jevbooks

← All projects

jarvis-merces

ctben/jarvis-merces

Thai voice assistant for Windows, decisions by Jev (TypeSafe AI).

Agent Decisions0.99Runner-up: Classification & RoutingQuestionnairePrefetch
Automated README summary

Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

jarvis-merces is a Thai-speaking voice assistant for Windows, ported from jarvisdemo001. It listens for the wake word "จาร์วิส", executes commands like opening apps, adjusting volume, media control, web search, and chatting.

How it uses Jev

Jev makes a single fan-out decision per utterance: intent type, command, app, volume level, chat style. The result with confidence is used to route actions; if confidence is low, it asks again.

Primitives:choicescorenoul

Technique worth stealing

Single fan-out decision with confidence to avoid guessing.

Try it

Run run_app.bat after setting TYPESAFE_API_KEY in .env.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.92
  • Shows a System One patternFound in material0.87
  • Describes handling uncertaintyunclear0.55
  • Reports measured numbersnot found in the excerpt0.23
  • Is a runnable toolFound in material0.87
  • Top-10 learning shortlist signalnot found in the excerpt0.35
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale0.67 / 2
  • About JevFound in material0.96
Signals
Jev is core to the project0.92Shows a System One pattern0.87Describes handling uncertainty0.55Reports measured numbers0.23Is a runnable tool0.87Top-10 learning shortlist signal0.35Is a replica of the model0.0500.51Solves a common problem (0–2)0.67 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.95Prefetch0.83Viewfinder0.57Funnel0.35Blind review0.2100.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 1 Oct 2026.