supabase/evals

Evaluating agents across Supabase

About the project

Supabase Evals is a test suite for measuring how well AI agents perform tasks involving Supabase, using defined scenarios, scorers, starting states, agent runtimes, and model experiments. It is for comparing agent and runtime configurations across local or hosted Supabase-like environments and recording their results. The catalogue add-ons support working with these evaluations.

150Stars on the repository

4Mods indexed here, across every type

yesterdayLast push, which is what freshness is scored on

Apache-2.0Licence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

supabase

supabase/evals

MCP server Claude CodeCodexCursor +2 ✓ vendor

MCP server "supabase", hosted remotely at localhost, as configured in supabase/evals.

not rated 150 +1 yesterday A tokens not measured original Apache-2.0