Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
Running Codex safely at OpenAI
OpenAI describes how it runs Codex securely using sandboxing, approvals, network policies, and agent-native telemetry.
From the source
How OpenAI runs Codex securely with sandboxing, approvals, network policies, and agent-native telemetry to support safe and compliant coding agent adoption.
openai.com
Visit source ↗openai.com
- Announced
- 08 May 2026 12:30 UTC
- Detected
- 03 Aug 2026 21:11 UTC (+87d after)