[NeurIPS 2023 Spotlight] LightZero
TextWorld is a sandbox learning environment for the training
Advanced evolutionary computation library built on top of PyTorch
Implementation of RLHF (Reinforcement Learning with Human Feedback)
An API standard for multi-agent reinforcement learning environments
Massively parallel rigidbody physics simulation
Training framework for Stable Baselines3 reinforcement learning agents
Monte Carlo tree search in JAX
Phi-3.5 for Mac: Locally-run Vision and Language Models
SwarmZero's SDK for building AI agents, swarms of agents and much more
The Library for LLM-based multi-agent applications
VMAS is a vectorized differentiable simulator
MuA multi-agent reinforcement learning environment
Build high-performance AI models with modular building blocks
Research-oriented chatbot framework
GuardDog is a CLI tool to Identify malicious PyPI and npm packages
Chat with your SQL database
Run AI-powered workflows over your codebase
An Autonomous LLM Agent for Complex Task Solving
Adala: Autonomous DAta (Labeling) Agent framework
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model
Create Customized Software using Natural Language Idea
A TensorFlow library for applied reinforcement learning
Pretrained model hub for Keras 3
World of apps for benchmarking interactive coding agent