# virattt/ai-hedge-fund

> An educational proof-of-concept AI hedge fund: LLM investor agents make trading decisions on given tickers, with backtesting and paper trading. For learning and research only; it does not place real trades.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 63,807 total · +2 stars on 2026-09-30 (UTC), ≈ 10 by evening
- Star trust: star growth looks organic
- Category: Finance & crypto · Language: Python · License: MIT · Created: 2024-11-29 · Last push: 2026-09-26
- GitHub: https://github.com/virattt/ai-hedge-fund · Page: https://gitnova.dev/en/r/virattt/ai-hedge-fund

## Useful for

- Launch the interactive aihf app and build a fund from strategies and tickers
- Backtest a mandate over history and compare its equity curve to a benchmark
- Run one fund cycle from a mandate file and get the JSON decision record

## Why it’s here

- 2 stars so far today, about 10 expected by the end of the day.
- Interest is fading: the two-day pace is 45% of the previous week and a half.
- About 11 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 11,208
- Issues and pull requests: 679
- Watchers: 675
- Average over the last week: 22 per day
- Usual pace: 32 per day
- Latest release: v2.4.1 (2026-09-25)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 12 days

09-19 3.4, 09-20 3.5, 09-21 3.3, 09-22 2.4, 09-23 2.1, 09-24 2.7, 09-25 2.7, 09-26 1.9, 09-27 1.8, 09-28 1.8, 09-29 2.0, 09-30 2.1

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-30 10:54 UTC, updated every 30 minutes.