# silv

- **Event:** [Built with Opus 4.6: a Claude Code hackathon](https://cerebralvalley.ai/e/claude-code-hackathon)
- **When:** Feb 10 at 12:00 PM – Feb 17 at 10:00 AM (EST)
- **Where:** Location TBA
- **Team:** [Matt Silverman](https://cerebralvalley.ai/u/silv)
- **GitHub:** https://github.com/mattsilv/robo
- **Demo video:** https://youtu.be/NlL9ZPDl6Rw
- **Gallery:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/130

Having your users provide phone sensor data into AI agents today is difficult. You have to build a native iOS wrapper to access the best context gathering experience. 

Robo is an open-source iOS app that turns your phone's 9 sensors (LiDAR, camera, barcode, BLE, HealthKit, motion, compass, iBeacon, WiFi) into APIs any agent can use. No iOS development required.  Use MCP, webhooks, REST APIs, or simple email/zip export. 

Features include microsruvey links (text anyone a browser link to crowdsource photos/data, no app install needed), a chat-first UX with tool calling, and guided capture with Apple's RoomPlan AR. 

Built in 6 days by one developer pair-programming with Claude Code: 336 commits, 100 PRs, ~22K lines of code across Swift and TypeScript on Cloudflare Workers.

https://robo.app/

---

Markdown version of https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/130. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt