Stars
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
100M tokens. Infinite compute. Lowest val loss wins.
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.
⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.
Collection of reinforcement learning algorithms
A small utility for file sharing between your devices that are connected to the same local network.
A curated list of awesome things related to Pydantic! 🌪️
🎧 Open source music streaming app! Available for both desktop & mobile!
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Doom with bare metal programming on Raspberry Pi 3
Transfer tensors between PyTorch, Jax and more
PufferAI / rocket-lander
Forked from arex18/rocket-landerSpaceX Falcon 9 Box2D continuous-action simulation with traditional and AI controllers.
A framework for Reinforcement Learning research.
Implement a MNIST(also minimal) version of denoising diffusion probabilistic model from scratch.The model only has 4.55MB.
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
vwxyzjn / LeanRL
Forked from meta-pytorch/LeanRLLeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)
gym_airsim_multirotor is a customized OpenAI gym environement for AimSim.
Quadcopter Simulation and Control. Dynamics generated with PyDy.
This is a new repo used for training UAV navigation (local path planning) policy using DRL methods.
A benchmark environment for fully cooperative human-AI performance.
A minimalistic window with lyrics synced to Spotify on the surface of your screen