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
cloudshipai/station
Station is a self-hosted orchestration platform for multi-agent systems, installed as the stn command-line tool and written in Go. It treats agents as versioned artefacts: agent definitions live in files that are committed to git alongside application code, so changes are reviewed and rolled back like any other source change rather than edited in a hosted console. Agents are grouped into teams in which specialist agents run under an orchestrator, which the documentation illustrates with an SRE incident response team. Evaluation is built into the workflow: an LLM-as-judge harness runs scenarios against every agent automatically, so behaviour regressions are caught before a change ships, and a deploy command pushes the tested configuration to production infrastructure the operator controls. Observability comes from OpenTelemetry traces exported to a Jaeger backend that Station itself starts, giving a span-level view of each agent execution, its tool calls and its handoffs. Tooling for agents arrives over the Model Context Protocol, with the companion Ship CLI supplying filesystem tools out of the box, and Station also runs as an MCP server over stdio so that Claude Code, Cursor, OpenCode, Claude Desktop and other MCP clients can drive its agents from inside an existing editor session. Model providers are pluggable and include the vendor CloudShip AI inference service with Llama and Qwen models, OpenAI, Google Gemini and Anthropic, chosen at initialisation and stored in a local configuration file. Docker is required for the tracing backend. The positioning is DevOps and platform teams that want agent workloads under the same version control, testing and observability discipline as the rest of their infrastructure, and that need everything to run on their own hardware with their own data.
https://github.com/cloudshipai/station
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.