Fabi 2.0 – An AI analyst that connects to all your data sources
Hey HN! Today we’re launching Fabi 2.0 For the past year we’ve been working with a number of product, eng, marketing and data teams, and the common issue we’ve been seeing with all these teams, especially small and growing teams, is that getting basic answers from their data requires jumping between a bunch of different tools/copy-pasting data and spreadsheets, or building out a full BI stack. With our latest release, users can not only connect Fabi to databases and data warehouses, but also to applications like HubSpot, Stripe, Shopify etc. We offer hundreds of connectors, and the AI…
What it does
In the maker’s words, at launch
Hey HN! Today we’re launching Fabi 2.0 For the past year we’ve been working with a number of product, eng, marketing and data teams, and the common issue we’ve been seeing with all these teams, especially small and growing teams, is that getting basic answers from their data requires jumping between a bunch of different tools/copy-pasting data and spreadsheets, or building out a full BI stack. With our latest release, users can not only connect Fabi to databases and data warehouses, but also to applications like HubSpot, Stripe, Shopify etc. We offer hundreds of connectors, and the AI makes it dead simple to start immediately building out analyses or dashboards. A bit about what’s going on under the hood: - We use Fivetran to connects to data sources (we tested at a number of different ETL solutions and Fivetran really stood out) - We pipe the data into a MotherDuck instance for each customer - We index data and metadata and store in our vector DB to get it ready for the AI. A lot of connectors just work without any further modeling, but some do require a bit of extra modeling. For those we automatically spin up dbt models to do some data wrangling under the hood - We offer an extra AI config layer for users to provide any additional context about their business and data source which they can write in plain English, which we’ve found to be really important to make it accessible to a wide set of teams Once the data is ready, you can start talking to it to analyze it like you could before in Fabi with any traditional SQL DB. You can give it a try here: [https://app.fabi.ai/](https://app.fabi.ai/home)
Does the same job
all alternatives →
- AAAI analyst agent – Seamlessly switch between chat and build modeOct 2025 · fabi.ai · ▲5
Hey, I'm Marc one of the co-founders of Fabi! We've all seen the "chat with your data" or the "AI-as-an-assistant" when building reports, but we felt like this wasn't quite right. So we decided to build a system that allowed users to: * Connect any data source to the AI * Purely chat with the AI and their data (so we show the output right in the chat before you even apply the changes) * Convert that chat to a repeatable analysis with a data app or workflow * Toggle back to chat mode without missing a beat Basically this means that if you're a data person, you don't have to go through these…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
