Let Pi control your apps on MacOS & Windows

Memory Engine by Clone

Data pipeline for HRM-Text pretraining

The codebase of Cola DLM

Reproduce work of https://arxiv.org/abs/2605.06548

A Python framework for AI-driven character animation using neural networks.

A machine learning library with a TypeScript API and Rust backend. CUDA and WebGPU compatibility. Built to understand how ML frameworks and models work internally.

The First Context Engineer That Replaces You.

Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.

Vercel's official collection of agent skills

Public GitHub Releases for the Autoskills CLI

Fully automatic censorship removal for language models

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Algorithm powering the For You feed on X

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Democratizing Reinforcement Learning for LLMs

A character-level language diffusion model trained on Tiny Shakespeare

Easily and securely send things from one computer to another 🐊 📦

dLLM: Simple Diffusion Language Modeling

The best ChatGPT that $100 can buy.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Post-training with Tinker

Cheat Engine. A development environment focused on modding

Neural Networks: Zero to Hero

An autoregressive character-level language model for making more things

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Open-source, secure environment with real-world tools for enterprise-grade agents.

Lightweight coding agent that runs in your terminal

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI