Skip to main content
ade is the typed control plane for ADE. Everything you do in the desktop app — create lanes, run agents, ship PRs, kick off tests, attach Linear issues — has a CLI command, so you can drive ADE from any shell. Agents running inside ADE use the same commands, which is how they inspect and operate the workspace they live in.
Two commands discover everything: ade <group> --help for exact flags on any command, and ade actions list --text for the full service-backed action catalog behind the typed commands.

Output modes

Most commands take an explicit output mode. Use --text for a human-readable summary and --json for stable, scriptable fields (the default when output is piped).

Command groups

Register projects and manage worktrees (lanes).
Start and inspect agent chats, terminals, and CLI sessions inside a lane.
Commit, push, and turn a lane into a pull request; read CI and comments.
Start dev processes and run test suites in a lane.
Attach and update Linear issues through ADE’s own Linear connection — no API key needed.
Control the machine-owned ADE runtime (the brain) and pair a phone.
List the computer-use proof artifacts ADE captured for a chat or session.
Find commands, flags, and the full action catalog, and check local readiness.
Prefer typed commands — they validate arguments and return stable fields. Reach for ade actions run <domain.action> only when no typed command covers the workflow yet.

Full reference

For every command, subcommand, flag, and the runtime modes behind them, see the complete CLI README on GitHub.

ade CLI README

The full ade command reference, runtime modes, and install paths.

ade code (terminal)

The interactive terminal UI built on the same runtime.

Architecture

How the control plane, runtime, and clients fit together.