Head to head
Clawdcursor vs agent-device
Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.
Clawdcursor
Cio.github.AmrDab/clawdcursorNo reviews yet
Safe cross-OS desktop control for any AI agent - the fallback execution layer.
Full listing
No reviews yet
Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps
Full listingThe short version
Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. The safety scan favours agent-device (94/100 against 58). agent-device has noticeably more public adoption.
| Clawdcursor | agent-device | |
|---|---|---|
| User rating | No reviews yet | No reviews yet |
| Safety grade | C58/100 | A94/100 |
| Adoption | Established | Widely used |
| GitHub stars | 402 | 4.8k |
| Downloads / week | 31 | 236k |
| Runs where | Your machine (local) | Your machine (local) |
| Gateway-ready | No | No |
| Tools | — | 1 |
| Write actions | — | 1 |
| Price per call | Free | Free |
| Licence | MIT | MIT |
| Last release | 2026-09-28 | 2026-09-27 |
| Category | AI and agents | AI and agents |