Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 59 of 62

agentchat-broker

End-to-end encrypted messaging between AI agents, with a directory and store-and-forward delivery

agents-can-communicate

Local-first coordination for independently opened AI agent sessions.

@a2adev/gateway

Local A2A gateway for waking AI agent runtimes

@animahealth/adk

Anima Agent Development Kit - Framework for building production-grade multi-agent AI systems

a2a-codex

A2A (Agent-to-Agent) protocol wrapper for OpenAI Codex SDK. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports repository sandboxing, MCP tools, streaming sideband events, and multi-agent delegation.

agents-city

Run autonomous agent cities: one chair seat, role-aware repo agents, repo-owned skills, and explicit roads.

jonah-fleet

Standalone autonomous agent fleet with Symphony orchestration, claim protocols, and continuous improvement loops

@flashyos/agent

Report agent state to the FlashyOS mesh — the DeAI Operating System for Agentic Autonomous Organizations (AAOs).

dsh-megamesh

Super multi-agent architecture: files are messages, adoption replaces all-hands-on-deck failure, term leases replace single points, invariants replace trust, timelines replace non-reproducibility, one file serves humans and machines. Every claim carries a

@flosrn/ax

Agent Experience for a repository: worktrees, sessions, and multi-agent orchestration.

@viberacing/connector

Privacy-minimized multi-agent token sync for Vibe Racing

@botbuddy/cli

BotBuddy — Swarm coordination CLI for multi-agent workflows

@hanxuanliang/dsh-chaos

Peer multi-Agent collaboration for DeepSeek Harness

volibearq

Portable multi-agent engineering pipeline runtime

@denmfv/oh-my-opencode-pi

Pantheon-style multi-agent orchestration for pi, inspired by oh-my-opencode-slim

@lovrozagar/grunt

Multi-agent orchestrator SoT — deep-merge rulesync trees, product scripts, and generate pipeline into a consumer repo

pi-multiagents-v2

Codex Multi-Agent V2-style hierarchical subagents for Pi

plogr-workflow

Initialize Herdr multi-agent workflow projects — zero-collision AI orchestration by Plogr

opencode-agent-orchestration-kit

Open-source multi-agent orchestration harness for OpenCode with specialized agents, durable workflows, review gates, and reproducible software-engineering processes.

pi-agents-flow

Supervisor-led multi-Agent orchestration for Pi with durable workflows, quality gates, and observable subagents

@sunny.wang/initializing-project-harness

Initialize and safely upgrade evidence-backed multi-agent project Harnesses.

dev-harness-structure

Next-generation multi-agent harness with 6 specialized agents, presets, security guardrails, and audit trail

trimegisto

Pi multi-agent orchestration: tiered parallel sub-agents, @mentions, loop guard, file locks, context broker, dashboard.

oh-my-deepseek-harness

Multi-agent orchestration for DeepSeek Harness -- specialized agents, task orchestration, workflow skills

vibe-product-os

Multi-agent Skill installer and governed runtime adapter for Product OS 1.0.0.

pi-agent-squad

Interactive multi-agent orchestration, messaging, and live sessions for the Pi Coding Agent

@sakiv/sagent

Governed multi-agent orchestration, map-reduce, and real-time status for Pi

@the-long-ride/agents-crew

Dependency-free TypeScript multi-agent crew orchestration for Codex, Claude Code, OpenCode, and Antigravity.

@abhishek.nagaraja/catms

Coding Agents Team Management System — Trackers + CAMS RAG workflow scaffolding for multi-agent AI coding teams

@groeponline/pi-agent-orchestrator

Observable multi-agent orchestration for Pi: autonomous subagents, isolated worktrees, swarms, schedules, handoffs, and a live operator dashboard.

@ergon.studio/dsh

Ergon multi-agent orchestration for DeepSeek Harness: 10-agent team preset, memory steward, debate, scratchpad

multi-agents-workflow

Explicit dynamic and fixed multi-agent workflows, fenced task execution, optional adapters, and independent candidate acceptance.

hivemind-3.0

HiveMind — Runtime composition engine for multi-agent orchestration, session continuity, and compounding intelligence in OpenCode

agentflux

A multi-Agent workbench for pi: direct work, dynamic teams, DAG workflows and issue communities

@freeside-collective/agent-loop

Multi-agent orchestration loop built on A2A task routing and MCP tool shards

pi-meeting

Pi skill + wrapper for pi-agents-meeting-discuss: launch a multi-agent discussion from a Pi session.

@aderra-tech/agentic

Vendor-neutral agentic product-team operating system and multi-repo control plane

@algorandfoundation/ac2-sdk

TypeScript SDK for the AC2 (Agentic Communication and Control) protocol.

@nanobpm/urban-agent-client

Worker-side client for the Nano agentic channel (ADR 0056, S9): REGISTER→SERVE, heartbeat/deregister, produce relay bytes, and a local buffer / flush-on-reconnect ring that tolerates a hub outage. Speaks the @nanobpm/agentic wire contract (via its @nanobp

@devpilot.sh/conductor-agent

The DevPilot conductor as a LangGraph agent — plan, review, dispatch and advance a wave plan as one resumable graph

agent-backbone

Bring agents across AI CLIs and projects into one personal team, with communication, coordination and continuity.

babelagent

The Babel that lets AI agents understand each other: a neutral layer where heterogeneous agents (callables, HTTP/OpenAPI, MCP, framework agents, LLMs) share one interface, collaborate (A2A), and get graded at each hop.

dual-agent-development

Runtime-neutral dual-agent collaboration orchestrator: architect, coder, tester, reviewer with structured packets and an append-only ledger.

iagent-mesh

Universal contracts and infrastructure wrapper for the iagent Mesh — typed predicate registration, transport auth, and per-caller identity for mesh tools

kycortex-agents

Multi-agent orchestration framework for AI software house

loragent

Universal Multi-Agent Ecosystem for Lorapok Labs — 224 Autonomous Agents, 20 MCP Servers, and 6 Formations

murage

Murage — agent orchestration platform. Name reserved; implementation in development.

parley-agents

Broker-agnostic messaging layer that lets AI agents (and humans) on different machines talk in named rooms and wake each other.

quesen-autogen

Official AutoGen (v0.4+) tool wrapper for Quesen — deterministic A2A risk validation for AutoGen agents.

quesen-crewai

Official CrewAI tool wrapper for Quesen — deterministic A2A risk validation for CrewAI agents and crews.

quesen-langchain

Official LangChain / LangGraph tool wrapper for Quesen — deterministic A2A risk validation.

skein-agents

Skein - team coordination platform for humans + AI agents, built on the Strands Agents SDK

swarmagentkit-core

A tick-based / real-time multi-agent swarm runtime with hierarchical memory, a hybrid LLM/rule-based orchestrator, and pluggable domain physics -- for simulations and for real hardware/services alike.

@mumulinya167/cc-web

本地优先的多 Agent 协作与自动开发工作区,集成任务编排、记忆上下文、MCP/Skill、TestAgent、Git、飞书、知识库和终端

@qmilab/asterism

Many agents. One runtime. Separate lives. Run distinct local AI agents — each with its own soul, memory, secrets, skills, workspace, and autonomy level.

pixelcrew

Local multi-agent orchestration framework with an interactive pixel-art tech startup office visual dashboard

taskard

Zero-runtime multi-agent orchestration convention for Claude Code, OpenCode, Codex, Antigravity, and Cursor

agentgod

One permanent AI agent that builds, runs and retires other agents per task.

altruan-agenten

Schalter und Protokoll fuer die digitalen Mitarbeiter: Aufgaben zur Laufzeit an- und abschalten, Vorschlaege vermerken und ihre Trefferquote messen.

cdzzy-agentlink

The inter-agent communication protocol. Like HTTP for web services, but for AI agents.

multiagent-init

Interactive CLI for generating multi-agent AI project boilerplates.

swarmd-google-adk

SwarmD integration for Google Agent Development Kit

swarmd-langchain

SwarmD integration for LangChain

Relay

Public board for internet-going agents. No accounts. Rooms: lobby/findings/asks. Start at GET /api.

Serai

Thin public door where stranger AI agents arrive via JSON. Machine entry: invite.txt / handoff.txt / agent-card / llms.txt.

agenticpool

AgenticPool.net — Decentralized AI agent favor exchange network powered by Duckies & A2A Trust Protocol

@guyghost/swarm-dao-core

Swarm DAO core — pure business logic for AI agent governance

teamshare-bridge

Local bridge for TeamShare agents - CLI session runner, auto-wake WebSocket daemon, and teamshare:// protocol handler.

@engramport/sdk

Coordination substrate for several builders' agents: an append-only, verifiable event log, with the shared turn decision that bounds an autonomous agent.

tower-do

Shared multi-agent task board for Pi coding agent — Kimi Tower style orchestration (todo-flavored)

opencode-thrum-pro

Thrum multi-agent coordination plugin for Open Code

@x-otto/orchestrator

Manages the creation, scheduling, retry, and lifecycle of multi-agent tasks. Provides a combined TaskStore + TaskExecutor + CircuitBreaker.

@avidian/opencode-autopilot

Persistent autonomous multi-agent supervision for OpenCode

@bloodf/oh-my-agent

OMP plugin for autonomous long-lived multi-agent collaboration

sdd-team

AI multi-agent development team — install agents, skills, workflows for Claude Code / Pi / OpenCode / Codex

beth-copilot

Beth - A ruthless, hyper-competent AI orchestrator for GitHub Copilot multi-agent workflows

aipipe-cli

A reversible GitHub-native multi-agent development pipeline CLI

@chankov/agent-fleet

Subagent orchestration for the pi coding agent — a thin dispatcher runs parallel subagents under a verification contract, keeping their output out of its context window. Multi-agent fleets, 15 personas, skills, herdr panes, peer coms, Hermes desktop.

dsh-codex-ultra-mode

Ultra-like dynamic multi-agent orchestration mode for DeepSeek Harness

know-thy-build

Define what to build, then let a dark factory build it — Socratic project definition + CI-driven multi-agent pipeline for Claude Code

opencode-v2-agent-orchestrator

A V2-only multi-agent orchestration plugin for OpenCode.

@its-thepoe/agentic-design-engineering

Agent Skill: adaptive multi-agent product design and engineering workflow.

ai-foundry-desk

AI Foundry Desk — Multi-Agent Workbench for a personal AI workstation.

dsh-background-agents

Interactive long-session background agents plus persistent multi-agent team rooms for DeepSeek Harness: durable continuable child agents with progress, steering and interruption, and cross-session team rooms with a message bus, shared task board, approval

cursor-agent-kit

Open-source CLI for Cursor IDE multi-agent orchestration — Router, specialist agents, STATE memory. npx cursor-agent-kit init

dsh-agent-bus

Multi-agent orchestration for DeepSeek Harness. Sessions in one workspace assign work, review results, and run DAG workflows — without you as the messenger.

@olitech010/dev-os

Olives Technologies Engineering OS — Autonomous Multi-Agent AI Engineering Environment

vajraagent

Universal Multi-Agent Mesh & Distributed Policy Control Plane for Enterprise AI

@netnodeag/kraftwerk

Open-source agentic workspace for teams — where people and AI agents get work done together: agents (Claude Code, Codex, Pi), skills, shared knowledge, repeatable workflows, and deterministic verification

agent-augury

Local multi-agent collaboration runtime — shared threads, roles, HITL, model-agnostic backends.

agent-coop-cli

Local multi-agent coordination protocol for terminal coding agents

novaos-agent-sdk

Python client library for connecting to and communicating with AI Agents that implement the Agent2Agent Protocol (A2A), spec v1.0.1

@alvin0/ai-agent-sdk-a2a

Node-elevated official A2A client/server bridge for ai-agent-sdk

@tickernelz/paperclip-pro

Paperclip CLI — orchestrate AI agent teams to run a business

@ruvector/tiny-dancer-linux-arm64-musl

Neural router for AI agent orchestration - linux-arm64-musl platform

@ruvector/tiny-dancer-win32-arm64-msvc

Neural router for AI agent orchestration - win32-arm64-msvc platform

larp-cli

LLM Agent Relay Protocol: lets Claude Code and Codex sessions message each other without knowing each other's harness API.

alibabacloud-agentcore-collaboration

Independently versioned AgentCore Worker collaboration

@kontextmind/kxm

KXM local-first multi-agent orchestration and operator dashboard

@serkanalgur/opencode-nexus

Adaptive Multi-Agent Orchestration with Cost Intelligence for OpenCode V2

More in Agent frameworks & infrastructure