configure
In the Console
Author models, agents, execution flow, schedulers, cells, and MCP servers in the Console. Once the Console’s API is deployed, you publish a versioned config there and the engine resolves it by ID.
Developer
api.openeng.app is not a website
It is a programmatic, per-user-authenticated API meant to be called with a credential — an identity token or an API key — not browsed. Today it serves the engineering apps’ pairing routes; its OpenEng AI routes open with the Console’s API. Here is where to go instead.
Status: OpenEng AI isn’t live yet. The Console and Web Console interfaces load, but the OpenEng AI API routes and the Broker aren’t deployed. Nothing can be saved or published, and no AI engine can register or connect. Pro, Enterprise, and pay-as-you-go launch in Q4 2026 and can’t be purchased yet. The OpenEng AI cards below describe how the API is built to work once it is deployed.
Where to go instead
call it
Through the engines
The AI engine starts with your OpenEng key and registers with the API itself; each app engine pairs with a one-time key from its app. Either way, you never hand-craft API requests.
keys
With an API key
Once the Console’s API is deployed, the engine starts with OPENENG_KEY, an API key from the Console (a Pro feature). Each key runs one engine at a time, so issue a key per machine under Deploy → API keys; headless runners use the same kind of key once the engine’s scheduler ships. A key is shown once, stored only as a hash, and revocable in the Console: a revoked key can’t register an engine again, so a running engine is cut off when its Broker session ends (within 24 hours).
Pro (launching Q4 2026) · credentialed
Looking for billing? Plans and subscriptions are served by billing.openeng.app; manage yours from Account & billing.