affaan-m/ECC
ECC is a harness-native operator system designed for agentic AI work, providing a comprehensive solution with skills, memory optimization, security, and research-first development across multiple A...
Awesome AI Agents › Multi-Agent Frameworks
Multi-Agent Frameworks
ruvnet/ruflo
Ruflo is a leading agent orchestration platform for Claude, enabling the deployment of intelligent multi-agent swarms, coordination of autonomous workflows, and building conversational AI systems.
Yeachan-Heo/oh-my-claude-sisyphus
Oh My Claude Sisyphus (OMC) is a multi-agent orchestration framework for Claude Code, simplifying complex AI agent workflows without a steep learning curve.
microsoft/JARVIS
JARVIS is a collaborative AI system that connects large language models with expert AI models from HuggingFace to autonomously plan, execute, and integrate complex AI tasks.
rowboatlabs/rowboat
Rowboat is an AI-powered platform that enables users to build and manage multi-agent swarms using natural language, integrating tools and knowledge for automated workflows and deployment via API or SDK.
cft0808/edict
Edict is an OpenClaw Multi-Agent Orchestration System featuring 9 specialized AI agents, a real-time dashboard, model configuration, and full audit trails, inspired by ancient Chinese imperial gove...
MemoriLabs/Memori
Memori is a versatile SQL native memory layer designed to enhance LLMs, AI agents, and multi-agent systems with advanced memory management, seamless integration, and high performance.
HKUDS/DeepCode
DeepCode is an open-source project that uses multi-agent AI systems to convert research papers and natural language into production-ready code through both CLI and web interfaces.
xbtlin/ai-berkshire
AI Berkshire is an investment research framework leveraging AI agents (Claude Code/Codex) to automate value investment analysis, synthesizing methodologies from renowned investors like Buffett and ...
aiming-lab/AutoResearchClaw
AutoResearchClaw is an autonomous, self-evolving system that generates scientific papers from an idea, incorporating multi-domain experiment agents and human-in-the-loop collaboration.
microsoft/agent-framework
Microsoft Agent Framework is a multi-language framework for building, orchestrating, and deploying AI agents and multi-agent workflows with support for Python and .NET.
omnigent-ai/omnigent
Omnigent is an open-source AI agent framework and meta-harness for orchestrating, supervising, and governing various AI agents, offering real-time collaboration and sandboxed execution across devices.
2FastLabs/agent-squad
Agent Squad is an open-source framework for orchestrating multiple AI agents to manage complex conversations, featuring intelligent intent classification, context management, and dual Python/TypeSc...
chaitanyagiri/munder-difflin
Desktop app that wraps terminal coding-agent CLIs like Claude Code and Codex into a coordinated multi-agent office with shared memory and messaging.
KunAgent/Kun
Kun is a local-first AI agent workspace designed for coding, writing, design, research, and automation, offering a unified runtime for desktop GUI and TUI interactions.
agentscope-ai/agentscope-java
AgentScope Java is an agent-oriented programming framework for building production-ready LLM-powered applications, offering features like ReAct reasoning, tool calling, memory management, and multi...
PurpleAILAB/Decepticon
Decepticon is an autonomous multi-agent Red Team testing service that uses AI to execute realistic attack chains, generating comprehensive engagement packages and operating within defined rules of ...
modelscope/ms-agent
MS-Agent is a lightweight and extensible framework that empowers autonomous agents with multi-agent capabilities, code generation, tool calling, and advanced exploration for complex task execution.
openagents-org/openagents
OpenAgents provides a collaborative operating system and platform for AI agents, enabling them to work together in a shared workspace with persistent context, files, and a browser.
parcadei/Continuous-Claude
Continuous Claude enhances Anthropics Claude Code with persistent context management, multi-agent orchestration, and intelligent code analysis to prevent compaction and enable continuous learning a...
openai/openai-agents-js
The OpenAI Agents SDK is a lightweight and powerful JavaScript/TypeScript framework for building multi-agent workflows and real-time voice agents with features like tool integration, handoffs, guardrails, and tracing.
i-am-bee/beeai-framework
BeeAI Framework is a production-ready framework for building scalable and flexible multi-agent AI systems in Python and TypeScript, supporting integration with various AI models and tools.
Kocoro-lab/Shannon
Production multi-agent platform in Go, Rust and Python that routes tasks across execution strategies on Temporal workflows, enforcing token budgets, WASI sandboxing, policy checks and replayable debugging.
Orkas-AI/Orkas
Local-first desktop application where a commander agent breaks down a goal and coordinates specialist agents in parallel or in sequence, using your own model keys and external CLI coding agents.
zchoi/Awesome-Embodied-Robotics-and-Agent
A curated and actively maintained repository compiling the latest research and advancements in Embodied AI and robotics integrated with Large Language Models and Vision-Language Models.
starpig1129/DATAGEN
DATAGEN is an AI-powered multi-agent research assistant that automates hypothesis generation, data analysis, visualization, and report writing, with expanding capabilities in crypto market intelligence through a strategic partnership.
HITsz-TMG/FilmAgent
FilmAgent is a multi-agent framework that automates the entire film production process in virtual 3D spaces by simulating key crew roles and employing collaborative strategies for scriptwriting and cinematography.
jgravelle/AutoGroq
AutoGroq is a revolutionary tool that dynamically generates tailored teams of AI agents to efficiently address user projects and inquiries without manual configuration.
google/adk-js
Code-first TypeScript toolkit for building, evaluating, and deploying AI agents, with type-safe tools, multi-agent orchestration, and dev tooling for Node.js and the browser.
yohey-w/multi-agent-shogun
Shell and tmux system that runs several AI coding CLIs in parallel under a samurai-themed shogun, karo and ashigaru hierarchy, coordinating agents through YAML files on disk instead of API calls.
tembo/tembo
Tembo is a unified command-line interface that consolidates multiple coding agents into one tool to enhance developer productivity and streamline coding workflows.
Ido-Levi/Hephaestus
Python agentic framework where agents work in Analysis, Implementation and Validation phases and may spawn tasks in any phase, so the workflow tree grows from what agents discover at runtime.
massgen/MassGen
MassGen is a Python multi-agent framework in which several agents independently solve the same task, observe and critique each other across refinement cycles, then vote to select the best answer.
cognizant-ai-lab/neuro-san-studio
Example and tutorial playground for the Neuro SAN multi-agent framework, where agent networks are declared in HOCON files and delegate subtasks through the adaptive AAOSA protocol.
AFK-surf/open-agent
Self-hostable open-source agentic AI system positioned as an alternative to Claude Agent SDK, ChatGPT Agents and Manus, running a multi-agent framework over several model providers.
Human-Agent-Society/CORAL
CORAL is Python infrastructure for autonomous multi-agent research runs, giving coding agents isolated git worktrees, graded evaluation, shared persistent state and island-based evolution across several agent runtimes.
Pan-Chera/Multi-Agent-CAD
Multi-agent framework that turns short natural language descriptions into printable parametric 3D models by generating build123d code, reported to use far fewer tokens than single-agent text-to-CAD baselines.
microsoft/maro
Microsoft MARO is a Reinforcement Learning as a Service platform designed for real-world multi-agent resource optimization across various industrial domains, providing comprehensive simulation, RL, and distributed toolkits.
JuliaDynamics/Agents.jl
Agents.jl is a high-performance, user-friendly Julia framework for agent-based modeling that supports both discrete and continuous-time simulations with extensive built-in agent actions and Open Street Maps integration.
wecode-ai/Wegent
Wegent is a self-hostable platform for defining and running teams of AI agents, combining a web control plane with the Wework desktop client for local code and terminal execution.
liquidos-ai/AutoAgents
AutoAgents is a Rust multi-agent framework with typed agents, derive-macro tools, sliding-window memory, pluggable cloud and local LLM backends, and OpenTelemetry observability.
ltjed/freephdlabor
freephdlabor is a Python multiagent framework that automates the scientific research lifecycle, coordinating ideation, experimentation and writeup agents under a manager agent to produce publication-ready manuscripts.
swarmclawai/swarmclaw
SwarmClaw is a self-hosted TypeScript runtime and multi-agent framework for autonomous agent swarms, with durable memory, MCP tools, delegation, schedules and support for more than twenty LLM providers.
hello-diana/MASCOT
MASCOT is the EMNLP 2026 reference implementation of a multi-agent companion framework where persona-tuned speaker agents are coordinated by a director agent, both trained with GRPO in a bi-level optimisation pipeline.
RobotecAI/rai
RAI from Robotec.ai is an agent framework for embodied AI on ROS 2 robots, bundling multi-agent cores, speech input and output, perception, simulation connectors and a benchmarking suite.
christopherkarani/SwiftAgents
Swarm is a Swift 6.2 package for building agents and multi-agent workflows, with macro-generated tool schemas, DAG-compiled pipelines, on-device Foundation Models inference and optional durable checkpointing.
qntx/ovo
Ovo is an embeddable multi-agent runtime kernel for Rust, offering dynamic agent spawning alongside journaled workflows scripted in Rhai; it was previously published on crates.io as machi.
composable-models/llm_multiagent_debate
This project implements a multiagent debate framework to improve factuality and reasoning in language models, demonstrated across various tasks like math, biographies, and MMLU benchmarks.
CopilotKit/open-multi-agent-canvas
Open Multi-Agent Canvas is an open-source multi-agent chat interface that enables managing multiple agents in one dynamic conversation and supports MCP servers for advanced research and task management.
expectedparrot/edsl
EDSL is a domain-specific language for designing, conducting, and analyzing AI-powered surveys and experiments with multiple AI agents and large language models, facilitating computational social science and market research.
AlexAnys/opencrew
Multi-agent layer on top of OpenClaw that turns one assistant into a managed team of domain specialists coordinating through Slack, Feishu or Discord channels, with an agent-to-agent protocol for discussion and review.
aristoteleo/pantheon-cli
PantheonOS is a distributed multi-agent Python framework with a CLI and chatroom UI, team patterns such as swarm and mixture-of-agents, and an evolution module that improves algorithms for single-cell and spatial biology analysis.
wjayesh/mahilo
Mahilo is a flexible multi-agent framework that enables real-time, human-supervised interaction and context sharing among intelligent agents for enhanced collaboration and productivity.
ennucore/clippinator
Clippinator is an AI-driven programming assistant that autonomously plans, writes, debugs, and tests software projects using a multi-agent system based on GPT-4, enhancing developer productivity through automation and human collaboration.
jason-lang/jason
Jason is an open-source interpreter for an extended version of AgentSpeak, enabling the development of customizable multi-agent systems based on BDI agent-oriented logic programming.
samholt/L2MAC
L2MAC is a groundbreaking LLM-based multi-agent framework that functions as a general-purpose stored-program automatic computer to generate extensive, unbounded outputs for complex tasks like large codebases and books, overcoming traditional LLM context window limitations.
metauto-ai/NLSOM
NLSOM is a multi-agent AI system where diverse agents communicate in natural language to collaboratively solve tasks through a Mindstorm process, enhanced by a reward mechanism to optimize performance.
lgy0404/LearnAct
LearnAct is a framework and benchmark dataset for enhancing mobile GUI agents through few-shot learning with human demonstrations, featuring a multi-agent system to improve task completion in diverse mobile applications.