What it is
An interactive multi-drone autonomy simulation for exploring how fast typed System 1 reflexes can request slower System 2 strategic advice without giving up control. Fleet size is configurable from one to fifteen drones.
How it uses Jev
Each drone uses Jev as its System 1 reflex layer, making typed action decisions over available flight actions from its local context. When confidence falls below the configured threshold, an optional System 2 planner provides one-use strategic guidance through OpenRouter while Jev keeps steering.
Primitives:choice
Technique worth stealing
Let fast typed reflexes keep control while an optional slower planner supplies one-use advice on low confidence.
Try it
npm install && npm run dev; starts with development mocks, no credentials required.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.88
- Shows a System One patternyes0.91
- Handles uncertaintyyes0.86
- Measuredno0.04
- Runnableunclear0.45
- Worth recommendingunclear0.57
- Model replicano0.08
- Problem scopescore on a 0–2 scale0.09
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.