Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 53 of 62

@wkoutre/teamwork-os

AI agent orchestration platform.

cc-codeconductor

A multi-agent orchestration framework for AI-assisted software engineering workflows.

@myersguo/iteam

iTeam client — CLI + agent daemon for the local-first multi-agent collaboration workspace

pillow-council

CLI for running PillowCouncil's multi-agent decision board locally.

agentic-yp

Official Node.js SDK for the Agentic Yellow Pages A2A routing network.

agentic-exchange-sdk

JavaScript SDK for Agentic Exchange agent discovery, reputation insights, and workflow orchestration.

@claude-flow/integration

Integration module - agentic-flow@alpha deep integration, ADR-001 compliance, TokenOptimizer

agentic-exchange-frontend

Frontend app for Agentic Exchange

openai-swarmjs

Agentic framework inspired from OpenAI's swarm framework for TS, JS

opencode-swarm

Architect-centric agentic swarm plugin for OpenCode - hub-and-spoke orchestration with SME consultation, code generation, and QA review

@agentic-profile/a2a

A2A (Agent-to-Agent) SDK for quickly developing multi-tenant agentic services. Supports globally unique user and business scoped agent ids, and universal authentication using the Agentic Profile

@agentic-profile/a2a-service

A2A (Agent-to-Agent) Express middleware for AI Agents using A2A and the Agentic Profile protocols

@jetpack-agent/supervisor

LangGraph Supervisor Agent for intelligent multi-agent orchestration

@nampham1106/deepagents

General purpose 'deep agent' with sub-agent spawning, todo list capabilities, and mock file system. Built on LangGraph.

@openfinclaw/findoo-plugin

Strategy Agent bridge — A2A protocol integration for LangGraph strategy-agent (37 financial analysis skills)

agentsmcp

Context-sync protocol for AI agents. Every agent has a mailbox.

@sonic-agent-kit/agent-setup-lib

A flexible framework for orchestrating multiple specialized AI agents to collaborate on tasks. This system leverages LangChain and LangGraph to create a directed graph of agent interactions, with a supervisor agent coordinating the workflow.

@assistant-ui/react-a2a

A2A (Agent-to-Agent) v1.0 protocol adapter for assistant-ui

@pmcollab/coworkstream-engine

Headless decision-routing engine for @pmcollab/coworkstream. Dispatches items to a plurality of agents, computes alignment status, escalates to human on conflict, and learns per-agent trust weights.

@ag-ui/a2ui-toolkit

Framework-agnostic helpers for building A2UI subagent tools — op builders, prompt assembly, history walkers, and request/envelope orchestration shared across framework adapters.

@prmaat/bridge

Universal PrMaat bridge — runs your LLM brain locally, posts to PrMaat rooms remotely. Operator-attested, audit-chained, cross-vendor agent identity. See CHANGELOG.md for per-version notes.

create-hivemind

One prompt. A full AI engineering team. Go lie on the couch.

agent-collab

A general-purpose coordination protocol and CLI for multiple AI coding agents working on one repository.

drake-agent-mesh

Name reservation — see https://github.com/Gilamonster-Foundation/agent-mesh

magic-agents

占位包:Magic-agents Agent管理平台)

newt-agent-mesh

Cryptographic peer-to-peer agent coordination (Python bindings for agent-mesh)

optio-agents

Agent-coordination layer for optio task types: the optio.log keyword protocol, its session driver, and the LLM-facing keyword documentation (SSOT).

ouragentteams

Multi-agent orchestration with a local LLM Leader directing cloud/local Workers.

@llm-helpers/agents

Multi-agent composition — run agents as tools inside other agents

@synapse-orchestration/cli

The synapse CLI — multi-agent orchestration for software projects

swarmly

A small open-source CLI for orchestrating multi-agent Claude Code swarms. Filesystem-coordinated, no GUI, no MCP, no subscription.

agi-farm

Multi-agent AI team builder for OpenClaw — bootstrap complete teams with Paperclip dashboard, auto-dispatcher, and infrastructure

@os-eco/overstory-cli

Multi-agent orchestration for AI coding agents — spawn workers in git worktrees via tmux, coordinate through SQLite mail, merge with tiered conflict resolution. Pluggable runtime adapters for Claude Code, Pi, and more.

@amtp/protocol

AMTP: Agent Markdown Transfer Protocol - HTTP for the Agentic Web

agent-protocols

Python SDK for Agent Identity, Agent Profile, Agent Delegation, Agent Discourse, Agent Knowledge, and Agent Mail protocols

swarmpilot

Placeholder for the SwarmPilot distributed task scheduling system.

SwarmZero

Marketplace for AI agents to automate tasks and monetize expertise.

gojaja

gojaja (过家家) — file-system coordination layer for multi-LLM-agent collaboration (Codex, Claude Code, Cursor, ...). Let your agents play house on a shared codebase.

crewai-arcgate

Arc Gate runtime governance for CrewAI agents

@untitled-devs/wasla

Universal synchronization layer for AI agent orchestrators

hungry-ghost-hive

AI Agent Orchestrator - Manages agile software development teams of AI agents

squad-station-2

Message routing and orchestration for AI agent squads

agentbnb

P2P Agent Capability Sharing Protocol — Airbnb for AI agent pipelines

@ai-sdk/swarm

> **Warning** > This is an experimental package. It is not maintained and the API is not stable.

agent-step-gate

External cryptographic step ledger for long-running multi-agent orchestration

maosorch

Multi-Agent Orchestrator System — docker-compose for AI coding agents

crew-mcp

MCP server + portable captain skill that turns any AI coding CLI into the orchestrator of a worktree-isolated multi-agent crew

wanderai

Wander AI Auto Dev Config: A dual-mode interactive CLI and compliant Model Context Protocol (MCP) server for multi-agent development teams.

crewgate

Multi-agent pipeline orchestrator for OpenCode — 7-gate autonomous execution

@novoaiorg/openai-agents-openai

The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.

@umyunsang/kosax

Conversational multi-agent harness for Korean public-service channels

pi-mesh

Multi-agent coordination for Pi - presence, messaging, file reservations

glove-mesh

Inter-agent mesh networking for the Glove agent framework — peer messaging on top of the inbox primitive, bring-your-own transport.

puzldai

Multi-LLM orchestration framework with agentic execution, memory/RAG, and training data generation

agentstate-lib

Stateful coordination layer for multi-agent AI systems

trinity-agent

Three minds, one context — Multi-agent AI orchestrator for Claude Code, Codex, and Antigravity CLI.

MetaGPT

MetaGPT uses AI teams to build software from your ideas.

biroai

Biro CLI — orchestrate AI agent teams to run a business

dealdesk

DealDesk CLI — orchestrate AI agent teams to run a business

@wundr.io/agent-delegation

Hub-and-spoke delegation pattern for AI agent coordination with audit logging and result synthesis

@agent-link/server

AgentLink relay server

strray-ai

Multi-agent orchestration and Codex governance for OpenCode, Hermes, Grok Build, and OpenClaw

cordn8

Agent-neutral coordination for AI agents, coding CLIs, LLM APIs, IDE assistants, and custom tools through a local auditable channel — with a built-in local web dashboard (Cordn8 Mantle).

maestro-agent

The Conductor for AI Agents — Multi-Agent Execution System with Task, Roles & Orchestration

@teamrc/cli

teamrc CLI - sync multi-agent teams across platforms

@openclawcity/become

Agents get smarter together. Open-source framework for multi-agent evolutionary learning.

@bundy-lmw/hive-core

Hive - Multi-Agent Collaboration Framework. Like bees collaborating efficiently, an AI Agent SDK.

@hotwired-sh/playbooks

Playbook definitions for Hotwired multi-agent workflows

quorum-deliberation

Name reservation for the forthcoming Quorum multi-agent deliberation engine. Not yet functional.

omcursor-workflow

Multi-agent orchestration layer for Cursor CLI

@instavm/murmur

Local multi-agent room — coding agents (claude, codex, gemini, cursor, copilot) coordinate live via a shared MCP HTTP daemon.

aegis-agents

Local-first, MCP-native multi-agent platform — job tracker + daily briefing for software engineers, with tracing, evals, and budgets.

agent-relay

Real-time agent-to-agent communication system

@moon-wave/multi-agent

Multi-agent patterns for moon-wave: AgentNetwork, AgentHandoff

spectralswarm

PRIDES methodology multi-agent AI team — 21 specialized agents for the full development lifecycle

arbiter-pipeline

Deterministic multi-agent AI pipeline for structured feature delivery with ALC evidence generation

@zana-ai/core

Zana engine — multi-agent orchestration, scheduling, persistence, and module system. Used by @zana-ai/mcp.

@inkobytes/nexus

Multi-agent coordination CLI for coding agents sharing a local repository

@douglas-agent/sandbank-relay

WebSocket relay server for multi-agent communication in Sandbank

@loomfsm/kernel

Generic finite-state-machine kernel for multi-agent LLM workflows — atomic state, replay-deterministic, zero runtime dependencies.

@agentplate/cli

Self-improving multi-agent orchestration that takes you from build → CI/CD → deploy. Interactive setup wizard, pluggable AI providers, agent swarms in git worktrees.

@iconicompany/multi-agent-orchestrator-local

Multi-Agent Orchestrator framework

relaycast

Headless Slack for AI agents. Channels, threads, DMs, reactions, and real-time events for multi-agent communication.

advanced-multi-agent-chatbot

A simulated advanced multi-agent chatbot UI

family-ai-agent

Multi-agent AI system with memory and autonomous capabilities

@weave_protocol/witan

Council Protocol - Multi-agent consensus, communication, and governance for AI systems

@prysm-ai/multiagent

Multi-agent collaboration system

win-agent

Multi-agent workflow engine powered by opencode SDK

olpai-volunteer-agent

Volunteer judge worker agent for OLPAI

pyagent-compress

Inter-agent message compression and token budget management for multi-agent LLM systems

pyagent-patterns

18 reusable multi-agent orchestration patterns for LLMs

conductor-oss

Markdown-native AI agent orchestrator. Write tasks in a kanban board, agents do the work.

pi-subagents-lite

Lightweight sub-agents for pi — spawn specialized agents with isolated sessions, tools, and models.

@ofear/xdou

A terminal-native multi-agent development system where selected coding and architecture agents co-develop through council, synthesis, implementation, review, and validation loops.

@crewai-ts/core

Unofficial TypeScript port of CrewAI (not affiliated with crewAI, Inc.).

aacp-crewai

AACP coordination layer for CrewAI multi-agent workflows

aacp-langchain

AACP coordination layer for LangChain multi-agent workflows

nexus-enterprise-agent

Enterprise-ready, SaaS-native Python multi-agent framework

glim-agent

[Future Scope - Do not use until v1.0.0] Autonomous AI agent framework and multi-agent system for GlimLang

predator-jungle-agent

PREDATOR – Praxic Reinforcement and Extinction-Driven Agentic Task Orchestrator and Realizer. A Deep Agentic AI system built on the Artificial Junky Neuron (AJN) framework by Justo Tapiador García (UA). Enhanced v2.0 with real transformers, persistent mem

More in Agent frameworks & infrastructure