🦥 We built a pixel-art office where five cats do your data analysis while a sloth naps 🐱

Description and use

The tool locally processes datasets, automating profiling, duplicate detection, and charting, then explains findings using a local Gemma 3 model.

Problem

Data analysts spend repetitive time on exploratory analysis steps such as profiling, quality checks, and starter charts before interpreting results.

Outcome

The assistant automates the repetitive first pass of exploratory data analysis, keeping all data on the local machine and providing explanations, code, and visualizations without external API calls.

Workflow

• Upload CSV/TSV/Excel file
• Python pipeline computes statistics and generates charts
• Gemma 3 (via Ollama) generates plain‑English explanations and code
• Guard removes any sentence containing a number not in the data
• User can ask follow‑up questions in chat
• Export results as ZIP or Jupyter notebook

Evidence

Every dataset starts the same way: df.head(), count the missing values, find the duplicates, draw a histogram, repeat. So we handed that work to a team of cats.

Source

Purrrfessorrr Slothhh is a local-first data analysis assistant. Upload a CSV, TSV, or Excel file, and a very sleepy sloth professor delegates the work to five specialist cats. Your data never leaves your machine.

Source

Python computes every number. The analysis is a plain, documented pipeline, so the same file always gives the same report.

Source

Gemma only explains. It sees a summary of the computed results, not your raw rows. A guard then removes any sentence containing a number that isn't in the real data.

Source

The app refuses to talk to any model that isn't on localhost.

Source