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
humanlayer/agentcontrolplane
Agent Control Plane, or ACP, is a cloud-native orchestrator for LLM agents implemented as a Kubernetes operator in Go. It is designed for long-lived outer-loop agents whose work is asynchronous: both model inference and tool calls may take a long time, may involve waiting on a person, or may be delegated to another agent, and the platform is responsible for durably tracking that state rather than holding it in a single process. The design follows the twelve-factor agents principles published by the same authors. Everything is expressed as custom resources applied with kubectl. An LLM resource names a provider, model parameters and an API key pulled from a Kubernetes secret, and its controller validates the credentials and reports readiness in the resource status. An Agent resource combines a reference to an LLM with a system prompt and a set of tools, where a tool can be an MCP server, another agent or a human. A Task resource pairs an agent with a user message and carries the current context window, and each individual ToolCall that occurs during a task becomes its own resource, so the whole run is inspectable through ordinary Kubernetes tooling and event streams. Human approval is a first-class step: a task can pause on a tool call until a person approves it, and humans can also be exposed to the agent as callable tools, which is the HumanLayer product angle. Providers other than OpenAI, including Anthropic, are supported through the same LLM resource. Installation is a single manifest apply, with a CRD-only variant and pinned version manifests available, and the documentation walks through a local kind cluster. The project is Apache-2.0 licensed and marked alpha. It suits platform teams that already run Kubernetes and want durable agent execution under existing operational tooling.
https://github.com/humanlayer/agentcontrolplane
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.