I don't. I write a lightweight API proxy, usually as a CLI app, that takes requests from the agent, adds secrets and makes the request, and then passes the response transparently to the agent. The agent can use APIs without ever seeing secrets or tokens.

This approach doesn't scale and won't work in the cloud without a lot more effort, but that's not been a problem for me yet.

It is a two step process : - First you create a container/sandbox/machine to contain your agent in it. If you are a dev, dev containers are a good solution. If you use OpenClaw, OpenShell is nice. there are plenty of examples on how to deploy it in a cloud instance. - Second you craft a set of credential with limited scope just for the job you want this agent to do. Don't trust the agent to restrict itself (it won't), just give it the minimum.

Practical example : you want an agent to read some of your mails and answer them. You don't give the agent access to your whole Gmail account, you create a second account for your agent and you forward the mails of interest to that second account.