Stars
Lightweight coding agent that runs in your terminal
A fork of Julien Pommier's Pretty Fast FFT (PFFFT) library, with several additions
DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding
GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Safety-critical controllers for single/multi robotic navigation: CBF-QP, MPC-CBF, and etc.
Group theory visualization software in the browser
[CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
PyTorch code and models for the DINOv2 self-supervised learning method.
Tools for understanding how transformer predictions are built layer-by-layer
A platform for reproducible world model research and evaluation
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Embodied Drosophila: 138,639-neuron whole-brain connectome simulation (FlyWire v783) in a biomechanical body (NeuroMechFly v2 / MuJoCo). Vision, olfaction, gustation, flight, and emergent behaviors…
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
Ray tracing and hybrid rasterization of Gaussian particles
A lightweight compiler and virtual machine that implements eBPF-like embedded programming language, with a unique capability of execution migration.
A lightweight, lightning-fast, in-process vector database
Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀
Firmware, hardware and documentation for my autonomous quad copter project
A small, fast, and embeddable programming language based on Lua with a gradual type system.
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Autonomous Navigation and Collision Avoidance for Ground Robots