# Local terminal

> A full-screen terminal chat (oap agent chat) with a live transcript, inline tool sessions, and approvals — zero external setup.

Source: https://openap.org/docs/terminal-chat

`oap agent chat &lt;class&gt;` drives an agent through a full-screen terminal UI — a live transcript,
inline tool sessions, and the same approval prompts you'd see in Slack — with nothing to provision. It's the
fastest way to work with an agent from your own machine.

## Interactive vs. scripted

There are two ways to run a session from the CLI, and they're deliberately separate:

- **`oap agent chat <class>`** — the interactive terminal peer of a Slack thread. It stands up an ephemeral
  local channel, streams the conversation, and prompts you inline when the agent needs an approval. It requires
  a real terminal (it refuses a non-interactive one, and points you to `run`).
- **`oap agent run <class> --prompt "…"`** — a scripted one-shot: apply a session with a fixed prompt and
  stream its turns, for automation and CI. Flags cap it — `--budget-tokens`, `--budget-turns`,
  `--budget-duration` — and `--no-tail` applies without streaming.

## The same rules, a different surface

The terminal is just another [channel kind](https://openap.org/docs/channels). The agent's tools, identity, authorization, and
approvals are identical to what it has in Slack or the browser — only the surface differs. An approval you'd
click in a Slack card, you answer at the prompt; a plan the agent proposes renders in the transcript. Nothing
about the terminal relaxes a gate.

> **Tip: Good for building and debugging**
>
> Because it needs no workspace, no app, and no network setup, undefined is the natural loop while
> you're developing an agent — change the class, chat with it, watch the tools run, repeat.
