Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 58 of 62
Pi extension for delegating work to specialized isolated subagents.
CLI and library for the Agent Dispatch Messaging Protocol (ADMP)
Pi extension for single-agent delegation and scripted multi-agent workflows
Open harness for reproducible multi-agent coding workflows
Multi-agent coordination + createTeam orchestration for AgentProdReady.
Scaffold the AgentOS multi-agent software-delivery framework into any project
**Multi-Agent AI Assistant built on OpenClaw**
Multi-agent coding runtime with a real-time collaboration WebUI, durable tasks, CLI, and SDK
Multi-agent orchestration — the swarm architectures
Orchestrate and manage multi-agent group conversations — an agent tool for SperaxOS.
AG-Kit Multi-Agent example
A provider-agnostic, evidence-based ideation engine: independent multi-agent generation, blind→pool brainwriting rounds, embedding-dedup + clustering + split-axis convergence, and an evaluate→regenerate feedback loop — as a zero-dependency injectable func
Multi-Agent Orchestration for AI Coding Assistants — task management, git isolation, file locking, and real-time dashboard
Zero-dependency multi-agent orchestrator with a file-based mail model for AI coding agents (Claude Code, Codex, Gemini, Hermes). Agents talk by reading and writing files; the orchestrator routes the mail.
Lightweight multi-agent coordinator for Hermes-agent: board state, role nodes (Conductor / Builder / Reviewer / Scout), A2A contract-driven task routing, and multiplexer-friendly terminal event streams.
An open-source multi-agent AI team built on Agency Swarm (linux arm64 TUI binary)
Auditable multi-agent coordination for OpenCode — parallel agent fleets with P2P messaging, witnessed receipts, and quorum ratification. Who saw this, who approved it, prove it.
An open-source multi-agent AI team built on Agency Swarm (win32 x64 TUI binary)
An open-source multi-agent AI team built on Agency Swarm (linux x64 TUI binary)
An open-source multi-agent AI team built on Agency Swarm (darwin arm64 TUI binary)
A pi agent framework that orchestrates coordinated sub-agent teams directly from the .pi/ithacus folder.
An ephemeral orchestration hub for AI coding agents: presence, leases, messaging and a shared blackboard, all with TTLs.
A Hamachi server for agents: start a hub, get an address, agents join and work together
AgentYard SDK — register, discover, and manage A2A agents
AI Agent Orchestration Framework
A local websocket-based message bus that allows your agentic coding harnesses to talk to each other.
Pi helper for the inter-agent message bus: connect listener and command-line tools
MARLA: Multi-Agent Reinforcement Learning Architecture for NASimEmu
Autonomous multi-agent ML research platform
Compose agents into a graph over oneharness/onejudge and merge their outputs into one event stream.
Messaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure. (YAAC: Yet Another Agentic Chat.)
AI agent orchestration toolkit. Seven subcommands:
Colorful CLI to discover and call x402-payable AI agent services on minia2a.uk. Zero deps.
TypeScript-native workflow engine for AI agent orchestration — code as config, no DSL
Signed, searchable, provider-neutral AI agent discovery with live schemas and A2A, MCP, Arazzo, and WebMCP interfaces.
睿思多智能体管理系统 CLI 工具
Stop multi-agent coding drift: contracts, path leases, evidence gates + optional self-improving dispatch (Homer-meta) for Pi
Repo-local multi-agent collaboration protocol + gateway CLI for AI coding agents (Claude Code, Codex): runs, task claims, evidence gates, review/verify, audit.
An open-source multi-agent AI team built on Agency Swarm (darwin x64 TUI binary)
A local-first, multi-agent development harness that turns a goal into planned, executed and verified work — with an evidence receipt for every run.
An open-source multi-agent AI team built on Agency Swarm (linux arm64 TUI binary)
Canonical capability manifest schema + 3-step pre-delegation negotiation handshake with HMAC-signed manifests, capability diff, and TTL. Zero runtime dependencies.
An email-like messaging platform for AI agents
AgentAvow bridge for Microsoft AutoGen (formerly agentgraph-bridge-autogen) — trust-gated tools and agent registration for the AgentAvow trust network
AgentAvow bridge for CrewAI (formerly agentgraph-bridge-crewai) — trust-gated tools and agent registration for the AgentAvow trust network
AgentAvow bridge for LangChain (formerly agentgraph-bridge-langchain) — register agents and graphs with the AgentAvow trust network
Sophisticated Multi-Agent Orchestration System with infinite tools, cross-platform support, and TUI interface
Passive-awareness bus for agent pods: threads, non-blocking mentions and background watchers that fold teammate discoveries in at step boundaries (AgentRadio).
In-process spawn subagent backend: runs a fresh child agent on ctx.agents
In-process fork subagent backend: runs a child agent seeded with a prefix of the parent's log
Shared in-process subagent run driver: drives a child agent on ctx.agents (used by the spawn and fork backends)
TAKT v2 CLI — multi-agent production system
Multi-agent orchestration, sub-agent delegation, parallel execution, and iterative refinement loops for nestjs-agentic.
AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
TGO — a thin multi-agent orchestration plugin for OpenCode
Multi-agent development workflow for OpenCode, with V3 profiles and an executable workflow engine
Pi extension for single-agent delegation and scripted multi-agent workflows
Herdr-native multi-agent orchestration for Pi.
Multi Agent Regulation System (MARS)
Parent-workspace AI development harness for multi-repo, multi-agent engineering work.
Reserved package name for WitArc, a multi-agent collaboration platform.
Deterministic, resumable multi-agent workflows — a harness-agnostic MCP server that orchestrates Codex, Claude, Cursor, and Kimi agents from plain JavaScript, with journaled resume, git worktree isolation, and personas.
kixparadigm-en — English edition of the kix paradigm preset for DeepSeek Harness: resident cognition layer (EN) + kixpower multi-agent orchestration, one-command import (preset + vision-bridge + guard plugins)
Connect your AI agents. One command. P2P multi-agent collaboration.
Politik — a governed multi-agent framework built on git. The SCM repository is the session: charter, record, state, and invite in one.
The Nano agentic protocol (ADR 0056): one app-tier channel carrying agent presence/registry, demand×supply, a shared blackboard and live terminal relay — with the wire contract, channel/hub, family modules and the operator cockpit, as subpath exports.
Nano Workforce — an Agent Graph Orchestration application for Agentic SDLC: durable BPMN processes that coordinate a graph of AI agents across the software delivery lifecycle.
XMesh — enterprise agentic mesh runtime for task execution, evidence, explicit rulings, and grounded learning.
A2A Protocol v1.0 bidirectional extension for the Pi coding agent — distribute tasks to remote agents, be called by them, and self-declare for local session discovery.
Multi-agent orchestration CLI — dispatch coding agents (Codex, Claude, Aider, etc.) in parallel
Multi-agent orchestration CLI — dispatch coding agents (Codex, Claude, Aider, etc.) in parallel
Framework-agnostic SDK for building A2A/kagent-compliant agent runners.
Agent fleet management tool
Coordinator that runs a small graph of AI-agent nodes with bounded spend, mechanical gates and journaled state
Declarative multiparty session protocols for AI agents
Multi-agent collaboration plugin: broadcast, sequential, debate, supervisor, consensus and relay strategies over DeepSeek/OpenAI-compatible LLMs
A credential-aware router that evolves which specialist to dispatch each task to, sitting above OpenClaw, Hermes, ZeroClaw, or any REST-accessible agent backend.
Native-first Codex subagent coordination with an optional cross-session bridge
Local, auditable coordination and decision tracking for human and AI-agent teams
Phase-Shifted Agentic Swarm (PSAS) methodology for multi-agent cognitive synchronization
Native Codex plugin for spawning, configuring, and overseeing ours-fleet agents.
Multi-agent orchestration across pi sessions
OSS-first engineering harness for deterministic, spec-driven, issue-driven, audit-governed and orchestration-first multi-agent software delivery.
Decentralized LAN multi-agent collaboration node — AI-controllable enhanced LocalSend (去中心化局域网多智能体协作节点)
Multi-agent team system for Pi — resident teammates, shared task board, and peer-to-peer messaging
Dependency-aware multi-agent workflow CLI for OpenCode.
Fork: Pi extension for single-agent delegation and scripted multi-agent workflows
Agentic HQ - Orchestrating agentic software development teams
Multi-Agent Mesh: crash-isolated multi-agent coordination — files are the messages, adoption replaces all-hands-on-deck failure. Built on asmfs-spec. Every claim carries an experiment number.
Connect your local agent (Codex, Hermes, …) to s.space as a first-class room agent.
Inter-agent messaging bus for Claude Code, Grok, OMP, Codex and others
Reference implementation of the Liquid Interfaces Protocol (LIP)
Runtime governance middleware for CrewAI: exit reports, overlap detection, knowledge inheritance.
Search, hire, and dispute other agents autonomously from inside your own agent's code — authenticated with the AgentCredential gora8 already gave you, no separate setup
Turn ad-hoc subagents into durable, accountable AI teams.
WorkSwarm
Velocity AI Engine — Universal AI Agent Orchestrator with Formal Verification
Remote multi-agent workspace CLI with deep Claude integration, native terminal streaming, and self-hosting.
Multi-agent team management plugin for DeepSeek Harness
Eko multi-agent connector for BonkLM — validates planner output + BrowserAgent + FileAgent + MCP-tool dispatch.