What makes Lumina Capital different from other AI hedge fund projects?

It strictly separates the LLM's unstructured debate from deterministic mathematical quant calculations, and includes a risk officer with absolute veto power over any allocation.

How much does it cost to use?

It is free for personal use and simulation; the project is released under CC BY-NC 4.0 for academic, educational, and research purposes.

What are the system requirements to run it?

Python 3.10 or higher. After installing dependencies with pip, you can launch the dashboard using the Streamlit command shown in the repository.

Open-Source AIAI Business & IndustryQiita 機械学習14h agoOct 15, 2026, 10:00 JST

Lumina Capital (v6.0) AI hedge fund engine open-sourced on GitHub

Send on LINE

3 Key Points

What happened
A developer published Lumina Capital (v6.0) on GitHub under CC BY-NC 4.0, letting individuals and researchers run an autonomous AI investing studio locally with Python 3.10+ and Streamlit.
Why it matters
For the first time, individual developers and researchers can freely test an AI investing engine that locks out trades when its risk officer detects tail risk or accounting fraud, making local validation of automated strategies possible.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

Existing open-source AI hedge fund projects on GitHub struggle with execution realism: they let LLMs read raw chart data and fundamentals to make trading calls, which leads to hallucinations and calculation errors. They also ignore trading frictions like fees and slippage, and lack safeguards when markets crash during long LLM reasoning. Lumina Capital (v6.0) tackles these problems by isolating the LLM's subjective debate from the deterministic math layer. Its multithreaded architecture runs a 10-second watchdog thread that enforces dynamic ATR and Fibonacci-based stop levels without waiting for LLM API calls. For quantitative research, this design mirrors how professional quant funds separate signal generation from execution. The project's open-source release under CC BY-NC 4.0 allows individuals to run a full autonomous investing studio locally, potentially speeding up reproducible experiments in AI-driven trading.

FAQ

What makes Lumina Capital different from other AI hedge fund projects?: It strictly separates the LLM's unstructured debate from deterministic mathematical quant calculations, and includes a risk officer with absolute veto power over any allocation.
How much does it cost to use?: It is free for personal use and simulation; the project is released under CC BY-NC 4.0 for academic, educational, and research purposes.
What are the system requirements to run it?: Python 3.10 or higher. After installing dependencies with pip, you can launch the dashboard using the Streamlit command shown in the repository.

Qiita 機械学習Read Original Article

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.