01
Speaks first, asks second.
Reads what you're working on. Suggests the next step before you can frame the question.
— Introducing
Lives where you work. Sees what you see. Acts when you ask.
— The idea
An ambient assistant. Next to your code, your terminal, your tabs — quiet until it has something worth saying.
01
Reads what you're working on. Suggests the next step before you can frame the question.
02
Files, browser tabs, terminal output — Lumen sees what you see, so you don't translate.
03
The more you use it, the less you have to say. Custom commands, your phrasing, your stack.
rfc
→
opens RFC template
ship it
→
runs CI, opens PR
— In practice
Live demo — press ⌘K from any app.
Found it — server/middleware/rate-limit.ts:42, removed in PR #4821 when you switched
to edge runtime.
- import { rateLimit } from './rate-limit' - export const middleware = rateLimit({ limit: 100 })
Want me to re-enable it for /api/* only?
fix/rate-limit-api/api/*#4877 → mainLumen is free while in beta. Takes 20 seconds to install.