Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 54 of 62
Claude Agent SDK integration for KAgent with A2A server support
TypeScript SDK for CueCue's AI-powered multi-agent research system
Portable, vendor-neutral AI Dev OS for multi-agent coding workflows
Unified pi orchestration package combining batch orchestrator, Ralph loop, and subagent dispatch for multi-agent pipelines
Comprehensive, high-performance, and safety-hardened Pi-native multi-agent orchestration package, featuring advanced workflows, damage-control rules, and developer tooling.
Lightweight, concurrency-safe, multi-tenant Feishu AI Agent framework
Yoke — a multi-agent harness: CLI/TUI (yoke) + HTTP API & Web UI server (yoke-server).
A multi-agent workflow for processing audio, image, and video data.
A production-grade Python framework implementing reusable multi-agent design patterns, stateful orchestration, and resilient execution harnesses for autonomous LLM systems.
Mesh topology for distributed agent communication and workload distribution
Agents
Agent communication mux — event streaming, hooks, sessions
Self-improving multi-agent orchestration that takes you from build → CI/CD → deploy. Interactive setup wizard, pluggable AI providers, agent swarms in git worktrees.
Multi-agent requirements development pipeline for OpenCode
Multi-agent self-improving system with shared experiential memory and parallel agent execution
Independent multi-agent team orchestration plugin for OpenCode
Multi-agent consensus CLI — ask multiple AI agents and compare answers
Multi-agent conversation loop with human-in-the-loop support.
Conversational meta-agent for your terminal: every prompt runs through a multi-agent coordination round (debate, adversarial, tournament, consensus) over Claude Code + Codex, on your subscriptions.
Framework-agnostic multi-agent task delegation - in-memory bus, typed tasks, LLM coordinator, dead-letter queue
Deterministic, crash-safe multi-agent workflow engine. Author workflows as TypeScript, orchestrate coding-agent calls with agent()/parallel()/pipeline(), and replay from a journal.
CrewChief: Multi-agent orchestration CLI for coordinating AI agents via git worktrees.
Multi-agent management tool — a CLI that manages a roster of named agent profiles on top of existing agent runtimes (claude-code, copilot-cli, ...).
CLI launcher for the agent-teams AI Kanban platform (pull pre-built images, or clone + build locally).
Agentic functional programming: a multi-agent runtime built on three primitives — recursive spawning, addressable mailboxes, and capability passing — with FP-style combinators on top.
Declarative YAML specs for multi-agent LLM systems — validate, compile, test, diff, render
Kubernetes Dashboard for Agent Systems — CLI + web control plane for multi-agent LLM blueprints
Graph-based workflow orchestrator with durable execution, multi-agent coordination, and human-in-the-loop approval gates.
Tools for building multi-agent apps.
A CLI that scaffolds a structured multi-agent workspace on top of AI coding tools (Claude Code, Codex CLI, Gemini)
Native CrewAI tools for the Rine network — send, receive, discover, and run E2E-encrypted agent-to-agent conversations and groups from a CrewAI crew
A2A agent protocol plugin for HiveMind-core
Orchestrate AI agents from your terminal — multi-source credential import, swarm topology, background queue, live dashboard
Flow orchestration, persistence, and visualization features for CrewAI TypeScript.
Agent-to-agent protocol and A2UI features for CrewAI TypeScript.
Native Mastra.ai tools for the rine network — E2E-encrypted (HPKE 1:1, MLS groups, PQ-hybrid) agent-to-agent messaging, discovery, and coordination as createTool tools, a toolkit aggregator, a lifecycle bridge, a Tier-3 workflow-resume bridge, and a setup
A2A (Agent2Agent) adapter for agentkit-js — expose agents as A2A servers and call remote A2A agents
Native LangChain / LangGraph tools for the Rine network — send, receive, discover, and run E2E-encrypted agent-to-agent conversations and groups from a LangChain / LangGraph agent
Remote AI Agent management toolkit — agentgw + agentd
mbali core: a reconciling control plane for fleets of remote AI agent sessions. Zero dependencies.
天空织机 Skyloom — 6 weather-themed AI agents: Fog, Rain, Frost, Snow, Dew, Fair
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
Open-source tmux AI agent team orchestrator for Claude Code, Codex, Gemini CLI, and custom terminal coding agents.
Multi-agent orchestration and Codex governance for OpenCode, Hermes, Grok Build, and OpenClaw
Optional autonomous multi-session orchestrator CLI for agentic-workflow-kit.
Multi-agent AI engineering runtime — audit, fix, graph, analyze
POMASA Multi-Agent System Dashboard
Foundation core for the iapeer multi-agent ecosystem: identity, registry, storage, codec.
Standalone npm launcher for Canvas Flow multi-agent GenAI workflows.
Multi-agent workflow orchestration for Pi — stateful workflow management with persistence, state machine, and execution tracing.
Production-grade CLI multi-agent AI assistant, real-time voice controller, and automated background job scheduler for local and cloud environments.
Multi-agent project orchestrator for hydra-acp — decomposes a goal into a task DAG, spawns worker sessions, coordinates via prompts.
Swarm DAO governance adapter for OpenCode — multi-agent deliberation, quality gates, and structured decision-making
oh-my-deepseek (omd) — Multi-agent orchestration layer for DeepSeek with prompt caching optimization.
Multi-agent orchestration layer for Kimi Code CLI
Multi-agent team orchestration on top of hoocode agents: DAG dispatch, planner, agent registry, tagged event channel
A local, filesystem-backed message board that lets AI coding agents open private channels, exchange messages and artifacts, and tear them down when done.
Nexus Protocol SDK — Ed25519 DID identity for AI agents. 15 lines to register, post, and vote.
Verigent trust verification for Microsoft AutoGen multi-agent systems
Verigent trust verification for CrewAI agent delegation
A lightweight framework for multi-AI-agent cohabitation — where AI agents live together, share memory, and collaborate like roommates. 🏠🤖
Generic multi-agent engine — model-agnostic, transport-agnostic
Multi-agent workflow orchestration for Claude Code — isolated git worktrees, structured state tracking, state-aware agent handoffs
SwarmAgency — a multi-agent AI team you can run from a single terminal
Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI
Autonomous multi-agent development framework with spec-driven sprints and convergent iteration
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)
Bring your swarm. Strix governs it. A framework-neutral bridge that turns a real multi-agent run (Claude Agent SDK / CrewAI / LangGraph / OpenAI Swarm) into signed delegations + governed tool calls + independently-verifiable proof.
Conservation-law governance for AI agent fleets — works with any framework
Run Claude Code as an A2A protocol agent server.
AACP coordination layer for AutoGen multi-agent workflows
Public chat for AI agents - WebSocket + JSON, 3-method SDK, no UI required
Portable multi-agent ultracode orchestration with a 3-agent adversarial debate that converges to unanimous consensus
Orchestrate micro-agent swarms using Markov transition matrices as handoff patterns
CrewAI tool that issues Vouch Credentials to authorize multi-agent tool calls.
Embeddable Temporal worker for the Stigmer AI agent platform — handles agent execution, workflow orchestration, and MCP server management
Polaris — standalone taskchain orchestration framework for governed AI agent workflows
Host-agnostic Node CLI for E2E encrypted agent-to-agent communication via XMTP
Agent Host Protocol (AHP) type definitions and reducers — vendored from Microsoft's open-source AHP repo, built via prebuild transform step.
Atabey — AI Governance & Multi-Agent Platform / Orchestrator — Core Engine
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
Universal collaboration protocol + CLI for multi-agent LLM teams
Multi-agent collaboration template for OpenCode
A customisable multi-agent workflow-orchestration engine for the pi coding agent.
A configurable, gated, cross-reviewed multi-agent code pipeline: write, gate, review, fix, stop.
Synapse Protocol SDK - Multi-agent systems on NATS with streaming, HTTP bridges, cryptographic ACL, and reputation scoring
Lightweight multi-agent TUI and stable cross-provider collaboration layer for Codex, Claude, Gemini, Grok, Kimi, and other CLI agents.
Deterministic multi-agent workflows for OpenCode — script agent/pipeline/parallel/phase with journaled replay, plus a native /workflows-style TUI viewer.
Inlay — multi-agent collaboration pipeline for ADR + Context (conflict-free, local-first)
A harness for precise, auditable agent workflows — compose a graph of roles, drive the CLI agents already on your machine, with typed, gated, replayable handoffs. Built on LangGraph.
Multi-agent decision-making framework with flat inference and a 4-layer creative pipeline
Multi-agent development orchestrator with TUI
Multi-agent orchestration system for AI-native software development. Delivers AI-DLC, Agile, and custom SDLC flows as markdown-based agent systems.
Multi-agent orchestration for VR-based drug discovery using Narupa integration with HoloScript
JavaScript-native multi-agent orchestration CLI for your terminal. Plan, debate, and run a swarm of agents locally.
AACP coordination layer for Pydantic AI multi-agent workflows
Swink™ AgentShore™ — RL-based multi-agent orchestrator
LeviathanTalon: hierarchical Kabbalistic multi-agent swarm orchestrator. 2,832 concurrent agents at full scale.
Coordination certificate for multi-agent (LangGraph) systems: prove your agent graph is deterministic, deadlock-free, loop-aware, optimally scheduled, and retry-safe — static analysis, CI-ready.
Meta-agent and runtime client for TellMesh hypervisor