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
AgentsMesh/AgentsMesh
AgentsMesh is a control layer for running a large number of AI coding agents at once and directing them from a single console. It targets the practical walls that appear when scaling past a few agents: machine capacity, workspace isolation, supervision, long runs that stall silently, and the lack of collaboration between agents working alone. The unit of execution is an AgentPod, an isolated environment holding a PTY terminal, a Git worktree sandbox and a real-time output stream. Runners are self-hosted daemons installed on operator-controlled machines; each advertises its capacity through a max concurrent pods setting, connects to the backend over gRPC with mTLS, and receives pods scheduled onto a chosen runner or one drawn from the pool, so code never leaves operator-controlled infrastructure. Every pod gets a dedicated sandbox directory, private credentials and its own branch so concurrent agents do not collide. Autopilot is a control agent that watches a pod and sends the next instruction as soon as it goes idle, bounded by iteration caps and recorded as decision history, with human takeover and handback at any point. Mesh and Channels bind pods into a topology so they can address each other with mentions while the collaboration graph updates in real time, and Tickets track units of work on a Kanban board bound to pods with progress and merge-request tracking. The architecture splits control plane from data plane: orchestration travels over gRPC with mTLS while terminal bytes stream through a stateless Relay cluster, keeping PTY traffic off the backend. Server components are written in Go as an API backend on Gin and GORM, the Relay and the Runner. Clients share a Rust core of ten crates compiled to WebAssembly for web and desktop and to a native library through UniFFI for iOS, driving a Next.js console, an Electron desktop app and a SwiftUI client, plus an internal admin console. Licensed BSL-1.1, with a hosted service and bring-your-own-key model.
https://github.com/AgentsMesh/AgentsMesh
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.