Metabase is a great first BI tool. Kater is the one your agent can build.
Metabase gets a team from zero to dashboards in an afternoon. As the dashboards multiply, metrics drift, and the work stays in a GUI that agents find hard to use. Kater keeps every model, query and dashboard as a file in git, with each metric defined once in SQL.
In Kater
Kater does not charge per viewer or per dashboard.
Kater vs Metabase at a glance
Kater and Metabase, feature by feature
Feature
Kater
Metabase
Building with agents
Source of truth
Yes.Files in git: models, queries, charts, dashboards and apps. Every save is a commit.
In part.Metabase’s own database. Remote Sync pushes YAML to git on paid plans, with one branch for each instance.
Coding agents
Yes.Claude Code, Codex and Cursor edit the files through the Kater MCP, or in a local copy.
In part.An MCP server can create questions and dashboards. Users report that agents struggle with the git files.
Checks on changes
Yes.A write through the MCP compiles first and is refused on error. Every change has a diff, History and Undo.
In part.Revision history on questions and dashboards.
Answers in your own AI
Yes.People ask in Slack, Claude or ChatGPT. The agent sees only what that person can see.
Yes.Metabot in every plan, with Slack and an MCP server.
Metrics and trust
Shared metrics
Yes.Kater SQL: your warehouse’s SQL with DIMENSION, MEASURE and EVAL. Defined once, read everywhere.
In part.Metrics are query-builder formulas on one data source. Metabase advises against joins in them.
Dashboards and apps
Build without code
Yes.Select fields, a chart and a place on the dashboard, all in the browser.
Yes.A query builder that non-technical people like.
Charts and layouts
Yes.More than 25 chart kinds, and HTML apps for any layout.
In part.Clean, simple charts, with limited control.
Scheduled delivery
Yes.Dashboards sent to Slack on a schedule, each person with their own rows. Your agent can run workflows on a schedule.
Yes.Dashboard subscriptions and alerts by email and Slack.
Platform
Warehouses
In part.Snowflake and DuckDB today.
Yes.Many databases, including Postgres, MySQL, BigQuery and Snowflake.
Open source
No.Not open source. Your content is files you can clone and keep.
Yes.Open source, and free to host yourself.
Embedding
No.No embedding (for now). It is in development.
Yes.Embedded dashboards and an embedding SDK.
Where Metabase is ahead
Metabase does some things better today. Here is each one, and why teams still
select Kater.
Where Metabase is aheadWhy teams still select Kater
Free and open source
You can host Metabase yourself at no cost and have dashboards the same day.
Why teams still select Kater
Kater is a paid product. Teams select it when drifted metrics and hand-built dashboards cost more than a tool. Your content stays files you can clone and keep.
More warehouses
Metabase connects to Postgres, MySQL, BigQuery and many more. Kater connects to Snowflake and DuckDB today.
Why teams still select Kater
Kater goes deep on each warehouse it supports. Queries run live, and the compiler checks each SQL dialect before a query runs. Have a warehouse we do not support? Request it.
Metabase emails dashboards and alerts on a schedule.
Why teams still select Kater
Kater sends a dashboard to Slack on a schedule, and each person gets their own rows. Your agent can run a workflow on a schedule, such as a Monday brief.
Embedding
Metabase embeds dashboards in your own product, with an SDK.
Why teams still select Kater
Kater has no embedding (for now). It is in development. Until it ships, apps export to PDF, PowerPoint, Word and Excel for readers outside Kater.
Metabase is free to host yourself. Cloud Starter is $100 a month with 5 users, then $6 for each user. Pro is $575 a month with 10 users, then $12 for each user. Enterprise starts at $20,000 a year. Git sync and row-level permissions need Pro or Enterprise.
Kater
A 30-day free trial with every feature, then a subscription quoted for your team. Kater does not charge per viewer or per dashboard. Kater runs no chat of its own, so answers run in the agent your team already uses.
Moving from Metabase
Most Metabase content is questions on tables. Your agent rebuilds them as queries on a shared model, so each metric is defined once.
What each Metabase object becomes in Kater
In Metabase
In Kater
Database connection
Connection, on Snowflake or DuckDB
Table metadata
Database dataset, written by schema sync
Model
Kater dataset, or a custom SQL dataset
Metric
MEASURE in the shared layer
Question, in the builder or in SQL
Query file, with a chart
Dashboard
dashboard.yaml
Collection
Folder, with Viewer, Editor and Manager access
Subscription
A schedule in the dashboard's dashboard.yaml, sent in Slack
Ask your agent to migrate one dashboard. Kater rebuilds it as a private draft on your warehouse, and you compare the numbers before you publish.
Yes, for teams that have outgrown a GUI. Kater gives you governed metrics in SQL, dashboards, apps and AI answers, and every layer is a file your agent can build.
Is Kater open source?
No. Your content is files in git, so you can clone a local copy and keep it. You can also write the shared layer back to your own GitHub repository.
Can non-technical people use Kater?
Yes. They read dashboards and apps in the browser, or ask their own agent in Slack, Claude or ChatGPT. Every answer uses the same governed metrics.
Does Kater connect to Postgres or MySQL?
Not today. Kater connects to Snowflake and DuckDB. If you run something else, tell us.
Can we keep Metabase and add Kater?
Yes, for as long as you want. Both read the same warehouse. Keep Metabase for its dashboards, and add Kater to give your team’s agent one definition for each metric, your context and your access rules. When you want, rebuild one dashboard in Kater, compare the numbers with Metabase, then move the next one.