Frameworks for multi-agent collaboration
An open-source multi-agent simulation platform where multiple LLM-powered agents collaborate on complex tasks in shared environments, with customizable roles, memory systems, and environment interaction for studying multi-agent collaboration.
An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world. Showcases multi-agent collaboration in complex scenarios.
An accessible multi-agent sentiment analysis assistant that breaks filter bubbles, reveals true public opinion, and predicts trends — built from scratch without external frameworks.
SWE-AF is an autonomous software engineering fleet platform using a multi-agent factory architecture. It orchestrates planner, coder, reviewer, and verifier agents to automate the full software engineering lifecycle from issue analysis to code fix, scoring 95/100 on benchmarks.
A collection of projects showcasing RAG, agents, workflows, and other AI use cases with practical examples and tutorials.
Asynchronous coordination layer for AI coding agents providing identities, inboxes, searchable threads, and advisory file leases over FastMCP, Git, and SQLite.
The Multi-Agent Framework for building the first AI Software Company, enabling natural language programming with multi-role collaboration for automated requirement analysis, design, coding, and testing.
Latent Collaboration in Multi-Agent Systems — exploring implicit communication and coordination mechanisms for efficient multi-agent reasoning and task allocation.
Turn any AI agent into a living microservice that is interoperable, observable and composable, enabling standardized agent communication and orchestration.
Open Multi-Agent is a lightweight TypeScript multi-agent framework that auto-decomposes tasks and executes them in parallel with a single runTeam() call. Only 3 dependencies, deploys anywhere Node.js runs.
Shannon is a production-oriented multi-agent orchestration framework built in Go, focusing on efficient and reliable agent coordination and task scheduling for enterprise-grade multi-agent systems.
LazyLLM is a lightweight multi-agent LLM application framework offering the easiest way to build multi-agent LLM apps, with built-in RAG, knowledge graph, fine-tuning, and integration with LangChain and LlamaIndex ecosystems.
PraisonAI is a low-code multi-agent framework with handoffs, guardrails, memory, RAG, and 100+ LLM providers, deployable to Telegram, Discord, and WhatsApp.
A multi-agent framework enabling AI agents to collaborate effectively, helping developers build powerful multi-agent systems.
GenAI Agents is a comprehensive collection of 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
AgentVerse is a multi-agent deployment framework by Tsinghua OpenBMB, offering task-solving and simulation paradigms for collaborative multi-LLM-agent systems.
ChatDev 2.0 enables full-lifecycle software development through LLM-powered multi-agent collaboration, simulating role-based teamwork in a virtual software company.
Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.
A simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, multi-agent collaboration, and seamless tool integration with built-in memory and tree-of-thought reasoning.
100+ AI Agent and RAG apps you can actually run — clone, customize, and ship. A great reference for quickly building LLM-powered applications.
DeepResearchAgent is a hierarchical multi-agent system designed for deep research tasks and general-purpose problem solving, using a top-level planning agent to coordinate specialized sub-agents for automated task decomposition and efficient cross-domain execution.
A low-code tool to rapidly build and coordinate multi-agent teams for complex task execution.
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click. Features multi-role AI teachers, intelligent Q&A, and personalized learning paths to redefine online education.
TradingAgents is a multi-agent trading framework built with LangGraph that mirrors real-world trading firm dynamics with specialized LLM-powered agents for fundamental analysis, sentiment analysis, risk management, and more.
A multi-agent framework to fully automate anomaly detection across different modalities including tabular, graph, and time-series data.
Agency Swarm is a reliable multi-agent orchestration framework built on OpenAI API, providing structured multi-agent collaboration and communication.
ValueCell is a community-driven multi-agent platform for financial applications, enabling collaborative financial analysis, trading strategies, and market research through multi-agent orchestration.
Teams-first multi-agent orchestration for Claude Code. Designed for team collaboration with support for multi-agent coordination, task distribution, and result integration to enhance team AI development efficiency.
A2A (Agent-to-Agent) Protocol is an open protocol by Google enabling interoperability and collaborative communication between AI agents built across different frameworks and vendors.
AI Agent Orchestration Dashboard for managing AI agents, assigning tasks, and coordinating multi-agent collaboration.
Hive is a production-ready multi-agent execution harness providing state management, failure recovery, observability, and human-in-the-loop control with auto-generated multi-agent topologies for complex business workflows.
AG2 (formerly AutoGen) is an open-source AgentOS providing a multi-agent conversation framework with flexible agent orchestration, tool integration, and distributed collaboration for building complex multi-agent systems.
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms. Features real-time task tracking, agent status monitoring, and collaborative decision-making.
Open-source multi-agent framework from Alibaba, enabling the construction of observable and interpretable agents with rich distributed capabilities.
Taskara is an orchestration platform for long-running agent tasks and multi-step automation, emphasizing persistence, scheduling, and execution control.
An AI Agent workforce platform that assigns every team member an AI agent squad for multi-agent collaboration, task orchestration, and compound skill building to scale team capacity beyond headcount.
An LLM-based multi-agent framework that lets developers easily build multi-agent applications with core abstractions for agent roles, tools, knowledge management, and collaboration patterns.
A multi-modal multi-agent framework for document understanding that leverages multiple specialized agents to analyze and comprehend complex documents.
Spring AI Alibaba is an Agentic AI Framework for Java developers, built on the Spring ecosystem to provide multi-agent collaboration, workflow orchestration, and RAG capabilities.
OpenHands is an open-source AI software engineering agent platform that can automatically execute development tasks, modify code, and support collaborative iteration.
A multi-agent framework open sourced by Ant Group for creating and coordinating multiple AI agents to collaborate on complex tasks.
A curated collection of 500 AI agent use cases across industries including healthcare, finance, education, and retail. Showcases practical applications with open-source project links.
Agent Squad is an open-source multi-agent orchestration framework from AWS for managing multiple AI agents and handling complex conversations.
Microsoft's official travel planning AI agent demo showcasing multi-agent collaboration with Azure OpenAI and Semantic Kernel for itinerary, hotel, and activity planning.
AI agent teams for any project. Assemble multiple AI agents to collaborate on tasks with work division and parallel execution.
Self-hosted AI agent orchestration platform for dispatching tasks, running multi-agent workflows, monitoring spend, and governing operations
World's first open-source, agentic video production system with 12 pipelines, 52 tools, and 500+ agent skills. Turn your AI coding assistant into a full video production studio.
CAMEL is an open-source framework for multi-agent collaboration, supporting role-play, task decomposition, and coordinated execution.
OWL (Optimized Workforce Learning) is a multi-agent collaboration framework for real-world task automation, decomposing and executing complex tasks through agent interaction.
A multi-agent orchestration system inspired by ancient governance structures, featuring 9 specialized AI agents with a real-time dashboard, model configuration, and full audit trails for complex multi-agent collaboration scenarios.
Code repository for AI Agents Masterclass tutorials covering multi-agent systems, tool use, RAG, and more.
An open-source multi-agent chat interface for managing multiple agents in one dynamic conversation and connecting MCP servers for deeper research.
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for complex task completion.
A multi-agent collaboration framework where AI agents form crews to accomplish complex tasks together. Role definition, task assignment, tool sharing, and process orchestration.
A multi-agent coding system where orchestrator, explorer, and coder agents collaborate on software tasks with shared context.
A lightweight multi-agent orchestration demo showcasing how specialized agents collaborate to accomplish complex tasks.
DIMOS is an agentic operating system for physical space, enabling natural language control of humanoids, quadrupeds, drones, and other hardware platforms, with multi-agent systems that seamlessly integrate cameras, lidar, and actuators.
Self-improving multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI with TDD enforcement.
A custom AI agent platform that lets teams build and deploy AI assistants by composing multiple agents, connecting them to internal knowledge bases and tools for trusted AI-powered collaboration in enterprise workflows.
A curated list of AI autonomous agents. A comprehensive collection of open-source agent projects for discovering and understanding the agent ecosystem.
DB-GPT is an open-source agentic AI data assistant framework integrating multi-agent collaboration, RAG, and AWEL workflow engine, purpose-built for AI+Data applications.
Building a self-evolving ecosystem of AI agents with automatic optimization, role evolution, and multi-agent collaboration from single agent to complex systems.
ChatArena is a multi-agent language game environment for LLMs, designed to develop and evaluate communication and collaboration capabilities of AI agents across diverse game scenarios.
A powerful multi-agent orchestration framework built on LangGraph for intelligent task decomposition and collaborative execution.
An API-first multi-agent coding assistant with CodeAct-style tool calling, terminal support, and collaborative code execution.
Multi-agent workspace manager that supports agent team collaboration, task scheduling, and resource allocation. Provides a unified workspace view for efficient multi-agent coordination.
Gweaver is an experimental platform for multi-agent collaboration and task weaving, useful for exploring decomposition, coordination, and role-based execution.
Multi-agent framework for design, simulation, and auditing. Built in Rust for high-performance multi-agent collaboration.
Generate short videos with one click using AI LLM. Multi-step automation workflow from script generation to video composition.
A private agent fleet platform with spec coding, where each agent gets its own GPU-accelerated desktop for running Claude, Codex, Gemini and open models.
A multi-agent LLM-powered Chinese financial trading framework, enhanced Chinese version of TradingAgents with multi-source market data, real-time news, and LLM decision-making.
Bee Agent Framework is a production-ready AI agent development framework supporting both Python and TypeScript, offering multi-modal agent building, tool integration, and observability capabilities for rapid production deployment.
Enterprise-grade agentic workflow platform from iFlytek, offering commercial-friendly SuperAgent building capabilities with complex workflow orchestration and multi-agent coordination.
The RL bridge for LLM-based agent applications, providing a simple and flexible reinforcement learning framework to optimize agent performance.
An LLM-based multi-agent framework for web search engines, similar to Perplexity.ai Pro and SearchGPT, enabling intelligent web search.
Multi-agent orchestration for AI coding agents with pluggable runtime adapters for Claude Code, Pi, and more.
OxyGent is an open-source multi-agent collaboration framework from JD.com, supporting flexible agent role definition, task decomposition, and collaborative orchestration for enterprise AI agent applications.
KaibanJS is a JavaScript-native multi-agent framework with a Kanban-inspired approach for managing agent collaboration, supporting task assignment, role definition, and parallel execution for rapid multi-agent system development.
A lightweight, event-driven multi-agent framework for embodied AI systems providing efficient multi-agent collaboration for physical world applications.
An autonomous company operating system powered by AI agents, providing intelligent workflow automation for research, data analysis, customer communication and other business processes.
Swarms is an enterprise-grade production-ready multi-agent orchestration framework for deploying and scaling collaborative AI agent swarms.
Open Agent Platform is LangChain's open-source deployment platform for agents, focused on multi-agent execution, long-running tasks, observability, and production orchestration.
Langroid is a Python multi-agent programming framework that leverages an intuitive Agent-Task-Tool abstraction to help developers build LLM-powered multi-agent applications.
A multi-agent system that keeps running for ~100 hours and solves very complicated coding or math problems that can be verified.
A multi-agent framework written in Rust for building, deploying, and coordinating multiple intelligent agents, designed for high performance and memory safety in latency-sensitive production systems.
Microsoft's comprehensive multi-language framework for building, orchestrating, and deploying AI agents and multi-agent workflows with support for Python and .NET.
Microsoft AutoGen is a multi-agent conversation framework that lets you create multiple agents to collaborate through dialogue and solve complex tasks.
Microsoft's enterprise solution accelerator for multi-agent automation workflows using Azure OpenAI, with agent orchestration and task decomposition.
An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration, built in Rust for reliable multi-agent task coordination and scheduling.
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, and MCP tools.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems.
A 24/7 all-scenario AI agent platform by NetEase Youdao that automates various tasks with multi-model scheduling, tool integration, and intelligent workflow orchestration.
A complete LangGraph-based example of multi-agent RAG, showing agents collaborating on retrieval, routing, reasoning, and answer generation.
Offline multi-agent simulation and prediction engine using Neo4j graph database and Ollama local inference for swarm intelligence simulation.
Omnara (YC S25) - Talk to your AI agents from anywhere. A unified platform for multi-agent communication and task coordination across platforms.
OpenAgents - AI Agent Networks for Open Collaboration. Build, deploy, and manage AI agent networks with multi-LLM support.
A demonstration of advanced agentic patterns built on top of OpenAI's Realtime API, showcasing real-time voice interaction and multi-agent collaboration.
OpenAI Swarm is a lightweight multi-agent collaboration framework focused on simplicity and controllability, ideal for learning and prototyping.
The AI-native Multi-Agent development platform built on Kotlin Multiplatform, covering all 7 phases of SDLC. Supports automated code generation, testing, deployment, documentation and full development workflow.
Production-grade multi-agent orchestration platform with JSON-defined agents, multi-tier memory, and built-in observability, battle-tested on 200+ enterprise AI agents with full enterprise deployment support.
Home of the AI workforce featuring multi-agent systems, AI agents, and tools for building autonomous AI workflows in enterprises.
Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
Agent-MCP is a multi-agent framework built on the Model Context Protocol (MCP) that enables coordinated, efficient AI collaboration with multiple specialized agents working in parallel on different aspects of a project.
The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code/Codex integration.
Industry-first professional AI Agent platform for controllable film and video production, covering the entire pipeline from shorts to live-action.
A spec-driven multi-agent project management framework that turns requirements, planning, execution, and review into collaborative agent workflows.
ROMA (Recursive-Open-Meta-Agent) is a meta-agent framework for building high-performance multi-agent systems with recursive task decomposition and coordination.
Solace Agent Mesh is an event-driven multi-agent AI framework for building and orchestrating multi-agent systems with MCP integration and complex multi-step workflows.
A GenAI-powered multi-agent medical assistant for diagnostic support, healthcare research, and question answering through coordinated agent roles.
Multi-agent orchestration workflow platform supporting Claude Code, Codex, Gemini, OpenCode and more. Provides unified orchestration interface for cross-platform agent collaboration.
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous swarms, with persistent memory, MCP tools, schedules, delegation, and support for many LLM providers.
PUA is a highly proactive AI agent skill that motivates agents to continuously improve and deliver high-quality results within 30 days, using a performance-driven persona approach.
A powerful, easy-to-use Python library for implementing Google's Agent-to-Agent (A2A) protocol for inter-agent communication.
A self-organizing multi-agent collaboration platform where multiple AI agents work as an autonomous team, handling planning, executing, reviewing, and patrolling tasks with zero human intervention.
A Pydantic AI framework for Claude Code-style deep agents with tool calling, sandboxed execution, multi-agent teams, skills, checkpoints, and extended context.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks using multi-agent architecture with support for multiple LLM providers.
Intelligent automation and multi-agent orchestration for Claude Code. Supports automated workflows, task coordination, and intelligent agent system building.
Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun-karo-ashigaru hierarchy.
CowAgent (formerly chatgpt-on-wechat) is a powerful AI assistant framework built on LLMs with autonomous planning, tool use, long-term memory, multi-agent collaboration, and multi-channel integration for WeChat, Feishu, DingTalk, and more.
Most agent workflows fail at the orchestration layer, not the model. A practical comparison of DAG, state machine, and visual builder approaches with production-ready code for error handling, human approval gates, and conditional branching.
An in-depth comparison of mainstream AI agent frameworks including LangChain, LangGraph, CrewAI, and AutoGen to help you choose the best development stack.
A practical breakdown of browser-use strengths and limits in web task automation, with strategies for stable execution and failure recovery.
A hands-on guide to building a complete AI agent from scratch, covering environment setup, core components, and tool integration.
From protocol modeling and server design to permission isolation, this guide shows how to build a stable tool integration layer for AI agents with MCP.
An in-depth guide on how MetaGPT achieves full software development automation through role-playing, including practical guidance for PM, Architect, Engineer collaboration.