Updated 6 months ago

marlware • Rank 16.4 • Science 64%

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

Updated 6 months ago

vmas • Rank 15.9 • Science 64%

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.

Updated 6 months ago

pymaro • Rank 15.5 • Science 51%

Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

Updated 6 months ago

benchmarl • Rank 8.2 • Science 54%

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.

Updated 6 months ago

gym-marl-reconnaissance • Rank 3.8 • Science 54%

Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams

Updated 6 months ago

agentica • Rank 11.6 • Science 44%

Agentica: Effortlessly Build Intelligent, Reflective, and Collaborative Multimodal AI Agents! 构建智能的多模态AI Agent。

Updated 6 months ago

multiagentpathfinding.jl • Rank 2.8 • Science 44%

Structures and algorithms for Multi-Agent PathFinding in Julia

Updated 5 months ago

https://github.com/bytedance/deer-flow • Rank 12.4 • Science 26%

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.

Updated 6 months ago

flatland.jl • Rank 2.5 • Science 31%

A barebones Julia version of the Flatland railway simulator

Updated 6 months ago

liteswarm • Science 44%

Lightweight Agent Framework for building AI apps with any LLM

Updated 6 months ago

comstream • Science 67%

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.

Updated 6 months ago

gym-pybullet-drones • Science 77%

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

Updated 6 months ago

tapeagents • Science 54%

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

Updated 6 months ago

tme-agent • Science 54%

TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.

Updated 5 months ago

https://github.com/agnostiqhq/multi-agent-llm • Science 23%

Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)

Updated 5 months ago

https://github.com/arbit3rr/flocking-multi-agent • Science 36%

Python implementation of "Flocking for multi-agent dynamic systems: Algorithms and theory" by Olfati-Saber for multi-agent triangular formation.

Updated 6 months ago

mallm • Science 44%

Framework: Multi-Agent LLMs For Conversational Task-Solving (MALLM)

Updated 6 months ago

agilerl • Science 54%

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.