Lists (1)
Stars
🤗 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.
Distributed Compiler based on Triton for Parallel Systems
A simple, performant, and scalable Jax LLM!
Collective communications library with various primitives for multi-machine training.
Anki is a smart spaced repetition flashcard program
DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale
CastleHill: Separable Causal Diffusion / Varitaion Flow Maps for LTX-2 long-form video generation
Algorithm powering the For You feed on X
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An overview of the different types of charts you can make with Swift Charts
Implement a reasoning LLM in PyTorch from scratch, step by step
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Official Codebase For paper "One-step Language Modeling via Continuous Denoising"
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.
Compound Engineering Framework for Alpha Feature Research in Quant Finance
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent. Stop babysitting your terminal. Employ a Peon today.
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
The Karpathy treatment for OpenClaw - stripped to ε. 515 lines of Python, 6 files, one dependency.
[ECCV 2026] Generate high resolution videos with a custom voice and appearance, based on LTX-2/LTX-2.3 + Identity In-Context LoRA
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
2-8B parameter image gen that actually runs fast on your Mac. 14 seconds. No cloud. No GPU rental.
LTX-2 text-to-video generation for Apple Silicon using MLX Swift
An open-source desktop app for generating videos with LTX models