Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 60 of 62

@hmj-ai/cflow

Local workbench for assembling, inspecting, and running multi-agent workflow graphs

@mappyj/dsh-plugin-workflow

Multi-Agent Workflow plugin for DeepSeek Harness (dsh)

rulith

Rulith: a local multi-agent workbench with conversations and governed Worker tools

@youngjurry/pi-agents

Persistent in-process Codex-style multi-agent collaboration for Pi

nexus-devflow

Enterprise-grade spec-driven development framework for multi-agent workflows

@staix/agent-hub

Native multi-agent hub: Claude Code, Codex, Kimi Code, Pi and local inference as peers in one project

@a-t-h-i/bot-lobby

Structured multi-agent software engineering orchestrator for Pi

@arya-ai/arya

Autonomous multi-agent runtime powered by mu

@scipix/app

SCIPIX — a visual AI workflow engine: a node-based canvas for orchestrating multi-agent AI pipelines.

loopforge-cli

Multi-agent development workflows for CodeBuddy, Codex, Cursor, and Claude Code

@pal-code/agents

Multi-agent extension for pal — delegate tasks to specialist sub-agents

mismcp

opencode multi-agent bus: agents ask each other questions over a shared SQLite queue

@khoralabs/agent-net

Custodial multi-agent network harness: agent pool, social fabric, memories, signed chat, and durable turn workflows

xz-pi-subagents

Focused multi-agent delegation with an interactive under-editor task list for Pi

@azatakmyradov/opencode-workflows-plugin

Sandboxed multi-agent workflow runs for OpenCode V2

@zamazingobjk/dulger

dulger — a multi-agent kanban orchestrator that wraps Claude Code / Codex

plangonaut

Human-governed project discovery, planning, multi-agent orchestration, and durable resume.

glido-coach

Route Codex prompts or run a visible multi-agent Codex team

@tylerho/pi-workflows

Sandboxed multi-agent workflow orchestration, plus a deterministic multi-angle code review built on it.

pi-multi-agent-mode

Codex-style collaboration for Pi: spawn_agent, followup_task, send_message, wait_agent, list_agents, and interrupt_agent. Named agent trees, configurable child model, history forks, mailboxes, and a packaged multi-agent-mode skill.

canon-ai

A spec-first, multi-agent AI coding pipeline you drop into any repo. The law your agents work under.

@dombaras/agent-harness

Reusable multi-agent harness for AI-assisted development: personas, skills, operating rules, model routing, and QA gates. Deploy into any project with `npx @dombaras/agent-harness init`.

graph-engineering

A durable, evidence-driven multi-agent engineering graph for repository audit and repair.

adaptive-ai-orchestrator

Local-first multi-agent workflow orchestrator

@xudesheng/pto

Power Take-Off for AI agents — governed multi-agent engineering workflows over interchangeable agent CLIs.

@theaileverage/marionette

Persistent multi-agent orchestration for Herdr, with a named lead, MCP tools, and a local dashboard.

@main12/agent-office-plugin

Payload CMS plugin for AI agent virtual office visualization — PixiJS canvas, multi-floor, multi-agent, WebSocket-ready

litecodeagent

Portable multi-agent workflows for Claude Code, Codex, Pi, OpenCode, Kilo Code, and direct API runners.

jaiye-agent

Multi-agent coordination protocol for AI coding tools

@adhd/backlog

Graph-store backlog for multi-agent teams - queryable, claimable, multi-agent-safe issue tracking with CLI and MCP

@tangleai/gmpl

Immutable evidence-bound multi-agent pattern recipes and prompt artifacts for MAS

blackboard-web

A local-first, cross-vendor multi-agent web harness for shared-context work on git projects.

openclaw-for-free

Unified Multi-Agent AI & Free Cloud VPS Control Station (Daytona & Freestyle.sh)

pi-swarm-supervisor

Multi-agent supervisor extension for pi

open-conclave

Multi-agent debate orchestrator plugin for OpenCode — Captain + parallel sub-agents + dynamic debate rounds + early stopping

pi-agents-helper

Pi skill + wrapper for pi-agents-helper: launch a multi-agent discussion with human interjection channel from a Pi session.

@te-river/opencode-gov-mode

Hierarchical multi-agent plugin for OpenCode Desktop — imperial government structure with Emperor, Prime Minister, Six Ministries, and deep subagent nesting.

@tangleai/mas

Tangle AI multi-agent runtime core — the one closed workflow IR, its pure validator/partitioner/lowering over JarenJS flow, and the store-neutral runtime contracts

@marcoscale98/pi-extensible-workflows

Deterministic multi-agent workflow orchestration for Pi

@ajayyarramalla/orchestrator

Multi-agent development orchestrator — autonomous task planning, execution, and validation with Claude Code integration

@sakura12/oh-my-deepseekharness

Multi-agent orchestration layer for DeepSeek Harness — 49 skills, 58 MCP tools, graph DAG runtime, team pipeline & HUD (OMC/OMX adaptation)

@fetot/mandor

A multi-agent orchestration workflow for product and engineering. Host-agnostic skills, per-repository adapters, and a knowledge vault that learns.

proofbridge-cli

ProofBridge: a multi-agent CLI workspace and cross-provider collaboration layer.

@ton-agent-kit/orchestrator

Multi-agent orchestration for TON — N agents collaborate on complex goals with parallel execution, dependency resolution, and fault tolerance

gial-cli

GIAL 3.0 — Hyper-Robust AI Engineering Orchestration & Multi-Agent Squad System

@worca/app

Worca turns a task into reviewed, merge-ready work. A deterministic multi-agent pipeline that plans, implements and reviews in isolated git worktrees, with quality gates, budgets and a human in the loop. Web UI, CLI and chat.

divineswe

Stateful multi-agent orchestration system for Claude Code, and an npm-installable OpenCode plugin

dsh-plugins-graph

LangGraph-style `graph` model tool for DeepSeek Harness — runs state graphs of subagent and pure-JS nodes with static and conditional edges, first-class cycles, and unbounded loops. Ships a web tool card visualizing live execution plus an interactive Grap

adam-network-crewai

CrewAI tools and integration for the Adam Network autonomous agent message stream

agent-bridge-orchestrator

Local message bus between terminal coding agents: Claude Code, Codex, Muse, OpenCode, Pi, Cursor

agent-company-core

Durable, policy-aware orchestration primitives for multi-agent systems

agent-conclave

One interface through which a coding agent spawns agents on any harness and exchanges messages with them

agent-coordination-substrate

Python client for Wiggle (wiggle.network) — a privacy-first, agent-native coordination layer: rooms with three privacy tiers, messaging, inbox, per-agent memory, roles, polls, and file exchange, with A2A + MCP discovery.

agent-harness-protocol

A provider-independent port for delegating work to agent harnesses

agent-harness-protocol-langgraph

LangChain and LangGraph adapter for Agent Harness Protocol

agent-mailbox

Local-first AI agent team workbench: project-scoped MCP mailboxes for existing apps and CLIs, shared context, task handoffs and human review.

agent-peer

A local IPC mesh so any AI coding agent harness (Claude Code, Codex CLI, Antigravity, pi, opencode, ...) can find, message, and reactively wake up any other.

agentity

Entity-oriented multi-agent runtime — your domain model, as a network of agents.

agentos-net

A decentralized protocol for autonomous AI agent identity and negotiation

agentplane

Define project policy once, render it into every agent harness, route work across providers, and get auditable results.

agentspace-sdk

Name reservation for the AgentSpace Python SDK (import agentspace), a live office for AI agent teams. The real SDK ships as 0.1.0.

alibabacloud-agentcore-collaboration

Independently versioned Worker collaboration for the AgentCore SDK

ccswarm

Reserved name. No functionality is provided by this distribution.

chatflow-agent

Lightweight, async multi-agent framework with native handoffs for Gemini, Gemma, Grok, OpenAI & Claude.

coagents

A Python library for building collaborative AI agents.

company-os-agent-ui

Local web control panel + live PM/Architect/Backend agent pilot for company-os-cli instances

dragon-py-a2a

DRAGON A2A 协议客户端(Python):官方 v1.0 卡面 + ARA 投影 + JSON-RPC 透传

enaya-agent

Task-delegation AI agent with multi-agent orchestration, research pipeline, and planning engine

langgraph-acp

Use ACP-compatible agents as first-class LangGraph nodes.

manyagents

Multi-agent evaluation and reasoning trace extraction for scientific workflows

py-agent-orchestra

A lightweight local workflow orchestrator for development and review agents.

switchboard-agents

A shared coordination board for AI coding agents driven by different people

Project100

A free, pseudonymous network for autonomous agents, pointed at one number: USD 100,000,000. Entry costs nothing and needs no account; an arriving agent finds open tasks at /api/v1/tasks, submits a result that is checked mechanically, and every passed work lays one stone in a public gallery.

common-agent-network

Public MCP coordination, knowledge, discovery, and feature requests for autonomous agents

protocol

Open protocol for two AI agents to negotiate terms their humans confirm. Spec, reference implementation, test vectors.

wombo-combo

WOMBO COMBO! — AI agent orchestration system for parallel feature development

a2a-exposed

Give any AI agent a public A2A (Agent2Agent) endpoint: a Cloudflare Worker, a wake webhook, or scheduled checks

skilld-ai

Production-grade AI agent team and collaboration framework CLI for modern projects

@vagarylabs/vagaris

Vagaris CLI — orchestrate AI agent teams to run a business

sauron-ai

Universal AI agent orchestrator and harness for 20 AI coding runtimes.

@ai-dossier/sched

The deterministic shell for hybrid model-driven orchestration of signed, versioned agent skills; never invokes an LLM.

@yiki21/pi-agent-team

Turn several machines running the Pi coding agent into one team over your tailnet. Three transports (broker / mesh / SWIM), one shared API and conformance suite.

@deepseek-ai/dsh-experimental-agent-team-profile

Experimental profile bundle enabling Agent Teams over dsh-base

@aisorun/aineighbor-cli

Autonomous Agent CLI and Client SDK for the AI Neighbor A2A Social Network

dsh-switchman

Autonomous Agent Teams doctrine for the four shipped DeepSeek Harness presets, plus language preferences, dispatch pools with model ranking, and context watermark control.

ai-agent-command-center

Next-Generation Spatial 3D/2D Orchestration Bridge & Autonomous Multi-Agent Swarm OS

johns-harness

John's Harness: a production agent harness that runs autonomous coding agents as one cooperative swarm.

@axiomantic/garden

Multi-Agent Swarm Orchestration, Empirical Dialectics & Ceremonies on top of Rhizo & Vine

@rhinos0608/pi-subagents

Pi extension for single-agent delegation and scripted multi-agent workflows

pi-owed

owed — the acceptance ledger for multi-agent task graphs. No receipt, not done.

@ai-agent-forge/plugin-multi-agent

Multi-agent orchestration plugin library for Agent Forge: role catalog/runner/assembly/orchestrator, root/child facade adapters, transition-store Goal/Plan/Todo domain plugins, dependency and discovery wiring, policy manifest, and domain recovery

@cecwxf/dsh-room

DSH Room — Web and Desktop plugin for encrypted multi-agent collaboration

speiidev

Multi-agent terminal orchestrator wrapper

abelien-harness

npx-installable multi-agent skill harness: generic kernel + pluggable domain packs

@entrogic-net/agents

AGENT.md parser and team profiles for BanglaClaw multi-agent setups

@nedimyilmaz/chimera

Chimera multi-agent daemon, CLI and MCP server

@moc-global/loft-agents

Multi-agent orchestration layer for LOFT Framework

autonomation

Operating doctrine for multi-agent software factories — Toyota Production System and TSMC manufacturing principles translated into artifacts for agentic engineering.

@toby1123yjh/vibe-studio

A multi-agent studio for independent developers and one-person companies

schellingaf

Schelling Add Forward's connector over stdio for multi-agent coordination, with your KEY kept on your own machine.

More in Agent frameworks & infrastructure