Awesome AI Agents › Collaborative Swarm Systems
agentUniverse is a sophisticated multi-agent framework designed to facilitate the development of multi-agent applications leveraging large language models (LLMs). It provides a flexible and extensible platform for building intelligent agents that can collaborate effectively to solve complex problems across various domains. The framework is built around a rich set of multi-agent collaborative pattern components, which act as a collaborative pattern factory. These components enable agents to perform distinct roles and maximize their capabilities through coordinated efforts. agentUniverse emphasizes the integration of domain-specific knowledge, allowing developers to embed expert experience seamlessly into the agents' workflows, enhancing their problem-solving effectiveness. Originating from real-world financial business practices at AntGroup, agentUniverse aims to assist developers and enterprises in creating domain-expert-level intelligent agents that work together to accomplish tasks efficiently. The framework includes several pre-built pattern components such as the PEER pattern, which divides tasks among agents responsible for planning, execution, expression, and review to iteratively improve reasoning and analysis. Another example is the DOE pattern, which focuses on data-intensive tasks requiring precision and expert opinion integration, such as financial report generation. agentUniverse supports integration with a wide range of LLMs from various vendors including Qwen, Deepseek, OpenAI, Claude, Gemini, Llama, KIMI, WenXin, chatglm, BaiChuan, and Doubao. This flexibility allows users to configure and switch between models easily to suit their application needs. The framework is open-source, licensed under Apache 2.0, and provides comprehensive documentation, tutorials, and sample applications to help users get started quickly. Overall, agentUniverse is a powerful tool for building collaborative multi-agent systems that leverage the latest advancements in LLM technology, with a strong focus on domain expertise and practical application in real-world scenarios.
https://github.com/agentuniverse-ai/agentUniverse
AgentVerse is a versatile open-source framework that enables the deployment and collaboration of multiple LLM-based agents for task-solving and simulation applications, supporting research and development in multi-agent AI systems.
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.
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 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.
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.
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.
uAgents is a lightweight Python framework by Fetch.ai for creating secure, decentralized autonomous AI agents that operate within a blockchain-enabled network.
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.