jevbooks

← All projects

tiptour-macos

milind-soni/tiptour-macos · Homepage

macOS menu bar companion for local computer use with JEV and Gemini.

Agent Decisions0.99Runner-up: Verification & Guardrails
Automated README summary

Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

TipTour is a macOS menu bar app that lets you control your desktop via typed tasks or voice, using your own API keys. It supports JEV for click-based tasks and Gemini for realtime voice and keyboard actions.

How it uses Jev

JEV receives your typed click-based task, locally detected control labels and locations, and recent action history. It chooses a target from detected controls, then TipTour executes and validates each action. JEV acts on its top-ranked target without a confidence cutoff, stopping when it chooses none, reports completion, or hits a 12-action limit.

Primitives:choice

Technique worth stealing

Local grounding of screen controls combined with JEV's choice over detected labels enables click-based automation without screenshots.

Try it

Open tiptour-macos.xcodeproj in Xcode, set signing team, build and run. Run scripts/test-jev.sh for isolated JEV tests.

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 projectnot found in the excerpt0.13
  • Shows a System One patternunclear0.48
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.94
  • Top-10 learning shortlist signalnot found in the excerpt0.17
  • Is a replica of the modelnot found in the excerpt0.10
  • Solves a common problem (0–2)score on a 0–2 scale0.89 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.13Shows a System One pattern0.48Describes handling uncertainty0.03Reports measured numbers0.02Is a runnable tool0.94Top-10 learning shortlist signal0.17Is a replica of the model0.1000.51Solves a common problem (0–2)0.89 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.64Menu0.2100.51

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 26 Oct 2026.