Dreambase.com
Fully integrated analytics from Supabase. Free to use.
417 followers
Fully integrated analytics from Supabase. Free to use.
417 followers
Dreambase is AI-native analytics for Supabase, powered by Skills. A Skill bundles your data sources, business logic, and visualization rules so Dreambase agents always understand your business. Connect Supabase, define your Skills, and get production dashboards and reports in seconds. No tracking SDKs, no ETL, no warehouse. Free to start.
This is the 2nd launch from Dreambase.com. View more
Dreambase Data Agent Skills
Launched this week
Today we're introducing Dreambase Skills, a composable layer that bundles your data sources (Supabase tables, Stripe, PostHog, any API or MCP), business logic, and visualization rules into reusable units our agents use to build accurate dashboards and reports. Onboarding scans your database and prepopulates Skills automatically. Coming soon via CLI, API, and MCP so other agents can consume them too.
Free Options
Launch Team / Built With
Dreambase.com
Antimetal
Congrats @alwaysunday and team - pumped for you!
ProdShort
How accurate is the onboarding scan auto-population feature for a database with unclear or inconsistent table names that don't follow standard SaaS conventions?
Dreambase.com
The "define once, reuse everywhere" approach to business logic makes a lot of sense - tired of re-explaining what my data means every time I ask an agent to build a report. Using Supabase for auth and data in my own SaaS project, and the gap between raw tables and useful dashboards is real. Does the auto-scan onboarding handle Supabase RLS policies, or does it only look at the schema?
Dreambase.com
skills as a composable layer is smart — way better than the agent reverse-engineering your schema every run. how do skills handle changes when someone alters a Supabase table? do they break loud, or silently drift?
Dreambase.com
@tijogaucher Hey Tijo, I am one of the engineers at Dreambase. From our perspective; breaking structural changes should never go unnoticed, normal data evolution should be adapted smoothly, and everything needs to be inspectable! That's how we have built Dreambase and we will continue to expand that visibility, which is a core part of data analytics. Leveraging AI and Agentic analytics should never uppend this responsibility. We are already working on enhancing our detection of breaking changes in our skills data sources so we can alert skill creators faster!
Dreambase.com
Hey, Eduardo here, founding engineer at Dreambase.
A few things I'm proud of in this release:
Skills aren't a config file. They're a composable unit that bundles connectors (Supabase tables, Stripe, PostHog, any API or MCP), business logic, formatting rules, and viz preferences. Our agents read Skills as context, loads them manually if selected or on demand depending on user intent and also analyze your data schemas live when necessary to see if there are any misalignments or additional considerations, which is why queries actually match how your business works.
Onboarding scans your Supabase schema and auto-generates a starter set of Skills. From there, the Skill Builder is a plain-language wizard that picks the right tables and connectors for whatever you're trying to track.
Soon, Skills will be accessible via CLI and MCP, so other agents and platforms can consume them too. If you're building agentic tooling on top of Supabase data, this is the part I'm most excited about.
Happy to nerd out on the architecture, the agent stack, or how we handle schema drift. Ask me anything.
Analytics without ETL or extra setup sounds great… curious how well it holds up with more complex data.
Dreambase.com