Awesome AI Agents › Collaborative Swarm Systems
Tribe AI is a low-code tool designed to rapidly build and coordinate multi-agent teams to solve complex tasks more efficiently. It leverages the langgraph framework to enable users to customize and orchestrate teams of agents, each specializing in different skills, to collaboratively tackle problems. The platform supports both sequential and hierarchical workflows, allowing agents to either execute tasks in a step-by-step sequence or operate in a team-like structure with leaders and members delegating and managing subtasks. This flexibility makes Tribe suitable for a wide range of applications, including football analysis, trip planning, and customer service, where different agents handle specific aspects of the task. Key features of Tribe include persistent conversations that save chat histories for ongoing interactions, observability through real-time monitoring of agent performance using LangSmith, and tool calling capabilities that allow agents to utilize external APIs and tools. It also supports retrieval augmented generation (RAG) to enable agents to reason with internal knowledge bases, human-in-the-loop functionality for human approval before tool execution, and integration with open-source large language models like llama, Gemma, and Phi. Tribe offers easy deployment options via Docker and supports multi-tenancy for managing multiple users and teams. Users can equip agents with various skills such as web searching, Wikipedia lookup, and financial news retrieval, and can create custom skills either through simple function definitions or by coding custom skills. The project emphasizes ease of use with drag-and-drop interfaces for building agent teams and provides comprehensive guides for deployment, workflow design, and skill creation. Tribe is actively developed and aims to enhance problem-solving by enabling collaborative agent teams that are adaptable, observable, and easy to manage.
https://github.com/StreetLamb/tribe
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.
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.
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.