Skip to main content
An agent speaks A2A the moment it starts. You don’t need a cluster, or even a connected CLI, to run it and hold a full conversation with it.
1

Build the image

Reads the Dockerfile to build, and AgentCard.json for the name:version tag.
2

Run it

Your agent is live at http://localhost:8000, speaking A2A over HTTP.
3

Chat with it

All three talk A2A directly to your container — no control plane involved.

Resuming a conversation

Conversations are tracked by session, keyed to the A2A contextId your agent returns.
--resume and --session-id are not interchangeable: --resume always opens the TUI (it fails outside a real terminal), --session-id sends a one-shot message into an existing session. Useful for iterating on multi-turn behavior — resume the same session after a code change instead of replaying every turn.

Chatting once you’re deployed

The same command works against a deployed agent or the routing engine once you’ve connected to a cluster:
A lone argument containing whitespace is the message, not the target.

Next

Deploy and manage

Push your agent to a cluster.

A2A agents and frameworks

The protocol behind every chat call.