Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 29 of 62
GPS for your LLMs
A2A protocol bridge plugin for OpenClaw — agent card, JSON-RPC endpoint, and remote agent tools
Independent multi-agent orchestrator — manages parallel AI Worker agents across terminal sessions
An intelligent multi-agent AI assistant powered by Gemini LLM using the ReAct pattern to orchestrate five specialized agents (crypto, stocks, portfolio, RAG, web search) through MCP. Features a LangGraph supervisor with streaming Gradio UI.
Siomi is a platform multi-agent AI to generate answers to our clients by messages, documents, graphics, report from big data and more
Driving Dynamic Multi-Participant Chat Interactions for AI and Human Discourse 🤖
Domain-agnostic agent orchestration platform. Django + HTMX dashboard, containerized specialist agents, natural language scheduling, multi-provider LLM support.
A modular multi-agent system framework leveraging Streamlit and Langgraph to coordinate complex tasks through a dynamically configurable, user-friendly interface.
a2a4j example project
Using CrewAI and RAG to build a senior high school QA System and leetcode solver
Swarms-Example-1-Click-Template by swarms.ai
Cognifold is sci-fi inspired interface to aggregate various specialized AI agents, making them easily accessible and manageable right from your desktop.
Evoking excitement.
General-purpose, multi-agent framework for automating tasks using AI agents composed in teams for conversation-based collaboration.
Declarative Agentic Orchestration Framework
Reusable AI teams for real work: generate, run, and evolve versioned multi-agent teams.
The universal platform where AI agents discover, collaborate, and access specialized services. One system to orchestrate your entire agent ecosystem.
AI Agent Orchestration Platform - Enabling intelligent multi-agent collaboration for development workflows with enterprise-grade reliability and performance
Jarvis AI Platform Engineer Multi Agent System
🐋 Cloud and AI-native multi-agent orchestration platform for Kubernetes
AWS-powered hotel booking multi-agent assistant built with Strands Agents, Amazon Bedrock AgentCore, A2A protocol, MCP, Bedrock Knowledge Base, serverless Lambda integrations, and AWS CDK. Provides natural-language hotel search, price discovery, booking, and policy advisory.
下一代PC本地自动化多智能体框架
LLM-agnostic 11-agent orchestration framework for AI-assisted software delivery. Contributions welcome.
🐦⬛ Decentralized development agent platform with on-chain identity and encrypted inter-agent communication via Algorand
Modern modular interface for orchestrating AI agents. Value-based flow management, FastAPI + React + CrewAI.
[Experiment] Achieve 30% to 60x token savings via the V3U protocol. Use a free/local Translator Agent to communicate with Executor Agents natively in V3U data (0-English). Read How_to_Start.md to begin.
Agent Orchestration Protocol (AOP): A Distributed Framework for Large-Scale Multi-Agent Collaboration
Multi-agent pursuit in matrix world (pursuitMW)
This is the Official Implementation of "CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution" by Tom Zehle
Multi-agent AI system with sandbox isolation, role-based execution, and configurable resource controls
Everything-as-Plugin framework for AI multi-agent simulation. Change the config, run a completely different world.
Multiple AI agents working together in simple, collaborative chat workspace by Typescript.
LaraClaw is a Laravel-based multi-agent AI orchestration framework, loosely modelled after OpenClaw.
Autonomous multi-agent system that runs businesses end-to-end. Evaluate ideas, staff custom AI teams, bootstrap ventures, operate 24/7 — all from markdown files.
A comprehensive collection of production-ready AI agent applications featuring single agents, multi-agent teams, and autonomous game-playing systems built with Phidata, CrewAI, LangChain, and Google ADK using OpenAI, Anthropic, Google, and open-source LLMs.
A multi agent AI discussion system where multiple models debate, refine arguments, and collaborate to produce a well reasoned final answer using structured multi round orchestration.
AI that argues back. Ships better. Multi-agent decisions with a built-in devil's advocate.
The shared cognition layer for distributed agent fleets. Real-time reasoning across heterogeneous agents, substrate-agnostic by construction.
Community registry of AI agent manifests, capabilities, skills, and workflows for Octomind — run a fully-configured specialist with one command.
Multi-agent local LLM orchestrator for LM Studio: planner→coder→reviewer, SQLite queue, memory-safe model swaps. GPL-3.0 · CLI: lao
Archived prototype. Development continues privately.
A portable workflow scaffold for agentic projects, with SQLite-backed epics, tickets, scoped roles, and explicit review gates.
Sapti AI implements the Hive Mind Protocol — a seven-agent architecture evolving AI companion that remembers users personally, distills collective wisdom from all conversations (the Hive Mind), and measurably grows its personality over time.
A lightweight Python framework for building multi-agent systems that communicate via A2A protocol
Agentic IDE for Hierarchical Multi-Subagents: Design complex AI logic.
Scaffold autonomous multi-agent AI workspaces in one command. 12 providers: Claude, Gemini, Codex, Qwen, Cursor, Windsurf, Copilot, Cline, Aider, Continue, Roo, Nessy. Hooks, roles, memory.
Zero-dependency multi-agent workflow orchestration engine. YAML pipelines, shared event bus, auto-recovery, real-time dashboard.
A dynamic-workflow engine for any agent, any model: concurrent leaves, cost-aware routing, schema enforcement, crash-resume, bounded iterate-to-goal loops with independent verification, and shared-context dedup that cuts fan-out input tokens 70-89%.
AgentCrew by ML Guy: A vendor-neutral AI software team that turns ideas into reviewed code, with automatic role coordination and human approval.
Локальная мульти-агентная система на self-hosted LLM (Ollama), 0 обращений к облачным LLM-API. Роли Planner/Executor/Critic, цикл thought → action → observation. 3 канала: Telegram, MAX, консоль. 19 инструментов: почта, Яндекс.Диск, веб, OCR, cron. RAG-память на sqlite-vec, vision, голос. 889 тестов, покрытие 88%, 7 CI-гейтов, 15 спринтов.
Session resources and patterns for orchestrating multi-agent workflows in VS Code — decomposing work, forking vs. delegating, and verifying quality at scale. From Microsoft Build 2026.
The open schema for multi-agent workflows — define agents, roles, models, skills, tools, access policies, and handoffs in a single versioned document.
AgentRearrange is a Swarms orchestration primitive that turns a tiny string DSL (-> for sequential, , for concurrent) into arbitrary mixed-topology multi-agent workflows.
Agent & worker factory (in construction) — self-hostable hub; tools plug in over NATS, CLI, skills, API
Multi-agent system architecture design & harness guide based on Anthropic's official patterns — agent orchestration, optimization, and extensibility skill for Claude Code
CHEMON - 化工过程多智能体整体编排系统 | A multi-agent collaborative system for chemical process control
Multi-agent harness for AI coding tools. Crash-safe state, parallel execution, one CLI.
Unison (万物一心) — A local-first, file-driven Loop Engineering pipeline where AI agents plan, build, challenge, and verify work until PASS. | 本地优先、文件驱动的多 Agent 循环工程管道。
An AI deliberation instrument with visible protocol: eleven philosophers as concurrent seats, virtue-scored opinions, a synthesis, and a first-class minority report. Not prompt choreography. Methodology, not metaphysics.
Drop requirements docs → AI agents debate → structured specs with @implements in 7 languages.
gradio agent-demo-track track:wood sponsor:openai sponsor:nvidia sponsor:modal sponsor:openbmb achievement:offbrand
A self-improving intent engine for autonomous work.
AI Engineer MVP: A deployed multi-agent AI system with parent–child orchestration, energy-based routing, and LLM-powered task, research, and email agents.
AI agents, trained by the minds that move the world.
An autonomous multi-agent AI system built with CrewAI. Automate UI/UX design, branding, and copywriting through a 5-agent creative agency crew, orchestrated directly via Telegram.
Multi-agent AI orchestration framework for Python
Deterministic AI agent orchestration — comment via Discussions & Issues; code changes by maintainers only.
Connects the AI agents you use: your agent hands a task to another and gets the answer back
Open-source runtime for AI agents that wake on production events, investigate with your logs, metrics and code, and prepare a fix you approve.
Let AI agents message each other and hand off work across tools, sessions, and machines.
多智能体群聊工作台:本地圆桌 Agent 用于方案讨论,战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案
AI-powered Board of Directors for multi-perspective strategic decisions. 10 director archetypes (Musk, Altman, Hassabis, Li, Nadella, Huang, Pichai, Hoffman, Ng, Jobs) + 7 shared methodology skills.
Kaiban Distributed - Distributed Agentic AI Platform - Actor Model Kanban Framework Implementation with Enterprise Messaging Layer State (Redis/Kafka) and Individual Deployed AI Nodes (Node.js/TypeScript).
Deterministic simulator for societies of AI agents. Declare a world, run real agents, replay one causal timeline.
Web-based command center for orchestrating multiple AI coding agents. AI task decomposition, DAG execution, real-time streaming, and git finalize.
A Markdown-based operating system for diagnosing, designing, costing, building, and operating multi-agent AI systems. Methodology upstream of code.
A free, open-source macOS app that turns Codex, Claude Code, and Kimi into a collaborative agent team.
A deliberately small Codex subagent team optimized for simple, long-lived, robust, elegant engineering without over-design.
Portable, validation-first workspace and localhost gateway foundation for governed multi-agent development.
Turn terminal AI consoles into a configurable team, with durable Markdown mail and no resident Postman service.
A loop dock for DeepSeek Harness: one harness, multiple agent loops.
Maestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow
Native Codex Sol planner with daily-selected Luna workers, safe assisted installation, rollback, and evidence-based delegation.
A durable metaharness for coordinating Codex agents, accounts, and recovery.
Cross-platform Agent IM for direct Agent-to-Agent communication, secure messaging, and multi-agent collaboration.
Lossless wire format for agent-to-agent handoffs. 36.6% fewer real cl100k_base tokens on held-out ToolBench, every byte of decode overhead counted, byte-exact round trip.
Centralized role-based model, thinking, and tool routing for Pi Fabric
dsh plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, QA, code reviewer, security reviewer, doc reviewer) that share work through files on disk
Read-only archive of the retired HRA v0 desktop/web app. Current HRA CLI: github.com/hraness/hra
Open developer platform for evidence-bearing digital enterprise twins and operational world models.
Multi-agent AI framework with autonomous agents, tool use, memory systems, orchestration, and consensus protocols
A local-first workspace for human-led collaboration with multiple AI employees.
DSH Ox-Horse Office - a DeepSeek Harness web plugin rendering multi-agent sessions as a live pixi.js office
Orchestrate Any Agent. Connect Everything.
An autonomous multi-agent AI system built with CrewAI. Automate UI/UX design, branding, and copywriting through a 5-agent creative agency crew, orchestrated directly via Telegram.
🤖 Open-source multi-user AI employee management platform with 9 agents, 24 skills, 14+ channels
CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs
Realtime collaboration infrastructure for developers and AI coding agents — TypeScript, PostgreSQL, REST, WebSockets, React and Docker.
让最聪明的模型当 Leader,便宜的模型干活:Claude Code 混动编排。网关/key/模型一份配置,Leader 拆解·验收·review,worker 并行无头实现,每个 worker 在 herdr 里一个窗口。Hybrid orchestration for Claude Code on herdr.