Stars
LLM/ML research homelab setup scripts, focus on x86 + nvidia gpu, sm120, multi-node env
Official implementation of the paper Generalization at the Edge of Stability.
The agent that grows with you
Agent skill to turn any arxiv paper into a working implementation
Multi-agent racing tournament on MetaDrive
Makepad is a creative software development platform for Rust that compiles to wasm/webGL, osx/metal, windows/dx11 linux/opengl
tmux config with built-in terminal automation and agent-to-agent communication.
Generate embeddings from large-scale graph-structured data.
OpenClaw-RL: Train any agent simply by talking
AI agents running research on single-GPU nanochat training automatically
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…
An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and…
Generic building-block toolbox for training neural networks with adaptive and recursive execution. It provides reusable components to control iteration, stopping, and unrolling during training, ena…
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A JAX Research Toolkit for Visualizing, Manipulating, and Understanding Gemma Models with Multi-modal Support based on Penzai.
ADAG: Transluce's MLP neuron-level circuit tracing library
Interactive visualizations of the geometric intuition behind diffusion models.
Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
LLM Council works together to answer your hardest questions
Core 7 layers of production grade agentic system
Open-source implementation of AlphaEvolve