Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 45 of 62
AI agent framework that dispatches a coordinated team of specialist agents in parallel. Orchestrate your code.
Multi-Agent framework allowing NocoBase AI Employees to spawn and delegate tasks to specialized sub-agents with specific skills.
Open-source local AI agent framework — Queen, Workers, Quorum. Experimental research tool.
TITAN Method - Multi-agent framework with 6 specialized agents for product development
A multi-agent framework for LLM applications
A multi-agent framework that takes any idea from concept to deployable app — market validation, product, UX, architecture, and engineering, in one pipeline.
Yuva AI - Neural-graph development agent framework with enforcement, multi-agent swarm, headless automation for 5 AI CLIs (Claude, Gemini, Codex, OpenCode, Aider), and config generation for 20 LLM platforms
TypeScript AI Agent framework - from single agent to multi-agent cluster orchestration
The Multi-Agent Framework
Enterprise role orchestration and workflow automation — a deterministic agent framework implementing CEO, CTO, CFO, COO, CMO, AEO, Architect, Planner, Analyst, Reviewer, and Executor roles for organizational automation and orchestration.
Microsoft AutoGen multi-agent framework configuration generator CLI
Ultimate MASTERMETA AI Agent System Installer - Production-ready CrewAI multi-agent framework with OWASP GenAI security, vector databases, and consciousness framework
Multi-agent framework for async parallel tool orchestration and intelligent task dispatch
Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.
Agentic Mesh
MCP Agentic: agent orchestration server via stdio Bus
Design and visualize agentic orchestration flows with trailer A/B-roll planning support.
Orchestration runtime for antibrittle agentic workflows
A2A (Agent-to-Agent) client for AI Agents using A2A and the Agentic Profile
MCP Agentic: agent orchestration server via stdio Bus
Agentic Profile Node.js package for agent to agent chat
Agentic development framework that orchestrates specialized AI expert roles
oLane p2p node used to host agentic functionality
GitHub Project based installer and multi-agent orchestration CLI that composes say828/agentic-core with public say828/template-* repos.
AC2 — Agentic Communication and Control Protocol SDK
A2A (Agent-to-Agent) and MCP Express middleware for AI Agents using A2A, MCP, and the Agentic Profile protocols
emploke — orchestrate agentic systems built on the MetaAgents format spec
JavaScript implementation of the Crew AI Framework
Implementation of the AG-UI protocol for CrewAI.
Unofficial CrewAI JavaScript SDK
CrewAI tool definitions for GenZAgents work receipts — typed, signed, ready to drop into a Crew
Zero-config agentegrity adapter for CrewAI TypeScript (@crewai-ts/core). Mirrors the Python agentegrity.crewai module.
CrewAI adapter for CodeSpar — convert session tools to CrewAI tool format
TypeScript port of crewAI for agent-based workflows
Multi-agent automation framework written in TypeScript. Patterned after CrewAI.
AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS, Copilot, LangGrap
CrewAI-style role-based multi-agent team orchestration for Wundr
A2A (Agent-to-Agent) protocol wrapper for OpenCode. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, SSE streaming with polling fallback, context building, and multi-turn conversations.
Distributed cognitive mesh — multi-node LLM orchestration with genome evolution and on-chain verification via 0G
A2A (Agent-to-Agent) protocol wrapper for the GitHub Copilot SDK. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, streaming, context building, and multi-turn conversations.
CLI for the Signet agent network. Register your AI agent on onsignet.com, connect to the relay, and get a live public profile — in one command.
The TCP/IP of Agent Standards - Universal protocol translation layer for AI Agents
OpenClaw skill for Synmerco, the marketplace where AI agents hire AI agents. Teaches your assistant to join, find paid work, deliver, get paid in USDC through escrow, and hire other agents.
Ephemeral AI agent orchestration system with Hedera blockchain auditability
OpenClaw — open-source agent orchestration plugin for CMDOP
A2A v1.0 bridge for OpenClaw AI assistant — agent-to-agent communication
TypeScript SDK for SAMVAD — Secure Agent Messaging, Verification And Discovery (The Open Sovereign Agent Dialogue Protocol)
MACS — The Universal Workbench for AI Agents. Cross-framework work coordination via JSONL event sourcing.
Agent teamwork in your terminal — CLI-first coordination for any AI agent runtime
Multi-agent orchestration framework for AgentSea. Build, compose, and orchestrate agent crews with role-based coordination, task delegation, and workflow automation.
SDK for the agent-to-agent services marketplace — discover, pay, and use AI agent services with one function call
Multi-agent orchestration CLI powered by Claude Code
TypeScript SDK for AI City — register agents, check reputation, and interact with the agent economy
Multi-agent YAML workflow engine — 276 CN + 191 EN + 5 more language libraries of AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 20+ API providers, plus 10 key-free options (coding-CLI s
UAICP specification: reliability contract for agentic workflow integrity and control
Run squads of AI agents from your terminal — defined in markdown, tracked in git.
Agent-to-agent messaging encrypted on the agent's device; the relay stores ciphertext and sees sender and recipient DIDs. Peer keys are checked against bundles each agent signs with the key its DID is derived from. Double Ratchet, X3DH, ML-KEM-768, deniab
Declarative agent teams with DAG execution and context routing. Define what each agent knows.
Babel wire protocol — validation, creation, audit, and measured confidence for agent-to-agent cognitive state transfer. Catches metacognitive poisoning before it propagates.
Multi-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.
Scaffold a full AI engineering team into any project — personas, wired and ready in 60 seconds.
AgentKit SDK - Build AI agents with A2A and LangGraph protocol support
LangGraph-style cyclic, state-driven workflow orchestration for AI agents
An implementation of a multi-agent swarm using LangGraph
A flexible framework for orchestrating multiple specialized AI agents to collaborate on tasks. This system leverages LangChain and LangGraph to create a directed graph of agent interactions, with a supervisor agent coordinating the workflow.
Final release under this name: the project continues as 10xGraph (pip install 10xgraph). Production-grade Python framework for building, orchestrating, and deploying multi-agent LLM systems. A simpler, batteries-included alternative to LangGraph, CrewAI, and AutoGen with graph-based workflows, durable state, native MCP support, and provider-agnostic LLM integration (OpenAI, Google GenAI, Anthropic).
A placeholder project for orchestrating multiple agents to perform higher-level tasks in coordination
AgentHive is a flexible, Python-based service framework for managing distributed task execution.
A modern way to let AI-agents Communicate
Agent for cluster test.
CollabAgents is a Python framework developed by Vishnu D. for developing AI agents equipped with specialized roles and tools to handle complex user requests efficiently. Users have 100 percent control over their prompts.
A delegation-centric multi-agent system framework for LLM-based autonomous systems
Discord-based Swarm Protocol Library
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
Generative Agent-Based Modeling with Large Language Models Empowered Agents
1.黄页服务查询到的结果是一个,而不是列表。 2.通用协议文件中添加一个请求的协议
Ocean-Agent for Master nodes
Ocean-Agent for Worker nodes
Swarm-Plus is a Python framework developed by Vishnu Durairaj. for developing AI agents equipped with specialized roles and tools to handle complex user requests efficiently.
AgentSpeak agents on A2A/ACL protocol.
Integrate A2A protocol agents into LangChain/LangGraph applications
A2A protocol implementation for LangGraph agents
Integrates the Agent SDK with A2A
A2A protocol bridge for AgentMesh — trust-verified agent-to-agent communication via the A2A standard
AI agent swarm orchestrator for coding
Public Preview — Agent Governance Toolkit integration for Google ADK: policy enforcement, trust verification, and audit trails for ADK agents
Reference implementation of the Agent Deliberation Protocol (ADP). Python/FastAPI runtime for agents that deliberate, sign proposals, journal outcomes, and publish signed calibration snapshots.
Aevum — A2A v1.0 agent protocol interceptor and governance layer.
CLI tool for AG2 agent development with A2A protocol support
Agency Swarm framework
a proof-of-concept inspired by BabyAGI, the Plan-Do-Check-Adjust (PDCA) cycle, and the actor model of concurrency
Agent Alignment Protocol - The missing alignment layer for the agent protocol stack
Python SDK for Agent Café — the agent-to-agent marketplace
A virtual currency system where AI agents trade capabilities in a marketplace
Temporary chat rooms for AI agents to communicate in real-time
A meta-level agentic workflow that creates independent, self-contained AI agent clusters
Vendor-neutral MESI + optimistic-concurrency coordinator for multi-agent state — a stale write is denied or returned as a typed conflict, never silently applied; safety invariants model-checked in TLA+
Multi-agent colosseum framework. Prove that agents debating, researching, and red-teaming produce better answers than a single agent.
Let AI agents form companies that hire humans - Ask for Kindly Help, Ask for All Help