Multi Agent Systems: open-source projects on GitHub
72 repositories on Multi Agent Systems, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Claude Agent Orchestration
Leading agent orchestration platform for Claude, enabling deployment of intelligent swarms and creation of conversational AI systems.
★ 49,189 · TypeScriptMulti-Agent Orchestration Claude
A platform for team collaboration with multiple agents in the Claude Code environment, simplifying coordination and task execution.
★ 33,521 · TypeScriptDeepTutor: Personal AI Tutor
DeepTutor — an AI-agent open-source project for personalized learning. 24341 ⭐ on GitHub, Python.
★ 24,341 · PythonFROM PROTOTYPE TO ENTERPRISE
Complete step-by-step tutorials for building GenAI agents for production — from prototype to enterprise deployment.
★ 20,541 · Jupyter NotebookADK Python: AI Agents
Open-source tool for creating and deploying AI agents on Python with full control.
★ 19,647 · PythonOPEN SOURCE COWORK DESKTOP FOR AI AGENTS
Open-source desktop application for multi-agent AI workforces. Runs complex workflows locally with support for any models and MCP.
★ 15,836 · TypeScriptMULTI-AGENT SYSTEM FOR CODE
Openrig combines Claude Code and Codex into a single agent framework. It orchestrates their work, enabling complex coding‑tasks via a unified CLI. Supports TypeScript and
★ 8,852 · TypeScriptADK-GO: AI Agent Framework
An open Go framework for building, evaluating, and deploying complex AI agents with flexibility and control.
★ 7,933 · GoMulti-Agent Orchestration Framework
The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai
★ 6,741 · PythonHARNESS-SDK: CREATE AI AGENT FAST
A model-driven SDK lets you create AI agents in just a few lines of Python code.
★ 5,999 · PythonStrands Agents SDK
A model-based approach to creating AI agents in just a few lines of code.
★ 5,888 · PythonPLATFORM FOR AI AGENT LIFECYCLE
Solace Agent Mesh — platform for full AI agent lifecycle: build, test, deploy, monitor, improve. Hosts agents, runs their tools, and coordinates via event mesh with sessi
★ 4,923 · ShellSolace Agent Mesh
Framework for building and orchestrating multi-agent AI systems with support for event-driven architecture and integration with real data sources.
★ 4,245 · PythonKoog — AI Framework for JVM
A powerful Kotlin framework for building reliable and resilient AI agents ready for enterprise use. Supports backend, Android, iOS and browsers.
★ 4,197 · KotlinLANGRID - Multi-agent AI for Code
A simple framework for building LLM-based agents with memory and tool support.
★ 4,029 · PythonSprix Sage Router
Sprix AI, together with 屿智同行, presents a state-aware router for agent networks, supporting SELF, COLLABORATE, and HANDOFF modes. Implemented in Python and easily integrat
★ 3,563 · PythonEVOLUTION OF MULTI-AGENT SYSTEMS
EvoAgentX is a framework for building self-evolving AI agents with memory. Supports multi-agent scenarios and LLM integration. GitHub stars: 3.3k.
★ 3,435 · PythonNEO: SELF-EVOLVING AI DEVELOPER
Neo.mjs is a self-replicating AI team that deploys a cross-model swarm into live applications via Neural Link, Hybrid GraphRAG, and self-healing cycles.
★ 3,199 · JavaScriptAI AGENTS: THE DEFINITIVE GUIDE
A complete guide to building AI agents: from concept to practice in Jupyter Notebook.
★ 2,949 · Jupyter NotebookMANTIS: TOOL FOR AI AGENTS
A modular skill set for autonomously discovering, reproducing, and fixing vulnerabilities in AI-agent code.
★ 2,782Multi-agent CLI bridge
CLI command to manage multi-agent work teams based on Claude, Codex, Gemini, and other AI models with project memory and tmux oversight.
★ 2,696 · PythonCompany Analysis Agent
A multi-agent tool for deep company analysis based on LangGraph, Tavily, and Gemini 2.5 Flash models with GPT-5.1.
★ 2,319 · PythonNIMBALYST VISUAL WORKSPACE
Visual workspace for Claude Code, Codex and OpenCode. Run multiple AI agents in parallel, edit output in markdown and diagrams.
★ 2,078 · TypeScriptADK-JAVA - CODE FRAMEWORK FOR AI
Open-source Java toolkit for creating, evaluating, and deploying AI agents with full control over code.
★ 1,769 · JavaOuroboros – Self‑Created AI
A self‑born agent that writes itself in Python. With 726 branches it is already grateful to the community.
★ 1,667 · PythonUAGENTS — CREATE AGENTS FAST
A fast and lightweight Python framework for creating decentralized agents.
★ 1,645 · PythonCLI-AGENT-ORCHESTRATOR - MULTI-AGENT ORCHESTRATION
The project orchestrates multiple AI agents (Claude Code, Kiro, Codex) in separate tmux sessions, simplifying collaborative code work.
★ 1,561 · PythonLUA N1AO AGENT: AI-PENTEST
An autonomous AI agent for system penetration, using a dual reasoning graph. Developed by Professor Lu Hui's team from Guangzhou.
★ 1,476 · Python80+ AI Agents in Python
Over 80 ready‑to‑use examples of AI agents in Python: autonomous agents, multi‑agent systems, and integration with uAgents, ASI:One, LangChain, and other frameworks.
★ 1,471 · PythonAGENTLAS-OS: Agents Environment
Manage specialist agents via a hub, automatically creating orchestrators for tasks. Works locally and is compatible with any model.
★ 1,458 · PythonCOORDINATION OF CLAUDE CODEX CURSOR
squadra synchronously manages windows of Claude, Codex and Cursor: tasks, prechecks, parallel tests. Built-in skills recall lessons, simplify code and forecast work.
★ 1,279 · PythonAUTOPROMPT-SKILL - SMART CODE AGENT
Autoprompt-skill is an AI agent skill that reduces code errors by 45% when completing agent tasks.
★ 1,242 · JavaScriptDARK-MOON Autonomous AI Pentest
Autonomous AI engine for continuous pentesting of web, cloud, AD, and Kubernetes with real vulnerability exploitation.
★ 1,238 · PythonADK‑JS AI Agent Toolkit
ADK‑JS is an open‑source TypeScript toolkit for building, evaluating, and deploying advanced AI agents with full control and flexibility.
★ 1,190 · TypeScriptENTERPRISE DEEP RESEARCH - DATA RESEARCH WITHOUT LIMITS
Salesforce Enterprise Deep Research is a tool for deep analysis of corporate data in Python using advanced AI methods.
★ 1,174 · PythonPOWERFUL TOOLS FOR AGENTS
A set of Python tools that extend the capabilities of AI agents.
★ 1,089 · PythonUniversal multi-agent framework
Portable platform for creating and managing agents based on the .agents standard with support for multiple development environments.
★ 993 · TypeScriptSTRANDS AGENT SAMPLES
Examples of agents created with the Strands Agents SDK in Python. Ready-made templates for quick start of AI agent development.
★ 940 · PythonPocketPaw: Your AI Agent
Launch your personal AI agent in 30 seconds. Full data control thanks to self-hosting.
★ 820 · PythonAI Maestro: Agent Management
AI Maestro orchestrates agents with memory search, code queries, and messaging. Manage Claude, Codex, or any AI from a single panel.
★ 697 · TypeScriptFLUJO: Multi-Agent Automation
FLUJO is a framework for building self‑learning multi‑agents and automating workflows in TypeScript.
★ 675 · TypeScriptAGENT ORCHESTRATORS SELECTION
Collected over 600 stars — the best tools for managing AI agents in one repository.
★ 664RAI: Agent for Robots
RAI is a framework for physical AI robots on ROS 2 and Python, supporting voice interaction, scenarios, and logs.
★ 616 · PythonMASFactory Vibration Multi-Agent
MASFactory is a Python framework for orchestrating multi-agent systems using a graph-centric approach and vibrational modeling.
★ 564 · PythonCAURA Shared AI Memory
Caura provides managed shared memory for AI agent fleets with multi‑tenant support, trust policies, and an audit trail.
★ 559 · PythonNEURO-SAN AI STUDIO
Neuro-san studio – a playful environment for rapid prototyping and testing of neural networks in Python. Suitable for experiments with LLMs and generative models.
★ 523 · PythonOPENTEAMS - AI TEAM FOR CODE
openteams lets you create, plan, and deliver code using a team of AI agents instead of a single developer.
★ 455 · TypeScriptPLATFORM FOR AI AGENTS
The open CAIPE platform helps create, deploy, and manage AI agents and their workflows on TypeScript.
★ 444 · TypeScriptMETIS: BOOSTING AI/LLM CODING EFFICIENCY
Metis is a TypeScript agent that boosts AI/LLM coding performance by 50%. It has already garnered 297 stars on GitHub and offers ready‑to‑use skills for automating testin
★ 443 · TypeScriptBUILDING MULTI-AGENT AI
Practical workshop on creating a multi-agent AI system with Deep Research Agent and Writing Workflow as MCP servers. Includes code, slides, and video.
★ 436 · PythonMULTI-AGENT ORCHESTRATOR FOR VS CODE
FacadeCode is a multi-agent orchestrator for VS Code. Runs Claude Code, Codex, and other CLI agents that launch, message, and operate each other across windows and machin
★ 367 · TypeScriptALPHORA: BUILDING AI AGENTS
A production Python platform for building composite AI agents, ready for scaling and integration.
★ 348 · PythonZYPHER AGENT: FULL GAME CONTROL
A minimalistic TypeScript framework for building AI agents with full control over tools, providers, and execution flow.
★ 332 · TypeScriptOPEN WORLD OF AI AGENTS
A simple start in the world of AI agents: notebooks with examples and practical tasks.
★ 328 · Jupyter NotebookNAC: HARNESS FOR AGENTS AND TASKS
nac — open-source harness in Rust for executing long-running tasks of AI agents. It uses a central orchestrator, threads, and structured episodes to keep work aligned wit
★ 314 · RustCONTEXT ENGINEERING FOR MAS
Universal framework for building multi-agent systems via semantic orchestration. Reduce code and speed up development.
★ 300 · Jupyter NotebookMCP SERVER FOR STRANDS AGENTS
MCP server that provides Strands Agents documentation to your AI tools for easy agent coding.
★ 296 · PythonALPACA TRADING AGENT
AlpacaTradingAgent — a multi-agent LLM framework for automated trading via Alpaca API. It supports market data analysis, trading signal generation, and order execution in
★ 284 · Pythonphi - Simple Phi-4 Launch
Run the powerful multimodal Phi-4 model directly on your Mac with Apple Silicon — no cloud, no complex setup.
★ 280 · Jupyter NotebookAGENTARK: ONE LLM INSTEAD OF MANY AGENTS
Official AgentArk implementation from CMU and Georgia Tech. Method distills multi-agent intelligence into a single LLM agent preserving task quality. Python code, 260 Git
★ 280 · PythonNew projects on this topic in Telegram
Telegram →