Engines

Use the Claude Code CLI as the engine.

The same binary you already run in a terminal, driven from a window that also has your diagrams, your dependency audit and your dashboards in it.

Download for macOS
v0.1.33 · .dmg · Apple Silicon & Intel
Signed & notarized by Apple · opens without a Gatekeeper warning
sha256 698955a0187bc039f4c74f5d05a9f10fbb27376a45788a0a241d1326b73873c7
Download for Windows instead
$curl -fsSL https://lucidtrain.com/install.sh | sh

Select Claude Code in the engine picker and Lucid Train runs the `claude` binary from your PATH as a local child process, talking to it with `claude -p` and stream-json in both directions. It is the same CLI you would run in a terminal, signed in the same way, so there is no second subscription, no API key for the engine and no proxy in the middle. If the binary is missing, the picker shows the install command; if it is installed but not signed in, it shows `claude auth login`.

How the connection actually works

The harness starts `claude -p` and keeps it alive, sending prompts and reading events as newline-delimited JSON in both directions. A long-lived process rather than one invocation per turn matters because it is what lets a session keep its context and be resumed rather than replayed from the top on every message.

Whose credential is used

On this route Lucid Train never sees the credential. It looks for the binary on PATH, spawns it as a child process, and speaks its protocol. Authentication is whatever that CLI already did when you signed into it, so the entitlement stays between you and the vendor and nothing is proxied, replayed or re-signed.

What Lucid Train adds on top

Claude Code is a terminal program. Running it underneath this harness puts the same agent next to a diagram canvas whose output it can be handed as a specification, a dependency audit that can shell out to real scanners, and a Grafana connection. Lucid Train also registers itself as an MCP server for the session, so the diagram tools arrive as mcp__lucid__ tools and are pre-approved rather than prompting on first use.

The two engine lists

One thing worth separating, because the two lists genuinely differ: the engine that runs a coding tab and the provider that powers Design mode are chosen independently. Coding tabs accept Claude Code, Codex, Cursor CLI and OpenCode. Design mode accepts Claude Code and Codex only. Picking Cursor for your coding tab does not move Design onto Cursor, because there is no Cursor provider behind that canvas.

What you keep and what you lose

You keep the model quality and the tool loop, since it is the same process. You lose the parts of Lucid Train that only the bundled engine implements: connecting a new Grafana instance and adding connectors both require the Lucid engine, though once a Grafana is connected every engine can query it.

What the engine picker needs

Value
Binary on PATHclaude
Installnpm i -g @anthropic-ai/claude-code
Sign inclaude auth login
Transportclaude -p, stream-json both ways
Drives Design modeYes
API key needed by Lucid TrainNone
FAQ

Questions

Do I need an Anthropic API key?

Not for the engine. Lucid Train spawns the CLI and the CLI authenticates itself however you set it up. An API key is only relevant if you choose the bundled Lucid engine instead and point it at a provider directly.

Is this a proxy around a subscription?

No, and the distinction matters. Nothing is converted between request formats and nothing is replayed through a shim. The vendor's own binary runs on your machine and Lucid Train reads its output stream.

Can it power the Design tab too?

Yes. Claude Code is one of the two providers Design mode accepts, the other being the Codex CLI.

What if the binary is not installed?

The picker detects that and shows the install command rather than failing at the first prompt. The same detection distinguishes installed-but-not-signed-in and shows the login command instead.

Related

Last updated