Gateway CLI reference

The Gateway is part of the NeuraFrame Studio™ service, so you drive it with the same neuraframe command. This page lists the subset you use to run and inspect the proxy. The full command list is in the Studio CLI reference.

Configure the gateway

neuraframe config set gateway.upstream_url URL   # your provider base URL
neuraframe config set gateway.profile NAME       # openai | anthropic | grok | generic | auto
neuraframe config set gateway.listen ADDR:PORT   # default 127.0.0.1:8081
neuraframe config get gateway                    # show the current gateway block

Config changes take effect after a restart: sudo systemctl restart neuraframe-studio.

status

Shows service state, version, whether the engine is active or in pass-through, the gateway listen address, and license validity. Use this first when a request is not being served from memory.

neuraframe status

stats

Reuse counters: how many requests were served from memory versus forwarded upstream. This is where you see the Gateway earning its keep.

neuraframe stats

logs

Recent service logs (via journalctl when available), useful for diagnosing upstream connection issues or profile mismatches.

neuraframe logs

doctor

Runs the compatibility preflight, then a service and license summary, in one command.

neuraframe doctor

license, trial, activate, billing

Licensing is shared with Studio. When unlicensed or expired, the Gateway forwards everything and serves nothing from memory, so it stays fully transparent. See Licensing & trial for the Gateway view.

neuraframe trial start     # start the 7-day trial
neuraframe activate        # activate a paid license
neuraframe license         # show device fingerprint and validity
neuraframe billing         # open the billing portal
Teaching corrections is not part of the proxy path. A plain model API has no concept of a correction, so neuraframe correct works through the native reuse API, not the gateway. You get reuse with zero code change; teaching is an opt-in extra.