Starred repositories
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
PyINE is a research framework for scalable elicitation and oversight of LLM reasoning, built on instrumented Python programs as a verifiable execution substrate.
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
Inspect: A framework for large language model evaluations
Minimalistic 4D-parallelism distributed training framework for education purpose
Share a single keyboard and mouse between multiple computers.
Gym-Anything: Turn any Software into an Agent Environment
Breakthrough Method for Agile Ai Driven Development
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
AI agents running research on single-GPU nanochat training automatically
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.
An interface library for RL post training with environments.
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Fast PlayStation 1 emulator for x86-64/AArch32/AArch64/RV64
Model Context Protocol Servers
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Official implementation of Maia-2, a unified human-like chess model across skill levels. For new projects, see Maia-3.
About An application for new tourists to know the public transportation available from one place to another in the city
Open Source Routing Machine - C++ backend
Your go-to microservice framework for any situation, from the creator of Netty et al. You can build any type of microservice leveraging your favorite technologies, including gRPC, Thrift, Kotlin, R…
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)