conductor
Create, run, monitor, manage, and review Conductor workflows — including agentic workflows (LLM + MCP + tools) — and build, test, deploy, and invoke Conductor Agents (SDK-native in Python/TypeScript/Java/C#, or bring a LangChain / LangGraph / OpenAI Agents / Google ADK / Vercel AI / Claude Agent SDK agent) and call remote A2A agents. Use when the user wants to define workflows, build AI agents (deployed agents with tools and human approval, ReAct loops, MCP tool use, RAG), scaffold an agent in their language, start executions, check status, pause/resume/terminate/retry workflows, signal tasks, schedule recurring runs, or review/optimize an existing workflow or agent. Uses the conductor CLI or falls back to bundled REST API script. Requires a reachable Conductor server — auto-detected for a local conductor server start, otherwise set CONDUCTOR_SERVER_URL.
