The agent that grows with you

Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Python version of the Playwright testing and automation library.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Artificial Neural Engine Machine Learning Library

Port of OpenAI's Whisper model in C/C++

为 Agent Swarm 打造的 IDE ，支持 Kimi-2.5, GLM-4.7 等（即使不像 K2.5 那样经过强化学习的模型也能用）An IDE built for Agent Swarms, supporting Kimi-2.5, GLM-4.7, and more (compatible with models even without RL-reinforcement li…

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The "Python Machine Learning (3rd edition)" book code repository

NVIDIA cuTile learn

Helpful kernel tutorials and examples for tile-based GPU programming

Deep Learning for humans

Fully automatic censorship removal for language models

Tensor library for machine learning

github action to speedup building using ccache

React Native binding of llama.cpp

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

🔎 Open source distributed and RESTful search engine.

Python bindings for llama.cpp

🚀 The fast, Pythonic way to build MCP servers and clients.

MLX: An array framework for Apple silicon

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

A metasearch library that aggregates results from diverse web search services