Hi everyone, I’m currently running the LangGraph Agent Server in a self-hosted setup (free version), using the langchain/langgraph-api Docker image. From the scaling documentation, I understand that in a production setup there is a separation between: API servers (handling HTTP requests) Que…

hi @gdrouet imho you don’t need Helm or any licensed image for this. The langchain/langgraph-api image already contains a standalone queue-worker entrypoint, so you can reproduce the “Split API and queue” runtime (from Agent Server → Runtime architecture ) with plain docker compose: run the same ima…

Free Self-hosted LangGraph Agent Server: how to separate API and queue workers using Docker

LangSmith Product Help

gdrouet April 20, 2026, 9:04am 3

It works perfectly thanks!

Topic		Replies	Views
Serving an agent with the LangGraph CLI dev command LangGraph self-hosted , python-help	4	112	April 30, 2026
How should I deploy a self-hosted multi-agent system? LangGraph python-help	9	262	May 3, 2026
Dynamically Enabling/Disabling Graphs in a LangGraph Server at Runtime LangGraph self-hosted , cloud , python-help	3	42	May 21, 2026
Hosting an agent server on Heroku LangGraph self-hosted , python-help	2	182	April 18, 2026
Best practices for self-hosting LangGraph Server OSS without LangGraph keys LangGraph self-hosted , cloud , python-help	4	99	May 22, 2026

Free Self-hosted LangGraph Agent Server: how to separate API and queue workers using Docker

Related topics