What it is
A Python adapter that replaces typesafe_sdk's system_one evaluation API with LLM APIs, letting developers compare TypeSafe against OpenAI, Anthropic, and OpenAI-compatible models on cost, speed, and intelligence.
How it uses Jev
Jev is not used. The adapter runs the same typed interface over LLM APIs instead of TypeSafe, so no Jev decisions are made.
Try it
pip install 'system-one-adapter[openai]' or 'system-one-adapter[anthropic]'
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-centricno0.17
- Shows a System One patternno0.09
- Handles uncertaintyno0.03
- Measuredno0.04
- Runnableyes0.95
- Worth recommendingno0.05
- Model replicano0.09
- Problem scopescore on a 0–2 scale1.03
- About Jevyes0.94
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.