You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Droid Control lets Droids *operate* software: launch apps, type commands, click buttons, record what happens, and produce polished video evidence of it. Built by Droids, for Droids.
@@ -192,9 +192,9 @@ Every video below was planned, recorded, and rendered entirely by a Droid.
192
192
193
193
## Automation drivers
194
194
195
-
Droid Control supports three automation backends. The right one is selected automatically based on what you're targeting.
195
+
Droid Control supports four automation backends. The right one is selected automatically based on what you're targeting.
196
196
197
-
<CardGroupcols={3}>
197
+
<CardGroupcols={2}>
198
198
<Cardtitle="tuistory"icon="terminal">
199
199
**Virtual PTY automation.** Default for terminal work. Playwright-style CLI with asciinema recording and forced truecolor output.
200
200
</Card>
@@ -204,6 +204,9 @@ Droid Control supports three automation backends. The right one is selected auto
204
204
<Cardtitle="agent-browser"icon="globe">
205
205
**Web and Electron apps.** Playwright-backed CLI with Chrome DevTools Protocol support. Navigates pages, fills forms, clicks buttons, captures screenshots.
206
206
</Card>
207
+
<Cardtitle="desktop-control"icon="desktop">
208
+
**Native desktop apps.** Accessibility-tree snapshots, element or pixel actions, and per-window screenshots via [trycua/cua](https://github.com/trycua/cua)`cua-driver` -- all without stealing focus. macOS and Windows are production tier; Linux is pre-release.
209
+
</Card>
207
210
</CardGroup>
208
211
209
212
## Video rendering
@@ -241,7 +244,7 @@ Demo and showcase videos are rendered with [Remotion](https://www.remotion.dev/)
241
244
The plugin uses a composition architecture with three layers:
242
245
243
246
-**Orchestrator** -- Routes each request through three independent lookups (target, stage, artifact) to determine which skills to load.
244
-
-**10 atom skills** -- Self-contained background knowledge loaded on demand, split into drivers, targets, stages, and polish.
247
+
-**11 atom skills** -- Self-contained background knowledge loaded on demand, split into drivers, targets, stages, and polish.
245
248
-**3 commands** -- Parse arguments into commitments, then delegate to atoms via hybrid handoffs.
246
249
247
250
Every workflow flows through **capture → compose → verify**. Commands declare *what* to produce; atoms own *how*. Skills chain through explicit handoffs rather than hardcoded pipelines, so the droid follows the flow naturally.
@@ -268,6 +271,13 @@ Only install what you need for your use case.
0 commit comments