Harness Hub
All news

Securing persistent agents like OpenClaw at OpenAI

How OpenAI combines trusted control-plane services, Codex sandboxing, auto-review, agent identity, and observability to run persistent agents.

Filed underopenai

Watch a demo of the Codex Security Plugin and see the workflow in action, from getting started to reviewing the results shown in the recording.

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.