Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 57 of 62

@askills/agent-chat-cli

Multi-agent chat room CLI with a structured turn-based speaking protocol

@spacesky-cell/agent-team-orchestrator

Agent Team Orchestrator - Multi-agent collaboration system powered by LangGraph

delegate-team

Local agent orchestration CLI with task routing, backend delegation, multi-agent workflows, governed remote coding, and optional memory integrations.

portmarshal

Agent-aware port ownership and guarded orchestration for multi-agent local development

coterix

Coterix — an orchestration layer for multi-agent systems.

pi-intercom-rp

Fork: duplex agent-to-agent conversation, send_message tool, /connect protocol, background mode for multi-agent narration

@aurora-ai/multi-agent

Multi-agent orchestration for aurora

omnibus-bridge

Local-first multi-agent ideation bridge for Omnibus.

@saikarun/s-ai

Multi-agent swarm intelligence with neural mapping, digital twin persona adaptation, crawl4ai, MCP, and bias-reduced consensus. 20+ AI providers.

orchestmux

Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.

oracle-messages

File-backed message bus for multi-agent coordination — download & run wrapper

pi-ultra-messenger

Swarm-first multi-agent messaging and task orchestration extension for Pi

toolgovern-integration-oma

Adapter shapes (per-tool governedTool and dispatcher-style governedExecutor) for wiring toolgovern into an open-multi-agent-style tool-executor call site.

@pi-vault/pi-subagents

Pi extension for delegating focused work to specialized subagents - foreground, background, and multi-agent chains.

@skathio/somi

SoMi — multi-agent engineering workflow system: plan, code, review — with SOLID/OWASP guardrails, deterministic hooks, and a global ruleset.

bug-analysis

Bug Analysis Platform — AI-powered bug analysis and multi-agent workflow engine. Includes a React frontend, Express backend, and LangGraph multi-agent server.

wotann-workflow

Deterministic multi-agent orchestration for any agent harness

pi-collab

Multi-agent collaboration extension for pi — enables multiple pi instances to communicate and collaborate on shared tasks

@ruizrica/agent-pi

Multi-agent orchestration suite for Pi — 6 modes, 43 extensions, 11 themes

@miadi/agent-pi

Multi-agent orchestration suite for Pi — 6 modes, 43 extensions, 11 themes

@baochunli/pi-collaborating-agents

Collaborative multi-agent messaging and remote focus overlay extension for Pi

palabre

CLI orchestrator for multi-agent AI debates and decision-making with Codex, Claude Code, OpenCode, Vibe, and Ollama.

@onlinechefgroep/pi-agent-orchestrator

Multi-agent orchestration for Pi: autonomous subagents, worktrees, swarms, schedules, handoffs, prompt compression, and live TUI observability.

the-bureau

Multi-agent orchestration for Claude Code via Redis streams and MCP

shaagent

Scaffold production-grade multi-agent AI systems into any repository

maestro-skills

Interactive setup for the Maestro skill orchestrator (multi-agent)

@namki1222/loomo

Weave your Claude Code & Codex sessions into a team that talks to each other — multi-agent messaging over tmux, no daemon, no MCP.

@rangor/cli

Rangor CLI — friendly init, multi-agent MCP, context in terminal

@agentx-sky/multi-agent-collaboration

Multi-agent collaboration framework

@agent-nuvira/sdk

Agent-Nuvira SDK — Build custom agents for the Agent-Nuvira multi-agent orchestration system

openclaw-a2a-gateway

OpenClaw plugin implementing the A2A (Agent-to-Agent) v0.3.0 protocol — bio-inspired routing, discovery, and resilience for multi-agent ecosystems

portlock

Deterministic runtime identity for multi-agent git worktrees

@nforma.ai/nforma

nForma — Multi-agent coding orchestrator with quorum consensus and formal verification (TLA+, Alloy, PRISM). Consensus before code, proof before production.

@wotann/workflow

Deterministic multi-agent orchestration for any agent harness

@matt82198/aesop

Orchestration kernel for autonomous software development — crash-only multi-agent coordination on git and plain text, fail-closed verification gates, self-learning guardrails.

@zhushanwen/pi-subagent-workflow

Unified subagent execution and multi-agent workflow orchestration for Pi — spawned-process agent runtime with sync/background modes, stateful workflow management with persistence, state machine, and execution tracing.

@madeinvibecoding/opensquad

Multi-agent orchestration framework — create AI squads that work together

co-agent-council

A Codex-first multi-agent council that turns independent model debate into an inspectable Co-Result.

@vrsen/openswarm-cli-windows-x64-baseline

An open-source multi-agent AI team built on Agency Swarm (win32 x64 TUI binary)

@dreki-gg/pi-workflows

Secure multi-agent workflow orchestration for pi

@vrsen/openswarm-cli-darwin-x64

An open-source multi-agent AI team built on Agency Swarm (darwin x64 TUI binary)

@polymind-inc/agent-framework-a2a

Agent2Agent (A2A) protocol client for the Agent Framework: use a remote A2A agent as an agent.

agency-x

This project is a Claude-compatible, LLM-agnostic sub-agent framework that simulates a complete SaaS product team. It is delivered as a reusable, developer-ready NPM package.

@runravel/ravel

Ravel — an agentic runtime: define an agentic team as a folder of agents, tools, and processes, and run it with orchestration, budgets, scheduling, and human-in-the-loop approval.

@awesamarth/watchdog

Control subagents, agentic loops, and execution graphs from one local command center.

berserqir

Berserqir — the agent legion harness. SDD + hierarchical memory + agentic loop + behavioral evals, portable across GitHub Copilot, Claude Code and Cursor.

@mrburnz/bonefish

Orchestrator Builder — define multi-agent teams in YAML, run them autonomously

@usespan/agent-sdk

Register your AI agents with Span's intelligent task orchestrator

fde-agent-kit

FDE agent substrate — A2A contract, ports, LangGraph agent runtime shell

@icurbe/switchboard

Supervised inter-agent messaging relay for Claude Code and OpenCode (and any MCP client). Projects, environments with web consoles, focused conversations with state docs (PROGRESS.md), LangGraph review subagents, multi-provider LLM supervision, single-pan

a2a-agent

MQTT 위에서 도는 커맨더-워커 A2A 오케스트레이션 에이전트

agent-arc-status

Reference implementation of the Agent Arc Status Protocol: types, parser, validator, renderer, cadence, state, and delegation-tree tooling. Zero runtime dependencies.

agent-chat-plugin

Peer AI agents coordinate through markdown messages in shared channel folders — no orchestrator, autonomous zero-token waiting, cross-platform.

agent-comm-hub

Python SDK for Agent Communication Hub — multi-agent messaging, task scheduling, shared memory

agent-commons

Private, self-hosted coordination control plane for coding agents

agent-framework-hosting-a2a

A2A conversion helpers for app-owned Agent Framework hosting.

agent-handoff-kit

Lightweight recovery layer for multi-agent handoffs

agent-inbox

A SQLite mailbox for local LLM agents — one HTTP API, an ActivityStreams messaging model, and a local stdio MCP server so AI coding agents can message each other. No external services.

agent-party

Ephemeral, end-to-end encrypted chat rooms for autonomous agents

agentbc

Local-first task control plane for coordinating Codex, Claude Code, and Hermes.

agentchat.py

DM your teammate's coding agent — encrypted agent-to-agent Q&A over a hosted relay

agentgraph-compiler

Compile structured YAML configurations into production-grade LangGraph multi-agent architectures.

agentocc

LangGraph multi-agent shared-state optimistic concurrency control (OCC) middleware. Detects and prevents Stale-Generation anomalies at commit time.

agents-network

A flexible multi-agent orchestration framework with configurable agent and tool registries

agentworld

Deterministic spatial multi-agent environment with an LLM-agent framework, verifiable rewards, and a connect-out benchmark platform

akgentic-agent

Collaborative agent patterns for the Akgentic framework

ballast-agents

Resilience and cost-control plane for multi-agent AI systems: circuit breakers, backpressure, cost-aware fallbacks, and chaos testing

bastet-agent-os

Local-first operating system for AI-agent teams: resource governance, gated workflows, and multi-project orchestration on top of Agent Memory OS.

claudeway

Verifiable multi-agent consensus for Claude. A coordination layer built around signed agreement.

conclave-llm

Multi-LLM deliberation protocol engine — like a conclave of AI cardinals

friday-framework-agent

Agent orchestration layer for Friday Framework

han-agents

Finalist agents from the Human Agent Negotiation (HAN) league of ANAC

ifuri-todo-agent

Central task registry and deterministic three-agent orchestrator for doctor-agent, repair-agent and validator-agent.

kidecon-agent

Kidecon Agent CLI — client sidecar for the Kidecon Agent Network

league-of-agents-platform

Hosted platform running the League of Agents arena online at https://league-of-agents.ai — a turn-based game for humans and agents, for fun and for benchmarks. Continuable matches, AWS-hosted, with safe-capacity safeguards and price-aware archive/cleanup. The league-site CLI is the local operator surface and how agents work with it.

mac-agent

A lightweight multi-agent coordination ledger for task handoff, context handoff, and quality gates.

matterloop-agents

Model agents and DAG-based multi-agent collaboration components for MatterLoop

memora-swarm

Bit-exact Byzantine-fault-tolerant state layer for federated learning and edge/defence swarms. Three layers — OR-Set CRDT (L1), an epistemic drift + human-in-the-loop layer (L2), and ACFA Q16.16 multi-Krum + G-Set (L3) — keep heterogeneous nodes byte-identical; one prompt-injected or equivocating node can't fork, poison, or move the agreed state. Every write is signed, attributable, and exactly replayable. Architected for large swarms; bit-exact by construction.

multi-agent-platform

Multi-Agent experiment collaboration platform

multi-agent-platform-server

Meta-package: Multi-Agent Platform CLI + server dependencies

okf-agentbus

SQLite-backed MCP event bus and control surface for heterogeneous agent orchestration.

open-agent-relay

Let teammates call your local agent or automation directly over the LAN.

optio-agents-all

Meta-factory over all wrapped optio agent engines: create_task dispatched by a tagged TaskConfig union.

protolabs-agent

protoAgent — LangGraph + A2A template for spawning protoLabs agents

s7g4-agentops

Multi-agent orchestration backend — FSM pipeline, workflow engine, and agent bus on one substrate

superagentic

Work leases in one SQLite file, so a fleet of agents divides a job list instead of racing it. Library, CLI and MCP server, zero dependencies.

swarm-cc

Graph-first multi-agent orchestrator for Claude Code - parallel task graphs, hook-written checkpoints, ask-first resume, right-sized model tiers

swarm-rd-orchestrator-cli

Ray-native context/memory sharing for parallel research agents, with an agent-native CLI and MCP server (Milestone 1 spike)

swarm-tminus

Time-shaped coordination primitives for swarm-anchor: predict-and-confirm, deadlines, rate limiters, BPM clocks, cron, and DAG-ordered campaigns. Stdlib-only Python.

swarmgraph-sdk

SwarmGraph SDK: deterministic multi-agent orchestration primitives

swarmkit-webui

SwarmKit web portal — the static Next.js build, served by `swarmkit serve`.

swarmmesh-cli

Shared-context and memory coordination server + CLI for swarms of parallel AI agents, speaking the SwarmMesh v1 protocol (HTTP + WebSocket + MCP), interoperable with the Node implementation.

swarmplane

A living task graph for agent orchestration on Google Cloud. Reference implementation.

taar-agent-taskforce

TAAR — Thirsty's Active Agent Runner: a local-first governed agent taskforce for Project-AI, with a GitHub Workflow Guardian.

tau-subagents

Subagents extension for Tau (a port of pi-subagents).

techtide-swarm

TechTide Swarm 357 — layered orchestration, durable memory bridge, and observability hooks.

wasmagent-protocol

Canonical JSON Schemas for the WasmAgent Agent Evidence Protocol (AEP) and compliance contracts. Single source of truth across the WasmAgent org.

@hunpeolabs/ai-agent-kit

Governed AI agent orchestration with repository intelligence, approval gates, specialist workcells, and reviewable evidence.

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

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

staffed

Compose and run coordinated subagent staff packs with progressive discovery, portable Markdown personas, and no runtime or dependencies.

More in Agent frameworks & infrastructure