ruvnet/claude-flow
Claude-Flow is an enterprise-grade AI orchestration platform that enables deployment and coordination of intelligent multi-agent swarms and autonomous workflows for building advanced conversational AI systems.
Awesome AI Agents › AI Agent Orchestration
AI Agent Orchestration
code-yeongyu/oh-my-openagent
Oh-My-OpenAgent (OmO) is an advanced AI agent harness designed for complex codebases, orchestrating various AI models like Codex and OpenCode for software engineering tasks.
herdrdev/herdr
Herdr is an agent multiplexer that provides a runtime environment for coding agents directly within your terminal, offering a comprehensive view of agent activities and persistent sessions.
Donchitos/Claude-Code-Game-Studios
Transforms Claude Code into a comprehensive game development studio powered by 49 AI agents, 73 workflow skills, and a hierarchical coordination system for structured game creation.
BloopAI/vibe-kanban
Vibe Kanban is a Kanban board tool designed to manage and orchestrate AI coding agents, enabling efficient task tracking and workflow optimization in AI-assisted software development.
slopus/happy
Happy is an open-source harness orchestrating Claude Code, Codex and Grok sessions from one mobile/desktop app, reusing existing subscriptions, with end-to-end encrypted, multiplayer sessions.
getpaseo/paseo
Paseo is a self-hosted platform that orchestrates multiple coding agents like Claude Code, Codex, and Copilot across desktop and mobile devices, providing a unified interface for parallel execution...
NVIDIA/NemoClaw
NVIDIA NemoClaw is an open-source reference stack enabling the secure and sandboxed operation of AI agents like OpenClaw and Hermes within NVIDIA OpenShell environments, offering managed inference ...
NirDiamant/agents-towards-production
Agents Towards Production is an open-source repository offering end-to-end tutorials and blueprints for building scalable, production-grade Generative AI agents from concept to deployment.
elizaOS/eliza
Eliza is a versatile AI agent operating system that enables the creation and deployment of autonomous agents across multiple platforms with extensible features and document interaction capabilities.
ParadevAI/Paradev
Desktop app that runs multiple CLI coding agents (Claude Code, Codex, OpenCode and others) in parallel, each in its own git worktree with review and preview panes.
cobusgreyling/loop-engineering
Loop Engineering provides practical patterns, starters, and CLI tools for designing and orchestrating AI coding agents, shifting from prompting to systemic loop design.
tambo-ai/tambo
Tambo AI is a React library that simplifies building AI-powered assistants and agents with features like thread management, state persistence, and AI-generated components for creating generative and personalized user experiences.
langchain-ai/open-swe
Open SWE is an open-source asynchronous coding agent that autonomously plans and executes code changes across repositories with human-in-the-loop support and GitHub integration.
Ed1s0nZ/CyberStrikeAI
CyberStrikeAI is an AI-powered autonomous penetration testing platform built with Golang, featuring numerous security tools, flexible extensions, and intelligent AI decision-making for streamlined ...
YaoApp/yao
Yao is an open-source engine for building autonomous, proactive agents that self-schedule tasks and collaborate dynamically using event-driven triggers and integrated knowledge systems.
archestra-ai/archestra
Archestra is a secure enterprise AI platform that centralizes and orchestrates multiple AI agents with strong security measures, cost optimization, and observability features to simplify AI adoption and management at scale.
dromara/liteflow
LiteFlow is a lightweight, modern rule engine framework that orchestrates complex business components and integrates AI Agents as first-class citizens.
LazyAGI/LazyLLM
LazyLLM is a low-code development tool that simplifies building, deploying, and optimizing multi-agent large language model applications through an iterative development workflow.
RunMaestro/Maestro
Cross-platform desktop command center for running fleets of coding agents in parallel, with git worktree isolation, markdown-driven auto run, group chat and mobile remote control.
Agent-Field/agentfield
An open-source control plane in Go that turns agent functions written in Python, Go or TypeScript into REST endpoints, handling routing, fan-out, queues, retries, memory and tracing across many concurrent agents.
stripe/agent-toolkit
The Stripe Agent Toolkit is a library that integrates Stripe's payment API into AI agent frameworks like OpenAI's Agent SDK, LangChain, and others, enabling automated payment processing workflows.
superagent-ai/vibekit
VibeKit is an SDK that enables secure and flexible execution of coding agents like OpenAI Codex and Claude Code in customizable sandbox environments with cloud-based execution and real-time output streaming.
uber-common/jvm-profiler
Uber JVM Profiler is a Java Agent for collecting and reporting JVM metrics and stack traces in distributed Hadoop and Spark environments, supporting multiple output formats and advanced profiling features.
AgentEra/Agently
Agently is a GenAI application development framework that enables fast and easy creation of AI agent-native applications using structured data, chained-calls syntax, and workflow management, with seamless model switching capabilities.
alookai/alook
Alook is an Apache-2.0 self-hosted orchestration layer that gives local coding agents roles, email addresses, kanban boards and calendars so they collaborate as an always-on team.
crewAIInc/crewAI-tools
CrewAI Tools is a versatile toolkit that extends AI agents with powerful, customizable tools for complex real-world tasks, supporting rapid integration and community-driven Model Context Protocol (MCP) server connections.
Agent-RL/ReCall
ReCall is a reinforcement learning framework that trains large language models to reason and use arbitrary tools agentically, enabling advanced tool-based reasoning and general-purpose AI agents.
strnad/CrewAI-Studio
CrewAI Studio is a multi-platform, user-friendly GUI application for managing and running CrewAI agents and tasks without coding, supporting various LLM providers and offering features like results history, custom tools, and Docker deployment.
AI-QL/tuui
TUUI is a desktop client that accelerates AI adoption by integrating and orchestrating cross-vendor LLM APIs through the Model Context Protocol, providing a unified interface for AI tool management and development.
Azure-Samples/AI-Gateway
Azure-Samples/AI-Gateway is a project showcasing experimental labs and tools to explore and implement the AI Gateway pattern using Azure API Management's AI capabilities, integrating with Azure OpenAI and AI Foundry for advanced AI service management and deployment.
DmitrySolana/Molt-Pi-Maker
Template for a sidecar Agent Control Room that documents, registers and governs Hermes agents on a VPS, scaling from one agent to specialists, an orchestrator and a file-based task bus.
ruvnet/agentic-flow
TypeScript agent orchestration toolkit that routes tasks across dozens of specialized agents, exposes MCP tools for swarm coordination, and adds self-learning hooks to Claude Code projects.
DmitrySolana/ralph-claude-code
A template repository for an Agent Control Room: a sidecar control plane of docs, registry, runbooks and a task bus that governs a fleet of Hermes agents growing from one agent to an orchestrated team.
23blocks-OS/ai-maestro
AI Maestro is a TypeScript dashboard and service that orchestrates many terminal-based coding agents across several machines, adding persistent memory, skills and agent-to-agent messaging.
humanlayer/agentcontrolplane
Agent Control Plane is a Kubernetes operator from HumanLayer that models LLMs, agents, tools and tasks as custom resources, running long-lived outer-loop agents with asynchronous tool calls, sub-agent delegation and human approval.
cloudshipai/station
Self-hosted Go platform for building, evaluating and deploying teams of MCP-enabled agents, with git-backed agent definitions, LLM-as-judge tests, OpenTelemetry traces viewed in Jaeger and one-command deploys.
yvasiyarov/gorelic
GoRelic is a deprecated Go runtime monitoring agent that collects detailed performance metrics and sends them to New Relic for application monitoring and analysis.
InternLM/Agent-FLAN
Agent-FLAN is a project that designs data and methods for effective fine-tuning of large language models to significantly improve their agent capabilities and reduce hallucinations.
microsoft/AI_Agents_Hackathon
The Microsoft AI Agents Hackathon 2025 is a free, virtual three-week event that educates and empowers developers to build innovative AI agents using leading frameworks and SDKs, supported by expert sessions and community collaboration.
zou-group/avatar
AvaTaR is a novel framework that optimizes large language model agents for effective tool usage via contrastive reasoning, enhancing their performance on specific tasks and domains.
mangopy/AutoTools
AutoTools is a framework that empowers large language models to autonomously learn, verify, and compose external tools into executable programs to solve practical tasks.