Skip to main content
A growing collection of commands you’ll reach for repeatedly when developing against a local Engine. Copy-paste-friendly. All examples assume:

Engine lifecycle

Start

Start in background

Stop

Stop and wipe the brain

The --volumes flag removes the engine_data Docker volume — the brain SQLite file and everything in it. Use this for a clean slate.

Rebuild after code changes

Tail logs

Brain inspection

List tables

Count rows in a table

Browse recent episodes

Browse recent trajectories

Reset memory (keep schema)

This wipes memory but keeps the schema and migrations applied. Faster than rebuilding the volume.

Configuration changes

Edit env, restart

If you set environment variables inline (not in .env), you’ll need to recreate the container:

Reload the catalog without restart

Use after editing agent definitions, skill definitions, or tool entries in catalog/.

Reload the soul template

Quick API tests

Health check

One-shot execute

List MCP servers

Search knowledge

Trigger a Learning Centre batch

Useful when you want trajectories from recent dev runs to consolidate into long-term memory immediately.

Tests

Run the full test suite

Run one test file

Run one test by name

Run with verbose output

Switching configurations

Switch LLM provider

In .env:
Then docker compose up -d engine.

Use a smaller model for development

Set in .env:
Cheaper and faster for iteration. Ship with the production model.

Disable a feature flag

Don’t forget the values are "true"/"false" strings, not booleans.

Dev shortcuts

Watch logs filtered by task

See requests in real time with low log level

DEBUG logs include MCP traces, model parameters, and context-assembly steps. Noisy but useful when investigating a specific call.

Curl with pretty SSE

See also