SolaceLabs/solace-agent-mesh
Solace Agent Mesh is an open-source event-driven framework for building and orchestrating scalable multi-agent AI systems that integrate with real-world data and systems.
Awesome AI Agents › Collaborative Swarm Systems
OpenBMB/AgentVerse
AgentVerse is an advanced framework designed to facilitate the deployment and management of multiple large language model (LLM)-based agents across various applications. It primarily offers two core frameworks: task-solving and simulation. The task-solving framework enables the assembly of multiple agents into an automatic multi-agent system that collaboratively accomplishes complex tasks. This framework is applicable in domains such as software development systems and consulting systems, where agents can work together to solve problems efficiently. The simulation framework allows users to create custom environments to observe and interact with multiple agents, making it suitable for applications like games and social behavior research involving LLM-based agents. AgentVerse supports a variety of use cases demonstrated through several demos, including an NLP classroom where agents simulate a professor-student interaction, a Prisoner's Dilemma scenario exploring cooperation and betrayal between agents, and collaborative software design involving code writing, testing, and reviewing agents. The framework is actively maintained and evolving, with ongoing refactoring to enhance stability and support for both frameworks. It also supports integration with local LLMs such as LLaMA and Vicuna, and plans to introduce more sophisticated memory features for conversation history. AgentVerse has been recognized in the AI community, featured in NVIDIA's blog, and accepted for presentation at ICLR 2024. The project is open-source under the Apache 2.0 license and encourages community engagement through its GitHub repository, Hugging Face space, and Discord channel. Overall, AgentVerse provides a versatile and powerful platform for exploring multi-agent collaboration and emergent behaviors in AI agents, making it a valuable tool for researchers and developers working with LLMs in multi-agent settings.
https://github.com/OpenBMB/AgentVerse
Also in Collaborative Swarm Systems
langroid/langroid
Langroid is a Python framework that enables building LLM-powered applications using a multi-agent programming approach for collaborative problem solving and enhanced developer experience.
EvoAgentX/EvoAgentX
EvoAgentX is an automated framework for building a self-evolving ecosystem of AI agents that generate, evaluate, and execute multi-agent workflows based on natural language goals.
agentuniverse-ai/agentUniverse
agentUniverse is a multi-agent framework based on large language models that enables developers to build collaborative intelligent agents integrating domain expertise for solving complex problems.
hyperspaceai/agi
Public research log of Hyperspace, a libp2p peer-to-peer network where autonomous agents run experiments across five domains, gossip findings, pool machines into private pods and train models collaboratively.
101dotxyz/GPTeam
GPTeam is an open-source multi-agent simulation platform that uses GPT-4 to enable AI agents to collaborate and communicate effectively to achieve predefined goals.
fetchai/uAgents
uAgents is a lightweight Python framework by Fetch.ai for creating secure, decentralized autonomous AI agents that operate within a blockchain-enabled network.
kaushikb11/awesome-llm-agents
A curated list of awesome frameworks and tools for developing Large Language Model (LLM) agents, showcasing a wide range of capabilities and features for AI agent development.