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.
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
Project & lanes
Project & lanes
Register projects and manage worktrees (lanes).
Chats & sessions
Chats & sessions
Start and inspect agent chats, terminals, and CLI sessions inside a lane.
Git & PRs
Git & PRs
Commit, push, and turn a lane into a pull request; read CI and comments.
Tests & run
Tests & run
Start dev processes and run test suites in a lane.
Linear
Linear
Attach and update Linear issues through ADE’s own Linear connection — no API key needed.
Brain & pairing
Brain & pairing
Control the machine-owned ADE runtime (the brain) and pair a phone.
Proof
Proof
List the computer-use proof artifacts ADE captured for a chat or session.
Discovery
Discovery
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.
