Libraries & frameworks
vectorizedmultiagentsimulator
proroklab/vectorizedmultiagentsimulator
A vectorized, differentiable multi-agent reinforcement learning simulator with a PyTorch 2D physics engine, multi-robot scenarios and Gym, RLlib and TorchRL integration.
Topics
Related projects
cleanrl10.7kHigh-quality single-file deep RL library covering PPO, DQN and SAC, focused on readability and reproducible experiment management.
relax669Large-scale asynchronous reinforcement learning engine for omni-modal model post-training, decoupling training from inference while supporting elastic scaling across distributed resources.
paperclip113.6kAn open-source control plane for orchestrating teams of AI agents with tasks, org charts, budgets, governance, and execution.
MiroFish84.9kA multi-agent swarm prediction engine that builds interactive digital worlds from seed materials for social, financial and opinion forecasting scenarios.
ruflo81.4kA meta-orchestration layer for Claude Code and Codex that coordinates agent swarms, memory, and secure federation.
MetaGPT71.2kA multi-agent software development system that turns a one-line requirement into PRDs, designs, and a complete code repo.