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

Описание и применение

Приложение локального анализа данных, которое автоматически выполняет первичный анализ, генерирует графики, код и объяснения, не отправляя данные в облако.

Задача

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

Результат

The tool automates repetitive exploratory analysis steps locally, producing reports, charts, code, and explanations without external API calls.

Рабочий процесс

• Upload CSV/TSV/Excel file
• Python pipeline computes outliers, duplicates, type problems, generates charts, writes Python/R code, suggests cleaning steps
• Gemma 3 (via Ollama) generates plain-English explanations from computed summaries
• Guard removes any sentence containing a number not present in the data
• User can ask follow-up questions in chat
• Export results as ZIP or Jupyter notebook

Доказательства

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.

Источник

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.

Источник

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

Источник

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.

Источник

The repetitive first pass of exploratory analysis (profiling, quality checks, starter charts, boilerplate code) happens in one guided workflow, so you spend your time on what the data means. We haven't benchmarked the time saved, so we won't claim a number.

Источник