Introducing: anfra, an open-source engine for trusted analytics with AI agents.
Your coding agent builds the app in HTML, JS and any chart library. anfra connects it to governed metrics, with drill-downs, comparisons and lineage built in.
https://t.co/qFKGrtaaiz
@teodorio AI has already compressed a lot of the work inside data teams. It's only a matter of time before it combines the roles too.
I think it's interesting that both are happening at once: the data stack is being re-bundled, and the data roles are getting bundled with it.
Day 3 of building @anfraAI
We picked one of @tableau's best dashboards to see if we could build one just as good (or better) with anfra.
Tableau is known for great visualisations, especially maps. Sales territory planning is a common example to demonstrate its frontend visualisation strengths.
So we used anfra to one-shot a sales territory planning app in one shot.
You can spin the globe to see where the company already wins and where it's missing revenue, compare every market on any metric, and zoom from countries down to states and cities.
Every metric and every interaction is auditable and grounded in a semantic layer.
Take about 20 minutes.
What do you think?
web developers have had DevTools for 20 years.
data teams still debug with screenshots in Slack.
so we built DevTools for BI at @anfraAI .
meet Inspect: point at any number, see the SQL that ran, trace it to the table.
your agents can get it too, via the CLI.
check out: https://t.co/2U8KAFUvFE
Day 2 of building open-source analytics engine in public. Let’s talk about low-cost, open-souce data stack.
Since building @anfraAI I have been trying this setup out, and it has soon become my new favorite open-source/almost $0 agentic data stack.
1. @duckdb (self hosted) or @motherduck free plans for data warehouse.
2. @dltHub and @getdbt for ELT (open-source). If it’s simple tables/sources, I might just skip them or hand-roll something with agents.
3. AMQL (https://t.co/vIwLeKWMie) as a semantic layer, metrics definition. It ships with anfra. It is static-typed with composable/programmable consturcts (not YAML-based strings).
4. anfra as the open-source agentic analytics engine + custom BI apps frontend. Either self-host or free cloud.
The main cost is just usually hosting, which I typically go with a @Hetzner_Online VPS box ($7/mo), best bang for the bucks I can find.
If the data volume is low, I just go with Motherduck free plan (10 GB free storage) + anfra Cloud (free plan) to save the management hassle.
Contexts are either markdown files, dbt descriptions or Notion, that get ingested into anfra via anfra context layer.
All this is set up with coding agents (Claude Code, Codex or @opencode). I rarely look at the code anymore.
What you get:
- Interactive, customizable dashboards on top of a governed analytics backend
- Everything stored as code, checked in to Git
- Connect ChatGPT/Claude to anfra MCP and you get AI analytics with trusted metrics for free (no extra API token cost)
What does your low-cost agentic data stack look like?
Day 2 of building anfra:
Sales asked if we should change the dates on our changelog so it looks like we ship one feature a week.
They worried that releasing a bunch of features on the same day would look fake.
This is how fast we actually ship. The changelog is generated straight from our code repo. Shipping once a week is how software used to be built. It's not how we build it now.
Check out anfra and our release notes. If you don't find what you need, trust that it's coming your way at the speed of light.
@UIbyBiba Let Claude handle the frontend, use anfra for the backend, and you can also have your own governed, fully interactive BI app.
https://t.co/9W3WHIhILt
@sh_reya 💯 agree. On (2), most AI analysis today ends up as a chat nobody else can use, or a screenshot with the queries stripped out. Efficient communication is something people can open, check, trust, and then build on. We're building anfra around exactly that.
https://t.co/9W3WHIhILt
Introducing: anfra, an open-source engine for trusted analytics with AI agents.
Your coding agent builds the app in HTML, JS and any chart library. anfra connects it to governed metrics, with drill-downs, comparisons and lineage built in.
https://t.co/qFKGrtaaiz
@HoytEmerson Most data consultancies we work with win clients by building a really really custom demo on the client's own data. Agents make that demo much faster to build, so it makes sense more folks are thinking about starting one.