marlware
Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment
vmas
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
pymaro
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
benchmarl
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
gym-marl-reconnaissance
Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams
agentica
Agentica: Effortlessly Build Intelligent, Reflective, and Collaborative Multimodal AI Agents! 构建智能的多模态AI Agent。
https://github.com/bark-simulator/bark
Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving
multiagentpathfinding.jl
Structures and algorithms for Multi-Agent PathFinding in Julia
https://github.com/bytedance/deer-flow
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
comstream
In this project, we implemented a topic detection system on Twitter. This system reads tweets from a data stream and assigns them to one of the existing clusters or a new one. Each cluster acts as an agent, which makes the proposed approach a multi-agent system. There is also a coordinator, who monitors the whole system and coordinates the agent.
gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
tapeagents
TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle
tme-agent
TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.
https://github.com/agnostiqhq/multi-agent-llm
Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)
https://github.com/arbit3rr/flocking-multi-agent
Python implementation of "Flocking for multi-agent dynamic systems: Algorithms and theory" by Olfati-Saber for multi-agent triangular formation.
agilerl
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.