Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
23 repos
-
A Python library for running thousands of MuJoCo simulations in parallel on CPU
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.
-
Continued development of pufferdrive
-
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
-
Reproducible Microduck RL experiments, policies, simulation assets, and hardware add-ons
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
Continual learning infra for self-improving agents
-
A curated list of software, simulators, policies, agent tools and coverage for the Pollen Robotics / Hugging Face Microduck robot
-
Playing Prince of Persia (1989) using Reinforcement Learning.
-
Reinforcement Learning (RL) environments for the Microban platform, a 30cm open-source and affordable humanoid robot.
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
-
Puffing up reinforcement learning
-
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
-
Python-first native robotics simulation and reinforcement-learning environments
-
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
-
Official code for "Representation Learning Enables Scalable Multitask Deep Reinforcement Learning".
-
One policy. Any motion. Train universal whole-body tracking in mjlab—swap clips, not checkpoints.
-
Arctic Training and Inference Platform
-
Predictive Style Matching (PSM), is method in which an offline predictor maps the robot’s lower-body state history and velocity commands to interpretable upper-body joint and gait targets that shape the rewards during training.
-
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.