Tokens & API keys¶
Autolab has two kinds of secret, and they're easy to mix up:
- Access tokens (PATs) — authenticate you (the CLI) to the control node.
- LLM provider keys — the Anthropic/OpenAI/… keys the agent uses to think.
Signing in¶
autolab login # browser sign-in; stores a token for this host
autolab whoami # show the active host and signed-in user
autolab logout # remove the stored token for this host
Tokens are stored per host in ~/.config/autolab/credentials.json
(owner-only), so logins to different hosts coexist without
clobbering each other.
Headless login¶
On a remote box, CI runner, or anywhere without a browser, pass a token directly:
Or skip storage entirely and let the environment variable carry it for a single
command — for control-node requests, AUTOLAB_TOKEN is used ahead of any stored
login:
Personal access tokens¶
A PAT is the same credential the browser login mints — a revocable token that acts as you on every project you can access. Manage them from the CLI or the dashboard's Access Tokens tab.
autolab token # print the token you're authenticated with
autolab token create --name gpu-box # mint a fresh, named token (prints it once)
autolab token ls # list your tokens
autolab token revoke gpu-box # revoke by name or id-prefix
Prefer a named token create over the bare print, so you can revoke just
that one later. Pipe tokens, don't paste them where they'll be logged:
Researcher+ for compute nodes
Registering an compute node clones private code, so the token must belong to a researcher, admin, or owner on that project.
LLM provider keys¶
The agent needs an LLM to write code and analyze results. Every project runs on your AutoLab Key — platform credits, nothing to set up. The dashboard's Credits tab shows your balance and usage and takes top-ups. Bringing your own provider key is not available at the moment.
Next: Drive the agent, or attach compute with Compute.