompiler
- ghidra
- ida-pro
Use a docx as a jinja2 template
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- low-precision
- pruning
- sparsity
- auto-tuning
在保留版面、公式与结构的前提下进行 PDF 翻译,适用于科研与技术文档
Client/server to synchronize media playback on mpv/VLC/MPC-HC/MPC-BE on many computers
Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
- pytorch-tutorial
- pytorch-tutorials
- pytorch
- quantization
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
- pytorch
- neural-architecture-search
- google-brain
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp