jevbooks

← All projects

jev-game-agent

felix0123456/jev-game-agent

Vision-based Android game autopilot driven by Jev typed decisions.

Automated README summary

Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

An Android app that plays mobile games autonomously: it captures the screen, asks a Jev vision model what to do, and injects taps and swipes via Accessibility, no root required.

How it uses Jev

JevApiClient posts the compressed frame plus objective to /v1/systemone with typed questions: game_status and action_type (choice), target_box (box), swipe_direction (choice), objective_fulfilled (noul). AgentCoordinator uses the answers to dispatch gestures and advance goal steps.

Primitives:choicenoul

Technique worth stealing

Downscale frames to 512px JPEG and ask one multi-question typed prompt per frame, then map the returned box to touch coordinates.

Try it

Build the APK via Gradle or the CI workflow, grant MediaProjection, Overlay and Accessibility permissions, then start a preset.

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 material0.95
  • Shows a System One patternFound in material0.79
  • Describes handling uncertaintynot found in the excerpt0.04
  • Reports measured numbersnot found in the excerpt0.03
  • Is a runnable toolFound in material0.90
  • Top-10 learning shortlist signalunclear0.49
  • Is a replica of the modelnot found in the excerpt0.07
  • Solves a common problem (0–2)score on a 0–2 scale0.39 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.95Shows a System One pattern0.79Describes handling uncertainty0.04Reports measured numbers0.03Is a runnable tool0.90Top-10 learning shortlist signal0.49Is a replica of the model0.0700.51Solves a common problem (0–2)0.39 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.96Fail open, fail closed0.90Blind review0.83Prefetch0.39Funnel0.2400.51

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 24 Oct 2026.