↓ Skip to main content
Mornati Blog
  1. Projects/

Jev & System One

Decision models that judge my Home Assistant automations and route each prompt to the right LLM.

6 posts Sep 23, 2026 → Oct 11, 2026 Repository

  1. 1

    · 20 minread

    system-one-router: Letting a "System One" Model Pick the Right LLM for Every Prompt

    My first model router let an LLM read a prompt file and pick an agent. This one asks a "System One" decision model four typed questions, scores the models with plain arithmetic, and publishes a benchmark to prove it works (and to show where …

  2. 2

    · 23 minread

    Jev in Home Assistant: Letting a Decision Model Make the Judgement Calls

    My automations are good at thresholds and bad at context. Jev answers typed questions with a calibrated probability, for about two thousandths of a cent each. Here is how I wired it into Home Assistant with the old rules kept as a safety …

  3. 3

    · 11 minread

    Jev in Home Assistant, Take Two: History, Feedback, and Why I Didn't Go Local

    The fix for "Jev has no memory" was never a different model. It was giving Jev a memory. Here is the history script, the feedback loop, and what the live scoreboard already disagrees about.

  4. 4

    · 21 minread

    Laya vs Jev, Ten Days Later: New Rivals, a Fine-Tune on My MacBook, and a Reality Check in Home Assistant

    Laya says "fine-tune me", so I did, on a 16 GB MacBook. Here is the recipe, how long it takes, what it changes on the 80-prompt benchmark, and why my house still runs on Jev.

  5. 5

    · 11 minread

    Clef-flash vs Jev: Cloudflare's Open Decision Model on a 16 GB MacBook

    Three days after Cloudflare's announcement, Clef-flash went through the same 80-prompt benchmark as Jev, Laya, Von and Kev. 90% topic accuracy, a confidence temperature that brings it level with Jev on calibration, and one problem no …

  6. 6

    · 22 minread

    Laya 0.4.2 and VegaML: a Decision Model That Rolls a Ball Downhill, on a 16 GB MacBook

    Laya shipped eight releases and nothing moved for routing. Its author also shipped VegaML, a decision model that answers by letting a particle settle in a valley. Zero-shot it isn't ready for my router, but it can learn from 40 labels in a …