Claude dynamic workflows, and open-multi-agent
In May 2026, Anthropic shipped dynamic workflows in Claude Code: the model plans and orchestrates the work at runtime. open-multi-agent makes the same bet in a different form factor.
Model-driven orchestration inside Claude Code. Claude writes its own orchestration scripts and fans out tens to hundreds of parallel subagents in a single session, checking its work before anything reaches you.
Read the announcement↗An MIT-licensed TypeScript library. A coordinator turns your goal into a task DAG at runtime and runs it in your own backend, on any provider — with the plan exposed as data you can inspect and replay.
Quick Start→The same bet: the model plans the work.
Both are model-driven. You don't wire a fixed graph up front — you hand over a goal and the model plans the work at runtime, decomposing it into steps that run in parallel and pulling the results back together. Claude's dynamic workflows do this inside Claude Code; open-multi-agent's coordinator does it in your backend. Same idea — so this page won't argue over which is more dynamic. The useful question is where the orchestration runs, and what you can do with the plan.
The difference is form factor.
They aren't the same kind of thing. Claude dynamic workflows are a capability inside Claude Code, orchestrating Claude subagents. open-multi-agent is a library you install into a TypeScript backend and point at any provider. Here is how the two line up.
| Dimension | Claude dynamic workflows | open-multi-agent |
|---|---|---|
| Where it runs | Inside Claude Code — CLI, desktop, and IDE | Your own Node.js backend — installed with npm, no hosted service to adopt |
| What it is | A capability of Claude Code | An open-source (MIT) library you embed |
| Models | Claude subagents | Any provider — OpenAI, Anthropic, Gemini, Bedrock, or any local / OpenAI-compatible model |
| Language / surface | Used from Claude Code | TypeScript, in any Node.js 18+ backend |
| The plan | Orchestration scripts Claude writes and runs in the session, checking its work before returning | A task DAG you can inspect and replay as data — planOnly, createPlanArtifact, runFromPlan |
Composable, not just parallel.
These aren't mutually exclusive. open-multi-agent speaks the Agent Client Protocol (ACP), so an OMA team can drive external coding agents — including Claude Code itself — as one agent inside the team. The model-planned orchestration you get in Claude Code can become a single node in a larger, provider-neutral run that you own end to end.
Where open-multi-agent fits.
Reach for open-multi-agent when the orchestration needs to live inside your own product: an open-source (MIT) library you npm install into a Node.js backend, running on any provider — OpenAI, Anthropic, Gemini, Bedrock, or a local, OpenAI-compatible model. The coordinator plans the task DAG at runtime, and the plan is data you can inspect, replay, and gate — planOnly to review it before anything runs, createPlanArtifact to store it, runFromPlan to execute a plan you have already vetted.
Taking this to production?
open-multi-agent is MIT-licensed and free to run yourself. When you need it delivered, integrated, or supported on a deadline, 元定义科技 (YuanASI) offers commercial delivery and support.
Looking for a framework alternative?
Weighing orchestration libraries against each other is a different question. See how open-multi-agent compares with LangGraph, Mastra, and the other frameworks.
All framework comparisons→