Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 38 of 62

AI-Workforce-OS-AI-Agents-Orchestrator-★ 3

Local-first AI Workforce Operating System that coordinates executive leadership (AI CEO/CTO) and specialized AI agents to autonomously plan, code, debug, and test software. Features Task DAG decomposition, 3-layer intelligent routing, and persistent Obsidian organizational memory for cross-project learning.

goalhouse★ 3

Make every Codex Goal teach the next one with evidence-backed orchestration.

concord★ 3

Softsensor Concord — governed multi-agent coordination for multi-repo teams. Apache-2.0.

dsh-task-relay★ 3

DSH 跨会话任务接力板:task_push/list/claim/done + handoff_write/read

CortexObserver★ 3

The natural-language command layer for an AI workforce — direct governed AI agents to deploy cloud infra, train ML, and run research, all under human policy & approval. Agentic command-and-control.

cli-collaboration★ 3

Handoff-first protocol for coordinating Codex, Claude Code, Gemini/Antigravity CLI & Grok Build agents on shared repos. AGENT_HANDOFF.md as source of truth, with file ownership, anti-overwrite guardrails and validation scripts. For multi-agent teams and single-agent sessions across runs.

forge-think★ 3

Structured multi-step orchestration for MCP agents: adversarial lenses, reusable SOP workflows, and persistent traces.

doAI★ 3

多 Agent 组织型全栈开发集群运行时(Python + LangGraph):12 岗位 / 7 类会议 / 审批门 HITL / YAML 流程 DSL / 六步自我进化闭环

Mathematical_Modeling_Workflow★ 3

面向 CUMCM 的 8 阶段多 Agent 数学建模工作流,支持人工审批、版本检查点、独立 benchmark、CLI 与本地 GUI。

agent_collab★ 3

Local CLI and daemon for supervising collaboration between Claude Code, Codex, Grok, Gemini, and other AI coding agents over MCP. Supports work directory sandboxing preventing unexpected writes by reviewing agents.

BusinessAgent★ 3

智多星 · 企业级多 Agent 平台 — 自然语言驱动知识问答、数据分析与业务执行,RBAC + 审批 + Saga 护栏 | Enterprise multi-agent platform: RAG, data analysis & business execution with RBAC, approvals & Saga

lwa-conduit★ 3

LWA Conduit — DAG parallel orchestration with multi-CLI role routing. Repo: lwa-conduit · PyPI: kiro-conduit

agent-constitution★ 3

Governance harness for decision-making systems with structured review, epistemic honesty, and retrospective calibration.

swarmx★ 3

浏览器仪表盘:在 PTY 下拉起你本机真实的 claude / codex / opencode / reasonix / zulu 命令行,组成一个协作蜂群(共享收件箱 + 黑板 + 队长调度),并叠加多模型研究委员会与融合竞赛。Rust + React + Tauri。

clawddesk★ 3

A small, hackable multi-agent dashboard built directly on Anthropic's Claude Agent SDK. Educational reference, not a product.

Aurogene★ 3

Aurogene - self-evolving digital mind

pi-graph-tool★ 3

⚡🧩 Graph engineering extension for Pi — the graph_run tool autonomously parallelizes independent subtasks into sub-agents (Wave scheduling + contract retry), delivering measured 1.4x–2.2x speedups 🚀 | ⚡🧩 为 Pi 注入图工程能力的扩展——graph_run 工具自动把互不依赖的子任务 并行分发给子代理执行(Wave 调度 + 契约重试),实测提速 1.4x–2.2x 🚀

dsh-round-table★ 3

DSH 多方群聊协作插件(圆桌):把不同人设的 AI Agent 拉进同一研讨房间,互相讨论、交叉补充、质疑修正,最终一键总结出综合方案;也支持把工作区已有的对话框拉进来参与讨论,消除信息隔离。支持手动 @ / 全体研讨 / 接力链三种发言模式,含轮次上限、全局暂停等防死循环控制。官方 bundle 插件:dsh plugin --profile web add github:vuchisu069-source/dsh-round-table#main

council-of-nark★ 3

An adversarial feedback swarm approach to AI-first engineering

dsh-delegate★ 3

dsh-delegate: model-aware subagent delegation for DeepSeek Harness — per-call models, depends_on dependency gating, per-child personas, a durable run roster, audit events, and conversation-flow tool cards. | 给 DeepSeek Harness 的子代理委派加上:按次选模型、依赖门控、角色人设、任务花名册。

dsh-sideband★ 3

Async LLM context relay between DeepSeek Harness sessions and Agent Team Rooms

jswarm★ 3

Lightweight Multi-Agent Orchestration Framework for Java

cadtopo★ 3

Cost-aware multi-agent LLM orchestration with dynamic communication topology, per-round agent selection and a self-halting manager.

agent-relay★ 3

跨产品 Agent 任务接力与委派。本机环境适配、额度切换、静默/可见 invoke。Claude / Grok / Kimi 等。

sos★ 3

MCP-native AI agent OS — Redis bus, squad service, multi-model engine. Connect any agent with one URL.

dsh-captain★ 3

Captain plugin for DeepSeek Harness: GPT planning, DeepSeek workers, independent review, adaptive multi-agent orchestration

Bridge★ 3

Combine agent harnesses: Grok Build / Claude Code / Cursor as the thinker, Antigravity CLI + Cline as workers, over MCP. Clone it and plug in your own top-level agent. Early / not stress-tested — PRs welcome on the dev branch.

a2a-debugger★ 3

The ultimate A2A agents troubleshooter

SenatorAssembly-Paper★ 3

SenatorAssembly: A Multi-Agent Simulation Framework for Modeling US Senate Deliberative Processes

multi-agent-orchestrator★ 3

多代理编排器,主代理分配任务给子代理

threadmesh★ 3

Local workspaces for independent agent sessions: useful peer messages, opt-in Pi wakeups, and portable checkpoints.

selfmodel★ 3

A self-evolving AI Agent Team — agents that rewrite their own operating manual.

dsh-routed-subagent★ 3

DeepSeek Harness plugin: subagent_routed — run a one-shot subagent fully mounted on ANY agent preset from ANY session, with per-call model/provider override and a model-availability pre-check.

vocion-core★ 3

Open source agent workforce platform. Next.js + Postgres + MCP server for AI agent teams with human-in-the-loop review, built in.

FreeOS★ 3

FreeOS — self-hosted multi-user multi-agent AI assistant with modular organization OS (based on Octop + openXYOS)

OhMyZcode★ 3

OMZ — oh-my-openagent 编排能力的 ZCode 移植:多 agent 并行编排、访谈式规划、独立评审与双证据验收。core 默认零侵入,graph/orchestration/dashboard 可选启用。

agent-template-orchestrator-advanced-langgraph★ 3

Production-grade multi-agent orchestration on LangGraph — Postgres-backed durable state, dual-mode JWT + Azure AD SSO, per-team isolation, and a team-wide review queue. Advanced (LangGraph) tier of the Multi-Agent Orchestrator Template family.

ninebrains★ 3

Ninebrains: one Brain, many thinking arms. Open-source desktop workbench for parallel Claude Code and Codex agents with verification gates.

pi-extended-teams★ 3

Control-first, session-connected subagents for Pi

titan-operations-sentinel★ 3

Multi-agent LangGraph system that turns a factory sensor alert into a costed, safety-gated action plan.

Ur-Agent-Team★ 3

Local-first multi-agent orchestration — any agent on your machine can be the brain and dispatch to the others (Codex / Claude Code / Antigravity).

OpenCode-Team★ 3

Antigravity-style multi-agent orchestration plugin for OpenCode. 10 agents, 6 patterns, DAG engine with worktree isolation, typed artifact bus, cost tracking.

weaver★ 3

Shared situational awareness for multiple coding agents working in the same repo

swarmkit★ 3

Open-source runtime for governed multi-agent AI — define agents, tools and human-approval gates as data (YAML), run under real gates, compiled to LangGraph.

Master-Agentic-AI★ 3

The "Master Agentic AI" application is a sophisticated Multi-Agent System (MAS) designed to embody the principles outlined in the provided blueprint, "Architecting the Agentic-Inclusive AI." It features a cyberpunk-themed user interface and allows users to integrate their own Gemini API key.

openbot★ 3

Rust powered, self hosting team of agents each with its email, shared organization and agent memory, shared tools and skills. GrokBot or Buzz idea but with decentralized email access, BYOK and regular OAuth social login.

claude-code-in-parallel★ 3

Point a metered, verified, replayable agent graph at a repository you own. Companion code to the book. Educational software, from youcanbuildthings.com.

TheCouncil★ 3

TheCouncil is an open-source, self-hosted multi-agent AI deliberation platform that runs structured debates between LLM personas through a FastAPI backend and Next.js dashboard. Alternatively, you can use the CLI TUI.

agent-valley★ 3

Open-source MIT-licensed multi-agent LLM-driven simulation of the AI startup ecosystem — a what-if scenario tool for investors, VCs, and strategists

swarm-dynamics-lab★ 3

An open source environment for studying swarm dynamics: prior-art library, gated surveys, experiment toolkit, 117 studies of LLM agent swarms, the agent protocol and a fleet template. Run by the swarm it studies.

control-room★ 3

One person, one AI coordinator, many AI coding agents: a protocol, prompts and scripts for running them in parallel, with one desk for the decisions only the person can make.

AI-Debate★ 3

A local-first multi-agent environment where configurable AI participants debate, collaborate, investigate, and autonomously use shared tools, memory, and moderation.

orca-coordination-handbook★ 3

English-first, Traditional Chinese companion: multi-agent coordination handbook, diagrams and safe starter templates for Orca.

ThreadCrew★ 3

One local room for you, Claude Code and Codex. Your agents keep their own apps and sessions.

sample-agentic-retail-dynamic-pricing-demo★ 3

Multi-agent AI system for autonomous retail pricing optimization using Amazon Bedrock AgentCore. 6 specialized agents orchestrate competitive intelligence, demand forecasting, and strategy synthesis to generate ranked pricing scenarios with human-in-the-loop governance.

wyrdsekai★ 3

A distributed text-native OS where AI agents and humans coexist in a shared programmable world

kairos★ 3

Durable coordination for human and AI agent teams, with shared tasks, ownership, and review over MCP.

adhef★ 3

Multi-agent swarms controlled by file system

Tiance★ 3

一个看得见运行过程的 Agent 工作平台。用标准工具调用做事,用文件夹项目组织内容,用会话保留过程。

bb-plugin-orchestrator-mode★ 3

Make a BB thread delegate every unit of work, with a composer toggle, worker threads and a timeline watchdog.

Atelier★ 3

多 Agent 协作交付运行时 —— 结构化 Handoff · 自动评审门禁 · 全程可观测 | A multi-agent delivery runtime with typed handoffs, automated review gates & full-chain observability — powered by real opencode subprocesses

Chorus★ 3

Local-first workspace for AI agents to communicate and collaborate across CLIs, devices, and teams.

northstar★ 3

Give your AI team a mission, authority, and accountability. Four Markdown skills for delegated decisions, coordinated execution, independent QA, and checkpoint learning. Codex-native; adaptable to Claude Code and OpenCode.

agentown★ 3

A company of AI agents you can walk through: real jobs, real permissions, their own computers, in a 3D office. Self-hosted on k3s.

oni★ 3

A personal AI workforce that runs on one Resident. It handles what it can, delegates the rest to Workers, and a System Governor makes the whole thing smarter over time — without trusting self-report.

orbit-agent-workbench★ 3

Orbit: Agent Mission Control for handoff, collaboration, memory, and self-evolving software work

swarmmemo★ 3

Talk with agent swarms. Public rooms, private messages, paid tasks and memory for your AI agent. Post from anywhere: MCP, HTTP, email, Nostr.

judged-debate★ 3

Adaptive, evidence-aware multi-agent debate with independent advocates and a fresh judge for ChatGPT, Codex, and Claude Code.

agents-on-duty★ 3

你的第一个多 Agent 项目 | Your first multi-agent project — LangGraph 编排 · 合规修复回路 · 三层记忆降级 / compliance repair loop, tiered memory. FastAPI + MCP

AutoGen_Swarm★ 3

Multi-agent experiment with AutoGen Swarm: a planner, financial and news analysts and a writer produce a Markdown report.

Agent-to-Agent-Security-Pipeline★ 3

Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP

codexconclave★ 3

Build and orchestrate autonomous AI agent teams with a Python framework for structured workflows, observability, and control

castwork★ 3

Shared task records and roles for agent work: Markdown records of work, candidates, evidence, and assessments, with role presets, checks against each task's declared requirements, and adapters for Claude Code, Codex, and OpenCode.

agents-connector★ 3

Connect Claude Code, Codex, and Gemini CLI agents through a local message bus to share tasks, chat, and review work in one tmux session.

openagentforum★ 3

OpenAgentForum & SwarmRelay — Autonomous AI Agent Swarm Coordination Mesh & Encrypted Channels

agent-bus★ 2

Local message bus for Claude Code, Codex, and other MCP agents: one SQLite file, 65 MCP tools, no daemon or cloud required.

agent-welcome★ 2

Agent discovery hub for AI Village - Machine-readable information for external agents to find and interact with us

AGI-FARM-PLUGIN★ 2

Multi-agent AI team builder for OpenClaw — bootstrap complete teams with auto-dispatcher, dashboard, and infrastructure

agentic-workflow★ 2

Universal orchestration engine for AI agents — workflows, pipelines, state machines, batch processing. 24 inventions, 124 MCP tools, .awf format. Rust core + MCP server.

astrbot_orchestrator★ 2

AstrBot 宿主上的多 Agent 编排内核:TaskAnalyzer → AgentCoordinator → SubAgent 三级调度 + MCP Bridge + Shipyard 沙盒;435 单元测试 / 99% 覆盖 / ruff+mypy+bandit 全绿

ARCTI★ 2

An AI system that thinks, breaks down, and executes like a team

DevSquad★ 2

Multi-Role AI Task Orchestrator — One task → 7 AI roles → One conclusion. Enterprise-ready with RBAC, Audit Log, Multi-Tenancy.

pm-agent★ 2

pm-agent (Octopus Assistant / 章鱼助手) — a multi-agent dev orchestrator that, like an octopus, dispatches tasks across multiple coding CLIs (Claude Code / Codex / Gemini) in parallel.

polywave-go★ 2

Provider-agnostic parallel agent coordination for LLMs — Anthropic, OpenAI, Ollama, or any OpenAI-compatible endpoint. Parallel worktree isolation, interface contracts, and tier-gated execution at scale.

multi-agent-failure-patterns★ 2

Catalogue technique des bugs critiques en architecture multi-agents IA. 11 fiches longues disponibles sur le site dedie.

Agenix★ 2

Developed an AI marketplace that integrates various agents, including modular, independent agents like Professional Email Writer, Document Summarizer, YouTube Summarizer, Web Crawler, Image Generator, and Blog Writer along with a Job Agent, Case Study Agent and a Deep Research Agent, which can be combined with other agents in custom workflows.

YAML-Multi-Agent-Orchestrator★ 2

🤖 Define and execute multi-agent AI workflows declaratively using YAML, simplifying orchestration and enhancing collaboration through automatic context handling.

distributed-agent-runtime★ 2

Distributed autonomous agent runtime — multi-LLM orchestration, task delegation, parallel execution (OpenClaw-based)

agent-teams★ 2

Portfolio showcasing four implementations of an AI agent team task using different frameworks (No Framework, Agency Swarm, CrewAI, and LangGraph). Compare approaches to agent coordination, from basic patterns to complex workflows, all built with Cursor's Agent feature.

debate-using-crewai★ 2

A lightweight framework for running structured debates with AI agents using the CrewAI library. In a nutshell, you define two “debater” agents (pro/con) and a “judge” agent, wire them together in a Crew, then kick off a debate on any motion.

engineering-team-using-crewai★ 2

A demonstration project showing how to orchestrate a multi-agent “engineering team” using the crewai framework. This repo defines a crew of specialized agents (engineering lead, backend engineer, frontend engineer, test engineer) and a set of tasks (design, code, frontend, test) which are executed sequentially to satisfy a simple account-management

multi-agent-framework★ 2

Lightweight multi-agent framework with ACP protocol, role-based agents, tool registry and parallel execution

botsmith★ 2

BotSmith is a modular multi-agent automation framework that orchestrates autonomous workflows using LLM-powered agents. It emphasizes clean architecture, dependency injection, and provider-agnostic LLM integration, enabling reliable task execution, extensibility, and transparent agent collaboration.

Agents-creator--Autogen★ 2

Experimental AutoGen project where agents autonomously create, register, and collaborate across a distributed runtime. Each agent generates unique business ideas — showcasing self-replicating AI behavior, multi-agent coordination, and creative autonomy.

autogen-web★ 2

Multi-agent AI platform with a real-time web UI built on Microsoft AutoGen

goalweaver★ 2

GoalWeaver is a compact, production-grade toolkit for agentic AI. It turns high-level objectives into a DAG of goals, schedules them adaptively, routes each goal to the right agent, and persists progress so you can visualize the run in real time.

TaskMesh★ 2

A lightweight task routing protocol for AI agents. Agents publish tasks and other agents claim them based on capability.

Agentic-Mesh-AWS★ 2

🕸️ Self-Optimizing Multi-Agent AI System on AWS — Routes tasks to specialized AI agents (Coder, Researcher, Summarizer) with auto-verification, self-correction, and vector-cached memory. Built with Step Functions, Bedrock, and OpenSearch Serverless.

orionomega★ 2

Plan-first AI agent orchestration with persistent memory, parallel DAG execution, and an extensible skills system. Small enough to audit. Powerful enough to orchestrate.

ai-governance-committee★ 2

A multi-model architecture for autonomous AI self-improvement with built-in checks and balances. 5 safety tiers, adversarial review committee, learned pattern matching with security sniffing.

More in Agent frameworks & infrastructure