I Built a Local AI Pet That Yells at You to Go Outside — No Cloud, No API Keys

Description and use

Miso is a local desktop pet that uses an open‑weight LLM to remind users to go outside, running entirely offline on low‑spec hardware.

Problem

Users with low‑spec hardware want a private, offline AI companion that reminds them to take breaks without sending data to the cloud.

Outcome

Miso demonstrates that a memory‑efficient, offline AI companion can run on low‑spec hardware, providing personalized reminders without cloud dependencies.

Workflow

• Clone the repository from GitHub
• Create a Python virtual environment and activate it
• Install dependencies with pip
• Download the required .gguf models via the provided script
• Run the application with python main.py (or install.bat on Windows)

Evidence

Miso is a cute, interactive desktop pet that sits in the corner of your screen. It works with you, not against you. The pet tracks how long you have been focused, and when your timer runs out, it gets angry (in a cute way) and literally tells you to go outside and touch grass using an open-weight language model running entirely on your laptop.

Source

This is a Progressive Desktop Widget — fully offline, open-source, local-only, and designed specifically for low-end hardware (i7-6600U / 8GB RAM). Zero cloud APIs. Zero subscriptions. Zero data leaving your computer.

Source

Quick start
bash
git clone https://github.com/CodewithTanzeel/touch-grasschallenge-miso.git
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python scripts/download_models.py
python main.py
Windows: .\install.bat

Source