Cloudflare open-sources AI OS with security model to tackle privacy risks
irvinebroque · x · 2026-08-24
Cloudflare has open-sourced Cloudflare OS, an internal AI productivity environment built on Cloudflare Workers for running agents with company context and systems.
The project introduces a security model using Gatekeepers and Isolates:
- Gatekeepers: Allow AI to read data but restrict write permissions.
- Isolates: Limit AI access to specific data sources.
This architecture addresses the security risks of AI agents accessing sensitive data (following the Inspect AI incident where user emails were stored), providing a safer sandbox for enterprise AI use.
More from coding & agent
- raylib 6.2 ships with 300+ improvements and 100 new contributors, 20 new API functions — jsuarez · 2026-10-16
- "Vibecoding" is as misleading a label as "AI" and "SI," dev complains — eschadiol · 2026-10-16
- Doc2Harness: New benchmark finds best coding agent passes only 53% across 329 cases — _akhaliq · 2026-10-16
- Perplexity open-sources SPACE, the Firecracker microVM sandbox behind Perplexity Computer — perplexity_ai · 2026-10-16
- Blackstone goes all-in on Factory for autonomous software development — matanSF · 2026-10-16
- Longtime Windsurf user cancels $10/month legacy plan, citing AI subscription fatigue — tristanbob · 2026-10-16