Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

ai-hedge-fund

Educational multi-agent AI hedge fund that paper-trades, with TypeSafe Jev as one supported model provider for its investor agents.

ProjectprototypeMIT
View on GitHub ↗

Overview

AI Hedge Fund is a proof-of-concept that explores AI-driven trading decisions for educational purposes. It does not place real trades. Investor agents analyse prices, fundamentals and earnings from Financial Datasets, and an interactive terminal app runs paper-trading funds with ledgers of real market days and fake money, an approval step showing each decision before it executes, and a kill switch. Sessions are stored in a hash-chained ledger.

The README lists TypeSafe (Jev) among supported model providers alongside Anthropic, OpenAI, DeepSeek, Google, xAI and Kimi. The list summaries describe a Jev adapter for structured judgments in the fund's decision workflow, which avoids parsing free-text model output.

What the decision model decides

TypeQuestionAnswers
ChoiceFor this ticker, should the fund buy, sell or hold?(inferred)buy · sell · hold

How it works

  1. Fetch market data for selected tickers
  2. Investor agents form judgments (optionally via Jev)
  3. Show the exact decision for approval
  4. Apply to the paper ledger

Strengths

  • Typed decisions avoid output parsing
  • Approval step and kill switch
  • Simple install via pipx

Caveats

  • Educational only; no real trading
  • Needs a Financial Datasets key

Getting started

pipx install aihf && aihf

At a glance

Type
Project
Status
prototype
Language
Python
Runtime
terminal app
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Quantitative finance: multi-agent AI hedge fund trading system featuring native JevLLM integration to execute fast typed decisions without parsing fragility.

    yibie/awesome-jev

  • An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.

    logicrw/awesome-jev-projects

Frequently asked questions

Does it trade real money?

No, it paper-trades for educational purposes.

How is Jev used?

As one of the selectable model providers for investor agents' structured judgments.

What keys are needed?

A Financial Datasets key and one model provider key, such as TypeSafe.

Related projects

  • jev-A-share-trader

    Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.

    ProjectbetaPython, TypeScript
  • jev-trading

    Local stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.

    ProjectbetaTypeScript
  • ml-quant-trading

    PyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.

    ProjectbetaPython
  • QuantStudio

    Chinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.

    ProjectbetaTypeScript
  • traderai

    Self-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.

    Servicebeta
  • Jev-Trades★ 51

    Next.js crypto dashboard where Jev judges each tick across timeframes and drives a SQLite paper-trading portfolio with automatic TP/SL.

    ServiceprototypeTypeScript