Metabase
Metabase is open-source business intelligence. It connects to the databases you already run, lets non-technical staff ask questions through a point-and-click editor while analysts drop to SQL when they need to, and turns the results into dashboards, scheduled email reports and alerts. One Docker container gets you a working instance in minutes.
View the repo · metabase/metabase ↗Teams who rebuild the same spreadsheets by hand every month and want self-serve dashboards instead, and finance or operations leads who want one agreed set of numbers on screen rather than five versions in circulation. It assumes your data already lives in a queryable database; if the numbers are scattered across SaaS tools, the pipeline that lands them somewhere queryable comes first, and matters more than the dashboard.
Install itdocker run -d -p 3000:3000 --name metabase metabase/metabasePoint it at a read replica rather than your production database, because one enthusiastic dashboard can degrade a live application. Model the data and define shared metrics early, or every team will quietly compute revenue differently and the arguments will follow. Manage permissions from the start, since a BI tool concentrates the whole business in one place, and note that the open-source edition has coarser access controls than the paid tiers.
Where Blash AI comes inWe connect Metabase to your finance and operations data, build the handful of dashboards that actually get used, and pair it with AI workflows that draft the monthly commentary a human then edits. Fed by pipelines in n8n and sitting over a properly modelled database, it becomes the reporting layer of a build rather than another tool nobody opens.
When you want this running on your real stack, that is the engagement
Book an AI audit →n8n →
n8n is workflow automation you run on your own infrastructure. It connects the applications a business already uses through a visual editor, with hundreds of prebuilt nodes, a code step for anything bespoke, and native support for calling language models mid-flow. Think of it as a self-hosted alternative to Zapier or Make that you own outright, including every piece of data passing through it.
Ollama →
Ollama runs open-weight language models on your own machine or server. One command downloads a model and serves it behind a local API that most existing AI tooling can talk to, so an application built against a hosted provider can point at your own hardware instead. Sensitive data stays inside your network, there are no per-token fees, and it keeps working with no internet connection at all.
LiteLLM →
LiteLLM is a gateway that lets you call models from Anthropic, OpenAI, Google and many other providers through one consistent API. It runs as a Python library inside your code or as a standalone proxy server in front of your whole stack, with cost tracking, per-key budgets, rate limits and automatic fallbacks for when a provider has a bad day.