jevbooks

← All projects

ai-hedge-fund

virattt/ai-hedge-fund

Educational AI hedge fund proof of concept with investor agents.

Finance & Trading81%Runner-up: Other

What it is

A proof of concept exploring AI-driven trading decisions for educational and research purposes. It runs investor agents over stocks to build and backtest a simulated "fund" — it does not actually place trades.

How it uses Jev

The README lists TypeSafe (Jev) as one supported model API key for the investor agents, selectable via --model jev-1.13.0 when running a mandate. It does not describe which decisions Jev makes, what state is passed, or how results are consumed in code.

Try it

pipx install aihf, then run aihf and configure a TypeSafe API key.

View on GitHub

judged by Jevjev-1.13.0

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-centricno0.04
  • Shows a System One patternno0.18
  • Handles uncertaintyno0.04
  • Measuredno0.03
  • Runnableno0.39
  • Worth recommendingno0.09
  • Model replicano0.18
  • Problem scopescore on a 0–2 scale0.00
  • About Jevyes0.75

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.