Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 60 of 62
Local workbench for assembling, inspecting, and running multi-agent workflow graphs
Multi-Agent Workflow plugin for DeepSeek Harness (dsh)
Rulith: a local multi-agent workbench with conversations and governed Worker tools
Persistent in-process Codex-style multi-agent collaboration for Pi
Enterprise-grade spec-driven development framework for multi-agent workflows
Native multi-agent hub: Claude Code, Codex, Kimi Code, Pi and local inference as peers in one project
Structured multi-agent software engineering orchestrator for Pi
Autonomous multi-agent runtime powered by mu
SCIPIX — a visual AI workflow engine: a node-based canvas for orchestrating multi-agent AI pipelines.
Multi-agent development workflows for CodeBuddy, Codex, Cursor, and Claude Code
Multi-agent extension for pal — delegate tasks to specialist sub-agents
opencode multi-agent bus: agents ask each other questions over a shared SQLite queue
Custodial multi-agent network harness: agent pool, social fabric, memories, signed chat, and durable turn workflows
Focused multi-agent delegation with an interactive under-editor task list for Pi
Sandboxed multi-agent workflow runs for OpenCode V2
dulger — a multi-agent kanban orchestrator that wraps Claude Code / Codex
Human-governed project discovery, planning, multi-agent orchestration, and durable resume.
Route Codex prompts or run a visible multi-agent Codex team
Sandboxed multi-agent workflow orchestration, plus a deterministic multi-angle code review built on it.
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.
A spec-first, multi-agent AI coding pipeline you drop into any repo. The law your agents work under.
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`.
A durable, evidence-driven multi-agent engineering graph for repository audit and repair.
Local-first multi-agent workflow orchestrator
Power Take-Off for AI agents — governed multi-agent engineering workflows over interchangeable agent CLIs.
Persistent multi-agent orchestration for Herdr, with a named lead, MCP tools, and a local dashboard.
Payload CMS plugin for AI agent virtual office visualization — PixiJS canvas, multi-floor, multi-agent, WebSocket-ready
Portable multi-agent workflows for Claude Code, Codex, Pi, OpenCode, Kilo Code, and direct API runners.
Multi-agent coordination protocol for AI coding tools
Graph-store backlog for multi-agent teams - queryable, claimable, multi-agent-safe issue tracking with CLI and MCP
Immutable evidence-bound multi-agent pattern recipes and prompt artifacts for MAS
A local-first, cross-vendor multi-agent web harness for shared-context work on git projects.
Unified Multi-Agent AI & Free Cloud VPS Control Station (Daytona & Freestyle.sh)
Multi-agent supervisor extension for pi
Multi-agent debate orchestrator plugin for OpenCode — Captain + parallel sub-agents + dynamic debate rounds + early stopping
Pi skill + wrapper for pi-agents-helper: launch a multi-agent discussion with human interjection channel from a Pi session.
Hierarchical multi-agent plugin for OpenCode Desktop — imperial government structure with Emperor, Prime Minister, Six Ministries, and deep subagent nesting.
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
Deterministic multi-agent workflow orchestration for Pi
Multi-agent development orchestrator — autonomous task planning, execution, and validation with Claude Code integration
Multi-agent orchestration layer for DeepSeek Harness — 49 skills, 58 MCP tools, graph DAG runtime, team pipeline & HUD (OMC/OMX adaptation)
A multi-agent orchestration workflow for product and engineering. Host-agnostic skills, per-repository adapters, and a knowledge vault that learns.
ProofBridge: a multi-agent CLI workspace and cross-provider collaboration layer.
Multi-agent orchestration for TON — N agents collaborate on complex goals with parallel execution, dependency resolution, and fault tolerance
GIAL 3.0 — Hyper-Robust AI Engineering Orchestration & Multi-Agent Squad System
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.
Stateful multi-agent orchestration system for Claude Code, and an npm-installable OpenCode plugin
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
CrewAI tools and integration for the Adam Network autonomous agent message stream
Local message bus between terminal coding agents: Claude Code, Codex, Muse, OpenCode, Pi, Cursor
Durable, policy-aware orchestration primitives for multi-agent systems
One interface through which a coding agent spawns agents on any harness and exchanges messages with them
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.
A provider-independent port for delegating work to agent harnesses
LangChain and LangGraph adapter for Agent Harness Protocol
Local-first AI agent team workbench: project-scoped MCP mailboxes for existing apps and CLIs, shared context, task handoffs and human review.
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.
Entity-oriented multi-agent runtime — your domain model, as a network of agents.
A decentralized protocol for autonomous AI agent identity and negotiation
Define project policy once, render it into every agent harness, route work across providers, and get auditable results.
Name reservation for the AgentSpace Python SDK (import agentspace), a live office for AI agent teams. The real SDK ships as 0.1.0.
Independently versioned Worker collaboration for the AgentCore SDK
Reserved name. No functionality is provided by this distribution.
Lightweight, async multi-agent framework with native handoffs for Gemini, Gemma, Grok, OpenAI & Claude.
A Python library for building collaborative AI agents.
Local web control panel + live PM/Architect/Backend agent pilot for company-os-cli instances
DRAGON A2A 协议客户端(Python):官方 v1.0 卡面 + ARA 投影 + JSON-RPC 透传
Task-delegation AI agent with multi-agent orchestration, research pipeline, and planning engine
Use ACP-compatible agents as first-class LangGraph nodes.
Multi-agent evaluation and reasoning trace extraction for scientific workflows
A lightweight local workflow orchestrator for development and review agents.
A shared coordination board for AI coding agents driven by different people
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.
Public MCP coordination, knowledge, discovery, and feature requests for autonomous agents
Open protocol for two AI agents to negotiate terms their humans confirm. Spec, reference implementation, test vectors.
WOMBO COMBO! — AI agent orchestration system for parallel feature development
Give any AI agent a public A2A (Agent2Agent) endpoint: a Cloudflare Worker, a wake webhook, or scheduled checks
Production-grade AI agent team and collaboration framework CLI for modern projects
Vagaris CLI — orchestrate AI agent teams to run a business
Universal AI agent orchestrator and harness for 20 AI coding runtimes.
The deterministic shell for hybrid model-driven orchestration of signed, versioned agent skills; never invokes an LLM.
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.
Experimental profile bundle enabling Agent Teams over dsh-base
Autonomous Agent CLI and Client SDK for the AI Neighbor A2A Social Network
Autonomous Agent Teams doctrine for the four shipped DeepSeek Harness presets, plus language preferences, dispatch pools with model ranking, and context watermark control.
Next-Generation Spatial 3D/2D Orchestration Bridge & Autonomous Multi-Agent Swarm OS
John's Harness: a production agent harness that runs autonomous coding agents as one cooperative swarm.
Multi-Agent Swarm Orchestration, Empirical Dialectics & Ceremonies on top of Rhizo & Vine
Pi extension for single-agent delegation and scripted multi-agent workflows
owed — the acceptance ledger for multi-agent task graphs. No receipt, not done.
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
DSH Room — Web and Desktop plugin for encrypted multi-agent collaboration
Multi-agent terminal orchestrator wrapper
npx-installable multi-agent skill harness: generic kernel + pluggable domain packs
AGENT.md parser and team profiles for BanglaClaw multi-agent setups
Chimera multi-agent daemon, CLI and MCP server
Multi-agent orchestration layer for LOFT Framework
Operating doctrine for multi-agent software factories — Toyota Production System and TSMC manufacturing principles translated into artifacts for agentic engineering.
A multi-agent studio for independent developers and one-person companies
Schelling Add Forward's connector over stdio for multi-agent coordination, with your KEY kept on your own machine.