Configure OpenHuman to use GonkaGate as an OpenAI-compatible inference provider
in one npx command.
npx @gonkagate/openhuman-setup@gonkagate/openhuman-setup is the onboarding CLI for OpenHuman users who want
GonkaGate configured as a native OpenAI-compatible custom provider without
hand-editing OpenHuman TOML config.
The CLI writes OpenHuman's native cloud_providers shape, routes OpenHuman
agent workloads to live GonkaGate model IDs from /v1/models, preserves
unrelated config, creates a timestamped backup before replacing an existing
config file, and verifies the written result.
Current OpenHuman credential storage is not a safe standalone JSON write target.
OpenHuman may store provider secrets in the OS keychain or encrypted JSON
depending on runtime policy. This CLI therefore does not mutate
auth-profiles.json; it prints the OpenHuman Settings -> AI step for the
GonkaGate key and redacts any gp-... value from output.
npx @gonkagate/openhuman-setupYou need:
- Node.js
>=22.14.0 - local OpenHuman config on this machine
- a GonkaGate API key from the dashboard
- an active OpenHuman session before custom providers can run inside OpenHuman
- Detects the effective OpenHuman
config.toml, includingOPENHUMAN_WORKSPACE, active user, legacy active workspace, staging root, and pre-login local config. - Fetches
GET https://api.gonkagate.com/v1/modelswith the user's GonkaGate API key and treats that response as the model source of truth. - Adds one GonkaGate
cloud_providersentry with sluggonkagate. - Writes workload provider strings for chat, reasoning, agentic, coding, and memory/summarization paths.
- Preserves unrelated TOML values and unrelated cloud providers.
- Creates one timestamped backup before replacing an existing config file.
- Verifies the local config shape after writing.
- Runs a direct GonkaGate
/v1/chat/completionssmoke with the selected live model. - Reports OpenHuman sign-in and credential state separately.
- Package:
@gonkagate/openhuman-setup - Provider id:
gonkagate - Base URL:
https://api.gonkagate.com/v1 - Transport:
/v1/chat/completions - OpenHuman provider shape:
cloud_providersentry plus workload provider strings - OpenHuman credential key:
provider:gonkagate, profiledefault - Model catalog: authenticated
GET /v1/modelswith the user's API key
Allowed secret inputs:
- hidden interactive prompt
GONKAGATE_API_KEY--api-key-stdin
Not allowed:
- plain
--api-key - repository-local secret storage
- shell profile mutation
- direct standalone writes to OpenHuman
auth-profiles.json
GONKAGATE_API_KEY=gp-... npx @gonkagate/openhuman-setup --yesOr pass the key through stdin:
printf '%s' "$GONKAGATE_API_KEY" | npx @gonkagate/openhuman-setup --api-key-stdin --yes --jsonBy default, the CLI uses the first model returned by GonkaGate /v1/models for
all OpenHuman workloads. Override values must be IDs returned by that live
response:
npx @gonkagate/openhuman-setup \
--reasoning-model provider/model-id \
--agentic-model provider/model-id \
--coding-model provider/model-id \
--summarization-model provider/model-id- It does not install OpenHuman.
- It does not write the old
api_url+api_key+model_routessetup shape. - It does not accept arbitrary custom base URLs.
- It does not use repository-hardcoded GonkaGate model catalogs.
- It does not print or persist
gp-...secrets outside approved OpenHuman credential handling. - It does not directly mutate OpenHuman
auth-profiles.json.
Automated release proof is npm run ci plus a temp-workspace CLI smoke. Before
publishing, also run one real-workspace smoke with an active OpenHuman session
and a real GonkaGate key pasted through OpenHuman Settings -> AI. Current proof
notes live in
docs/specs/openhuman-setup-prd/release-proof.md.
npm install
npm run ciThe CLI can be exercised against a temporary OpenHuman workspace with:
npm run build
GONKAGATE_API_KEY=gp-... OPENHUMAN_WORKSPACE="$(mktemp -d)" node bin/gonkagate-openhuman.js --json --yesThe product requirements for the implementation live in
docs/specs/openhuman-setup-prd/spec.md.
The current execution plan lives in
docs/specs/openhuman-setup-prd/implementation-plan.md.