jevbooks

← All projects

jevdroid

antiyro/jevdroid

Control Android over ADB with Jev-typed decisions.

Agent Decisions1.00Runner-up: Classification & Routing
Automated README summary

Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

JevDroid is an experimental Python framework for controlling Android devices over ADB or UIAutomator2. Given a goal, it reads the accessibility tree, chooses an action, and executes it: open apps, tap, swipe, navigate back.

How it uses Jev

Jev chooses the next Android action from the accessibility tree state plus the goal. Goals and visible UI text are sent to the selected TypeSafe or Vercel provider. The chosen action is then executed through ADB or UIAutomator2, subject to action permissions and per-run budgets.

Primitives:choice

Technique worth stealing

Send the accessibility tree plus goal to Jev to pick one action, then execute it under explicit permissions and budgets.

Try it

pip install -e ".[android]" then jevdroid run "Open Display settings without changing a setting" --package com.android.settings --allow-taps --budget 0.05

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 material0.87
  • Shows a System One patternFound in material0.77
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersFound in material0.90
  • Is a runnable toolFound in material0.89
  • Top-10 learning shortlist signalunclear0.47
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale0.90 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.87Shows a System One pattern0.77Describes handling uncertainty0.05Reports measured numbers0.90Is a runnable tool0.89Top-10 learning shortlist signal0.47Is a replica of the model0.0400.51Solves a common problem (0–2)0.90 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.31Check-up0.2500.51

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 20 Sept 2026.