RISE / AI integration / updated October 2026
Use your own AI for reading.
RISE can use an AI connection you control: Jev through your OpenRouter account, or the specified Kev-4B model on your computer. RISE’s server does not run a model or store its access key. Reading and manual settings work without AI.
Read the design note ↗CURRENT STATUS
What is established, shipped and not adopted
- 01 / ESTABLISHED
Bounded decisions, one contract
RISE builds finite choice questions from its public catalog, admits an answer only if every choice was offered, and maps it to reading settings in deterministic code. A model can pick an offered value and nothing else. The same contract serves hosted Jev, local Kev and the evaluation harness.
- 02 / SHIPPED
Shared inference retired
The Cloudflare Worker serves the app and a static decision catalog only. The six former inference routes answer 410 with instructions to connect. Connecting OpenRouter uses OAuth PKCE; the key lives in the tab’s memory and reaches only openrouter.ai. Local RISE starts the reader and a pinned Kev-4B on loopback with a per-run key the page never sees.
- 03 / NOT ADOPTED
Kev on RISE requests
RISE has no production Kev deployment, by design. In RISE’s internal checks, local Kev did not meet the bar for reading requests; those results are not published (RISE task SCR-004). Jev’s earlier 48 of 49 preference result belongs to the historical evaluation below and is not a Kev result. The local Kev path is tested on Windows with an RTX 5080; the Apple Silicon path is untested.
SOURCES
Source documents
The decision contract, the OpenRouter connection, and the Worker that calls no model.
↗ LOCALRun RISE locally with KevPinned Kev-4B on your own GPU, every service on loopback, no hosted bill.
↗ UPSTREAM MODELKev sourceModel family and serving API by Jared Palmer.
↗ EARLIER EVIDENCEJev case studyHistorical integration and evaluation.
→