Work
Kevin S Lin, who writes his name as Kevin Lin on his own website, works at OpenAI. He describes what he does as building tools for humans and agents. He lives in Seattle and is often in San Francisco.1 His GitHub profile names OpenAI as his company and Seattle as his location.2
Dendron
He created Dendron, an open-source note-taking tool,1 and is listed as its founder on his DEV profile.3
Writing
He wrote Securing Persistent Agents Like OpenClaw at OpenAI, published on the OpenAI developer blog on 12 November 2026.4 He also writes a newsletter, Bit by Bit.1
- Made
-
-
Securing Persistent Agents Like OpenClaw at OpenAI OpenAI blog post on running hundreds of always-on OpenClaw agents safely: trusted control plane, sandbox, auto-review, agent identity and logs.
A post by Kevin S Lin on the OpenAI developer blog, published on 12 November 2026. It describes how OpenAI runs persistent agents across the company, including hundreds of OpenClaw agents; more than 500 agents now work in the background there. It says that OpenClaw launched almost a year earlier.
Content
- The risk: persistent agents run all the time, act without being prompted and can write any code to reach a goal. The main danger is the agent doing something misaligned, not only attackers.
- Threat model: the deterministic infrastructure (network, identity, sandbox, the gateway that configures agents) is trusted; the agent, its environment and the code it writes are not.
- Five measures: separate the gateway from the agent harness, set hard sandbox boundaries and let a second model review actions (auto-review). The sandbox covers the network allowlist, the workspace, the process and a credential broker for secrets. The agent also gets an identity of its own, and every configuration change and every agent turn is logged.
- Configuration: two files of the Codex harness, an admin file that sets limits (
requirements.toml) and the agent's configuration within them (config.toml). - Outlook: OpenClaw Enterprise (OCE), an open-source, vendor-neutral control plane announced at DevDay, in pilot with version 1.0 planned by the end of the year.
Not covered: memory, prompt injection, vetting skills and plugins, updates and incident response.
Securing a Persistent AI Agent explains the post in my own words and what I take from it.
-
- Mentioned in
-
- Securing a Persistent AI Agent How to let an AI agent work on its own without handing it the keys: OpenAI's five safeguards explained, and how I apply them to my own agents.
- See also
-
- OpenAI American AI company in San Francisco, a public benefit corporation, that develops ChatGPT, Codex and the GPT models.
- Tags