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:

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.

Original post →

More from coding & agent

coding & agent channel →