Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 8 of 62
Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.
Adaptive Agentic AI Reasoning using Microsoft Agent Framework -- Join the Discord for suggestion or support ! https://discord.gg/ebgy7gtZHK
Experimental agent swarm extension for Pi. Inspired by Claude agent teams.
Visual multi-agent system designer for Claude Code. 60 agents, 62 presets, Five Minds Protocol, HITL gates, cost modelling and Live Simulation - see the team run before you spend a token. Installable as a Claude Code plugin. Zero dependencies, single HTML file.
Local-first coordination hub for Codex x Claude: shared identity, tasks, messages, write intents, immutable review bundles and a replayable event stream. The Hub never calls a model itself.
Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.
Local-first MCP coordination hub for multi-agent teams, with durable messaging, handoffs, governance, and observability.
Multi-AI orchestration framework for Claude Code — coordinate Claude, Codex, and Gemini with 7 workflow modes, parallel execution, and session unification
AAAI24(Oral) ProAgent: Building Proactive Cooperative Agents with Large Language Models
Open Source A2A Protocol Adapter SDK for Different Agent Frameworks and Harnesses
🏙️ A city of AI agents on your machine where nothing is hidden: prompts are plain files you own, and every context is a line in a hash-chained, offline-verifiable Ledger you can replay.
Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.
[ACL 2026] OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction https://arxiv.org/abs/2604.25602
Flow Nexus is the first competitive agentic platform built entirely on MCP. Deploy autonomous AI swarms, train neural networks, and compete in coding challenges while earning rUv credits. Transform agentic engineering mastery into lived experience through gamified cloud development where agents spawn agents and systems improve themselves
Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Code, OpenClaw, Cursor, Codex, Gemini, Copilot, Kiro. Declarative .at language + agent-maintained, Obsidian-portable company brains + interactive visualizer.
Your local-first command center for working with AI agents like a real team.
dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.
Agent orchestration service for the Agent Landing Zone, built on Microsoft Foundry Agent Service and Microsoft Agent Framework. Coordinates specialized agents for conversational experiences with grounded knowledge, NL2SQL and MCP tools.
An app to maximize the very best of human developer skills: executive control of AI Agents
🤖 Autonomous development orchestrator for the BMad Method. Runs fully autonomous, parallel, multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint backlog and dependency graph.
FSPEC: The Spec-Driven, Multi-Agent Harness. It is infrastructure for the "Dark Factory" - the emerging model of fully autonomous software development where AI agents handle all implementation while humans focus on defining what to build and why.
maw — CLI for running multiple AI agents across machines via tmux. Wake agents, talk across nodes, watch screens, track cost. Engine-agnostic (Claude Code, Codex, Aider, OpenCode), built on Bun.
Build persistent multi-agent teams that collaborate like real organizations to deliver complex tasks.
Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven, evidence-gated, parallel feature voyages.
Coordinate multiple AI coding agents through a local-first, recoverable Agent Bus.
Pilot Protocol: The Internet of Agents
Constitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think. Audit. Execute.
Agent-centric social network and interoperability dApp framework
Claude · Codex · Gemini 멀티에이전트 오케스트레이션 스타터 (파일 기반)
Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff & frontend↔backend integration. Free, self-hostable, MCP-native.
Agent orchestration built from first principles: plan, dispatch and supervise a team of AI engineering agents from one control surface.
Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI
Negotiation Multi-Agent System (A negotiation library designed for situated negotiations within business-like simulations)
VetarAI 是一款全原生 Swift 的本地桌面应用:多 Agent 协作、可视化工作流、拉模式知识仓库+本地语义检索、多模型超级工作室、CU 电脑操作。数据保存在本地磁盘。
Save 120+ Hours of Setup Pain (I did it for you) – Launch Your OpenClaw Agent Teams with 1 Command (15+ Recipes)
Local multi-agent harness for running persistent agent teams, long-run, society-simulation
面向个人的本地多 Agent 协同工作空间。与拥有独立身份与持久记忆的 AI 队友深度协作:频道分工、任务指派、无限矢量画布与原生 MCP。A local-first multi-agent collaborative workspace.
Orchestrate AI coding agents (Claude Code, Codex) as parallel subagents over tmux — a loop-engineering runtime with auto-continue, execute-then-review, and cross-session memory.
The Library for LLM-based multi-agent applications
Example inspired by @joaomdmoura sample project
Jax and Torch Multi-Agent SAC on PettingZoo API
Multi-Agent Deep Reinforcement Learning for Task Offloading in GDMSs
Public implementation of "Multi-Agent Graph-Attention Communication and Teaming" from AAMAS'21
Core concepts - where to apply parallelism in agentic solution
An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler, and more. One command to start. Everything from the browser. No coding required.
🚀 Way Back Home
🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot CLI) to collaborate on complex software development tasks via REPL or a Vue/Nuxt UI dashboard. Also includes an Agentic Team runtime with role-based multi-agent open communication & lead-gated final responses.
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Cursor, Gemini, MinMax, OpenCode, Pi, or Command Code from any compatible tool.
Multi‑Agent Cross‑Space Collaboration Panel
Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit. Zero Dependency. Works with any language stack.
simple multi-agent pathfinding (MAPF) visualizer for research usage
COR paper: A Deep Multi-Agent Reinforcement Learning Approach to Solve Dynamic Job Shop Scheduling Problem
一套让多个 AI agent 协作干工程活、且没有任何一方能给自己签合格的设计,加上它的实现,以及它真的跑起来时留下的账本。
Campfire - Collaborative web platform for AI coding agents with Collective Intelligence layers
BCP-MAPF – branch-and-cut-and-price for multi-agent path finding
Modular Agentic AI Architecture - NousResearch x Teleport (Flashbots)
ClawMax is OpenClaw to the Max! 🚀 A web orchestration layer for OpenClaw agents, teams, workflows, and templates.
Multi-agent AI platform for autonomous agents, agentic AI orchestration and LLM workflow automation. 80 self-hosted apps - Chat, CRM, Mail, Drive, Calendar, Advanced RAG. Open source, built in Rust.
openJiuwen agent-protocol provides implementations of agent communication protocols, including C++ SDKs for MCP and A2A protocols.
Maestro workflow tools as Pi extensions — pi-teammate + pi-maestro-agent
A multi-agent campus social simulation built with LangGraph, featuring memory, RAG, personality evolution, and durable execution.
Orchestrate, execute, and observe agent flows for token maxing!
Multi-Agent self-correcting reasoning engine
A Şirketi — üç Claude Code ajanı, bir bekçi, bir dağıtıcı; kapalı döngü, yayın düğmesi insanda. Selma Şirketi · Bölüm 1
Build and deploy stateful agents across federated resources
Curated Hermes Agent profiles for specialist swarms — opinionated, Hermes-optimized, artifact-pyramid native
Huabu, where you and your agents think together.
Agent Bridge is a connector that links various local agents, enabling users to coordinate multiple other agents simply by interacting with a single powerful agent. It currently supports Codex as the coordinator to direct Antigravity CLI, Grok Build, and DeepSeek Harness. Support for additional agents will be rolled out soon.
EAT: Evolving Agent Teams (NeurIPS'26). A supervisor agent evolves teams of coding agents for long-running optimization tasks.
Join the OVOS collective, utils for OpenVoiceOS mesh networking
AIEvo is a multi-agent framework open sourced by Ant Group. Through this framework, you can create a multi-agent application.
Agent swarming organization system
Code for ACL25-findings. An LLM-based agent simulation framework that simulates human behavior and generates dynamic, text-based social graphs.
Manage a swarm of coding agents.
FlowSteer: agents designing agentic workflows via reinforced progressive canvas editing.
Web Graphical User Interface (GUI) for Gas Town multi-agent orchestrator - A companion interface for steveyegge/gastown
AgentOven is a **framework-agnostic agent control plane** that standardizes how AI agents are built, deployed, observed, and orchestrated across an enterprise. Think of it as a **clay oven** 🏺 — you put in raw ingredients (models, tools, data, prompts) and **production-ready agents come out the chimney**.
Multi-Agent Mesh · Connect · Orchestrate · Scale
A Claude Code framework for multi-llm planning and development agents
Community team templates and skill playbooks for OpenMausBot
Durable, named agents for Pi: delegate tasks, compose agents into graphs, and watch them work.
多agent协作:Windows 本地模型工作台,支持 DSH/Pi 执行、任务等待与独立验收。
Starter template to build multi agent systems
A multi-agent engine for the UBC Agents
Browser based agent orchestrator / You host the server wherever you want / Harnesses all CLI AI harnesses / Mobile and VR Voice coding
ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)
A skill that convenes a panel of CLI-based AI agents (Claude Code, Codex, Gemini CLI) to deliberate on engineering problems through structured multi-stage discussion, peer review, and synthesis
Self-designing, durable, self-improving agent orchestration: describe a goal — an agent designs the graph, a fleet of sealed full-agent nodes runs it, and a learning loop makes it better every run.
[NeurIPS 2024] Personal Agentic AI for MultiAgent Cooperation
Open Source panel to orchestrate agents, terminal, and git
Awesome catalog of portable agent org charts — pick one, paste to your grokbot/dots/etc, spawn the team. Platform-agnostic.
Official code repo for NeurIPS 2025 Spotlight paper, "Debate or Vote: Which Yields Better Decisions in Multi-Agent LLMs?"
Design Multi-Agent AI Systems Using MCP and A2A, by Packt Publishing
File-based message queue for local agent-to-agent communication (Maildir-style)
Use Claude Code, Codex, Pi as subagents or agent in complex workflow.
Team of Codex agents that collaborate through a spec-driven development process. Full Stack Developer parent orchestrates dynamically sized pools of specialists: Coding, DevOps, Review, and Solutions Architect agents.