OpenBB: Open-Source Investing

Hey, it’s Matt. And this is AI Street Markets, where I highlight tools connecting AI + investing. This edition:

⚙️ OpenBB the open source investor platform

Forwarded this? Subscribe here. Join readers from Bloomberg, JPMorgan, BlackRock & more.

OPEN SOURCE

In researching AI tools for investors, I've only come across one that's fully open source: OpenBB. And that tends to throw off the financial set.

“They were like, ‘why are you doing this open source? This doesn’t make sense,” Didier Rodrigues Lopes, the company’s founder and CEO, told me. “They just knew that you don’t do things like open source, but they didn’t really know why.”

I was surprised as well. Wall Street hasn’t historically worked this way, which is strange when you think about how much data is freely available. But that’s changing, more and more of the code that runs Wall Street is out in the open.

OpenBB has caught on: it recently passed 100,000 signups and has more than 40,000 stars on GitHub. Open-source software is free and developed by a community of coders.

Didier’s diverse background is in engineering and coding. Fields that are more open to open source software.

The origin story: Didier was a sensor fusion engineer in London. His old math professor asked for help coding a PhD thesis on financial forecasting. One thing led to another, and he was spending evenings creating investment reports with screenshots, regression models, and sentiment analysis.

"Financial people started reaching out to me, and for them it was crazy that I had it open sourced.”

With OpenBB, you get access to open-source financial tools that pull data from sources like FRED (macro), Yahoo Finance (equities), Alpha Vantage (real-time markets), and Finnhub (fundamentals, sentiment, earnings)—letting you analyze stocks, ETFs, crypto, and economic indicators via Python or a GUI.

Wall Street has been shedding its proprietary mindset over the last decade and embraced open-source software. It’s more cost effective and financial services firms have realized it’s not a core business value proposition, Dov Katz, a managing director at Morgan Stanley, told Business Insider in a story earlier this year.

Llama Finds Wall Street Users

Meta says its open-source Llama models are gaining traction in finance and beyond. Goldman Sachs, Nomura, AT&T, DoorDash, and Accenture now use the models for tasks like customer service, document review, and code generation.

How the OpenBB’s business model works:

  • You bring your own API keys from data providers (many have free tiers)

  • OpenBB aggregates everything into one interface

  • You only pay OpenBB for enterprise features or hosting

There are lots of free and underused datasets out there. One is the FRED dataset, alone has 800,000 different datapoints to analyze.

"The decision is not built versus buy—it is build from scratch or build on top of infrastructure," Didier explained.

PRIVACY

Running LLMs on Your Laptop

I was surprised to learn Didier was running a 3.2 billion-parameter Llama model locally on his MacBook.

You can just run it on your machine. And so what some people do is when they're having private conversations, they use these models locally, so there's no data leakage. But also if you are on an airplane where there's no wifi, you can just use it."

Why this matters:

  • Prompts stay on your machine

  • No data sent to OpenAI or third parties

  • Works without internet

  • Full control over the model

"I think that in the future, this is what firms are going to be doing. Because otherwise, your data is going out, which is like a big no for a lot of investment firms," Didier said.

I had spoken with Professor Alejandro Lopez-Lira in an interview last summer who said that in five years banks would be running AI on their machines. We’re already starting to see this happening.

TAKEAWAY

As AI gets cheaper and more private, open-source tools like OpenBB let firms build custom workflows instead of conforming to whatever they get out of the box.

You can try OpenBB yourself by downloading the code here.

DIRECTORY

AI Tool Directory

I’ve put together a database of 50+ AI and investing tools categorized by use case, where you can search, for example, by due diligence or AI agents or earnings data. Each company card has a short description and a link to the platform.

I did my best to add all relevant companies, but I know there are probably more out there. If you know of any that should be included, please reach out: [email protected].

I plan to add more data on each company, but I wanted to see what interests readers most first. So please reach out with comments!

To access this (free) database, please recommend AI Street to someone you think will get value from reading AI Street. (Please don’t send this to a burner email; I can see where they go 🙂)

Share the link below and after they join, you’ll receive the database by email.

How did you like today's newsletter?

Login or Subscribe to participate in polls.

Reply

or to participate.