jevbooks

← All projects

jarvis

craigraphics/jarvis

Voice commands for your Mac: patterns first, Jev decides, LLM writes.

Automated README summary

Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Jarvis is a macOS voice-command tool for one person's daily use: it opens apps, plays music, sets reminders, checks calendar, drafts emails, writes Obsidian notes and takes selfies, and lets you teach it any app with `jarvis add`.

How it uses Jev

When no pattern matches, Jev answers multiple-choice questions over the command's candidate actions and returns a confidence score. A confident answer, including "unknown" for questions and small talk, is final; if Jev is unsure, an LLM is asked to choose from the same list.

Primitives:choice

Technique worth stealing

Route each command to the cheapest step that can handle it: patterns, then Jev's multiple-choice with a confidence threshold, then an LLM.

Try it

`uv tool install git+https://github.com/craigraphics/jarvis`, then `jarvis setup`, `jarvis doctor`, `jarvis`.

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-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

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 material0.88
  • Shows a System One patternnot found in the excerpt0.29
  • Describes handling uncertaintynot found in the excerpt0.10
  • Reports measured numbersnot found in the excerpt0.03
  • Is a runnable toolFound in material0.91
  • Top-10 learning shortlist signalnot found in the excerpt0.33
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale0.56 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.88Shows a System One pattern0.29Describes handling uncertainty0.10Reports measured numbers0.03Is a runnable tool0.91Top-10 learning shortlist signal0.33Is a replica of the model0.0500.51Solves a common problem (0–2)0.56 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.99Ghostwriter0.95Traffic light0.33Inspection0.27Grey zone0.22Check-up0.2100.51

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 4 Nov 2026.