Everyone should be a data analyst. Turn questions into insights instantly with AI and billions of rows of data on crypto, sports, and everything in between📊
learn more here 👉
Joined July 2024
- Tweets968
- Following25
- Followers1.7K
- Likes588
Baselight retweeted
We started Finisterra Labs with a clear vision: to index the world’s structured data.
Over the last two years, we've amassed over 510 billion rows of data across 87,000 datasets. It’s been an incredible journey building a platform that changed how we interact with data. 🧵
Baselight retweeted
Building one of these agents with @BaselightDB would be literally minutes (actually, connecting the Baselight's MCP to any of the existing coding agents could get you this out of the box).
Context is all you need!
We are currenlty missing the datasets required to implement this exact one, but I am really excited about this work and similar use cases that are surfacing for niche agents.
Soon we will incentivise devs to distribute their datasets for Baselight to build the knowledge base for agents so any niche agent can be built out of the box :)
Huge fan of this one @tarikjmoody 🙌 Thanks!
I'm building the Claude Code for real music lovers, DJs, music journalists, and radio programmers (inspired by @virattt's Dexter Finance CLI.
Crate, built on the Claude Agent SDK, is a personal research assistant AND music workspace for DJs, collectors, music journalists, and serious listeners.
Here's the problem it solves: If you want to know who played bass on a specific album, what year a rare pressing came out, how much it's worth, or how two artists are connected, you'd normally have to bounce between five or six different websites, cross-referencing everything manually. It's tedious. And most people just give up.
Crate does all of that digging for you in seconds.
You ask a question in plain language — "Who produced the original pressing of this record?" or "Show me everything this session musician played on in 1974" — and Crate searches across multiple music databases simultaneously (Discogs, MusicBrainz, Genius, Bandcamp, and more), then brings back a single, connected answer.
Think of it as having a record store clerk with an encyclopedic memory, a music librarian, and a pricing guide — all rolled into one AI-powered tool you can talk to from your terminal.
Baselight retweeted
What’s the most cited scientific publication ever?
We just made it possible to answer questions like this instantly.
OpenAIRE Graph is now available in @BaselightDB - one of the world’s largest open scholarly knowledge graphs, providing a 360° view of global research.
Baselight retweeted
Here’s the @BaselightDB query for the TOP 10 most cited publications (OpenAIRE Graph): baselight.app/u/pjsousa/quer…
Baselight retweeted
Last week we talked about the "SaaSocalypse" and engineers no longer writing code. This week, I accidentally proved it to myself.
I needed a personal finance tracker. Instead of downloading an app, dealing with Excel, or coding one myself, I built "Mr. Malone", a custom financial advisor.
The catch? I didn't write a single line of code. Just English, Markdown files, Claude Code, and @BaselightDB.
This experiment made me realize something huge: Agents aren't just replacing code, they are making applications entirely obsolete. We are officially entering the LLM OS era.
Big thanks to @karpathy for the "Software 3.0" and LLM OS frameworks, and @LynAldenContact for the macro insights that sent me down this rabbit hole.
Link to the full story and the architecture below 👇
Baselight retweeted
And I blame @BaselightDB for this. Having an agent and a global source of data for anything comes pretty handy!
Baselight retweeted
If you want to learn more about how @BaselightDB storage agnostic architecture leverage @WalrusProtocol for datasets storage drop by this space tomorrow
🚨 Data as storage vs data as infrastructure.
There's a difference. A big one.
@AlkimiExchange + @BaselightDB
Thursday, Feb 5 | 5PM GMT / 9AM PT 🦭
Set reminders!
xitter.cf/i/spaces/1YqxolvZPalKv
Baselight retweeted
Data as storage = locked away & wasted.
Data as infrastructure = opens new possibilities & real value.
@AlkimiExchange is redefining adtech, making ads more transparent, verifiable, and efficient.
@BaselightDB does the same for big datasets: turns them into easy-to-use, shareable assets.
Both via Walrus
Thu Feb 5 • 9am PT / 5pm GMT
Host: @DTDaun
Tag a partner, project, or team building with verifiable data who should join this! 🚀
Set your reminder & join the conversation 👇
xitter.cf/i/spaces/1Yqxolv…
Baselight retweeted
Good morning! Today’s the day 🦭
Walrus proves that just storing your data is missed potential. Decentralized infra is the future.
-Verifiable ad impressions with full transparency (@AlkimiExchange)
-Massive datasets turned into queryable, shareable markets (@BaselightDB)
Both live on Walrus.
9am PT / 5pm GMT with @DTDaun
Drop a 🔥 if you’re tuning in later!
xitter.cf/i/spaces/1Yqxolv…
Baselight retweeted
In case it wasn't obvious already why projects like @BaselightDB are more necessary than ever!
We're feeding AI our best work for free, and nobody is talking about what happens next.
AI will scrape every blog and social media post you publish.
AI will scrape every single open-source code you share.
AI will scrape every tutorial you record.
And then, they will sell this info back to you in the form of tokens and soon, ads.
The economics of the future of content creation are broken.
If we don't fix this, we will regret it.
Baselight retweeted
This is one of the key reasons why we started building @BaselightDB.
The goal was to fix it for structured data, but moving forward we will have to extend the model to all digital content.
Actually, @svpino, we would love your feedback on what we are building 🙏
Baselight retweeted
New post in my Critical Infrastructures of our Society Series!
This time, we’re talking Semiconductors.
I explore why the 21st Century is fought over sand, not fuel, and walk you through how ASML and TSMC ended up owning two crucial monopolies in the global value chain.
Read at adlrocha(.)substack(.)com and link below (soon) 👇
Baselight retweeted
It is the pandemic though? Or it has to do with @BaselightDB
Baselight retweeted
We just included in @BaselightDB a dataset for the People's Bank of China. I am really excited about this one because it was always hard to find data from China for my analyses. Now I can use @BaselightDB to research things as cool as the opportunities for a CNY carry trade 👇
Baselight retweeted
This is a feature that I am very fond of. As an active @BaselightDB user I kept seeing myself doing the same kind of analyses over an over again. What if we could automate them so they could be executed with a single click?
Enter @BaselightDB Bases 👇
Bases and Analysts are LIVE in Baselight! 🚀
Start a Base to prepare Baselight AI with all the knowledge needed to chat about a topic. You can also use an Analyst to generate with a single click that analysis you were looking for.
We're launching with Sports, Prediction Markets, and Finance-themed Bases, but more coming soon!
Which Base do you want to see next? Let us know or contribute! 👇
Baselight retweeted
Is the risk premium on corporate debt worth the spread right now?
With interest rates being lowered and government deficits soaring, I I had to know how "safe" my fixed income allocation truly is. Making this analysis using @BaselightDB and its Finance Base took me literally 5 mins. Without Baselight I wouldn't have known were to start.
Link to the full analysis below 👇
What complex analysis would you love to do in 5 mins? Want your team to leverage your data for similar insights? DM me or comment! 🙏
Baselight retweeted
🔥 @BaselightDB making data analytics actually accessible!
No engineering headaches, just clean insights. Building on Walrus 🦭
Most data is locked up, unstructured, or too expensive to access. And @BaselightDB is building the fix.
Talked with @adlrocha about the vision and why they chose @WalrusProtocol.
Don't miss this one. 👇
Baselight retweeted
Looking to trade on today's NFL games using @Kalshi or @RobinhoodApp? Here's my @BaselightDB analysis with a few suggestions :)
Not financial advice, of course, and only for educational purposes. But @BaselightDB is a great data source for prediction markets.
Baselight retweeted
Data shows the way! These are our weekly numbers for data supplied in the platform:
🚣 Rows: 316,215,218,486 (▲ +6.8 B)
⬛ Tables: 306,664 (▲ +70)
💽 Datasets: 57,356 (▲ +21)
All of this data is waiting to be analysed, and this is just a few sentences away. Use Baselight AI to see the magic happen.
