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
RunMaestro/Maestro
Maestro is a cross-platform desktop application for orchestrating many AI coding agents and projects at once, aimed at users who work primarily from the keyboard and juggle parallel workstreams. It acts as a pass-through to the underlying provider, so whatever MCP tools, skills, permissions and authentication are already configured in the backing CLI apply unchanged; the difference is that Maestro drives them non-interactively, sending a prompt per task and collecting a response in a new or resumed session. Supported backends are Claude Code, OpenAI Codex, OpenCode, Factory Droid and Copilot CLI in beta, with additional agentic coding tools planned. The intended workflow is to collaborate with an agent on a detailed specification document and then let Auto Run execute it automatically, giving every task a fresh session with clean context so unattended runs can last many hours. Auto Run and Playbooks form a file-system-based task runner that batch-processes markdown checklists, can loop, and keeps full history. Git worktrees let sub-agents work on isolated branches in their own directories while the main repository stays interactive, with one-click pull request creation. Group Chat coordinates several agents in one conversation through a moderator agent that routes questions and synthesises answers. A built-in web server with QR code access provides mobile monitoring over the local network or a Cloudflare tunnel, and maestro-cli supports headless operation from cron or CI with human-readable or JSONL output. Each agent has both an AI terminal and a command terminal, plus message queueing, session discovery and import from existing provider histories, git diff and commit views, a file explorer with @ mentions, output filtering, slash commands, themes, cost and token tracking, and a usage dashboard with activity heatmaps and CSV export.
https://github.com/RunMaestro/Maestro
Also in 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.
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.
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.
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.