MindEase: A Local AI Mental Wellness Check-In Assistant

Meghana — Sun, 18 Oct 2026 03:36:49 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

I built MindEase, a local AI-powered mental wellness check-in assistant that helps users reflect on their emotions through a conversational interface.

MindEase detects emotional tone and provides supportive responses, motivational quotes, calming techniques, and journaling prompts. It is designed to make everyday emotional reflection more accessible.

Key Features

🧠 Emotion detection for moods such as anxiety, sadness, motivation, and calm.
💬 Conversational memory using LangChain's ChatMessageHistory.
🌿 Calming suggestions, including breathing exercises, grounding techniques, and affirmations.
✍️ Journaling prompts and motivational messages.
🎨 An interactive Streamlit interface.
💾 Downloadable wellness logs for personal reflection.

MindEase could be useful for individuals seeking a simple wellness check-in tool or as a starting point for wellness-focused applications.

It is an experimental wellness tool, not a replacement for professional mental health care.

Demo

The application runs locally using Streamlit.

GitHub Repository: MindEase — Mental Health AI Agent

The repository includes a screenshot of the application's interface.

Code

Explore the source code and setup instructions:

https://github.com/Meghana-2124/mental_health_ai_agent

How I Built It

I built MindEase using Python, Streamlit, LangChain, TextBlob, and Ollama.

Ollama (Gemma 2B): Runs the open-weight language model locally to generate conversational responses.
LangChain: Supports the conversational workflow and memory management through ChatMessageHistory.
TextBlob: Performs basic sentiment analysis.
Streamlit: Provides the interactive user interface.
Python: Connects the different components.

The project follows a four-layer agent architecture:

Input Understanding — processes the user's message.
State Tracker — maintains conversational context.
Task Planner — helps determine an appropriate response approach.
Output Generator — generates supportive responses using the language model.

The project also explores reflection logs, prompt iteration, and output testing.

Why Does Open Innovation Matter?

Open innovation makes AI development more accessible to individual developers who want to experiment and build practical applications without depending entirely on proprietary, paid APIs.

Using Ollama and an open-weight language model allowed me to experiment with local inference and customize the conversational workflow. LangChain and Streamlit helped me integrate the model into an interactive application.

Local inference can also reduce dependence on external AI services and help keep conversation data on the user's device, provided the application does not transmit that data elsewhere.

Building MindEase gave me an opportunity to explore how open AI technologies can be combined to create an interactive wellness application.

Buy or Bye — An AI Purchase Reality Check for My Impulse-Buying Friend

Meghana — Mon, 05 Oct 2026 06:55:58 +0000

Why Does Open Innovation Matter?

Using the open-weight Gemma 3:1b model through Ollama allows Buy or Bye to run its AI explanation layer locally instead of relying on a closed hosted LLM API.

This makes the AI workflow local, controllable, and transparent.

🎥 Demo

Demo video: https://www.loom.com/share/149be4d701334eef9021cf69c96f4ce6

🔗 Project

GitHub Repository: https://github.com/Meghana-2124/buy-or-bye

How the Decision Works

Buy or Bye evaluates:

Budget — Is the product within the user's budget?
Need — How strongly is the product needed?
Usage — How often will it be used?
Existing Product — Is something similar already owned?
Impulse — How impulsive is the purchase?
Cheaper Alternative — Is there a cheaper option that meets the need?

Decision Logic

Python uses deterministic rules to generate one of three verdicts:

BUY  → Purchase factors are generally positive
WAIT → There are reasons to reconsider
BYE  → The purchase does not make sense based on the inputs

The decision is calculated before involving the AI model.

Why Gemma Is Used

Gemma is the explanation layer, not the decision-maker.

Python → Decides
Gemma  → Explains

Python provides the fixed verdict and purchase factors, while Gemma turns them into a short natural-language explanation.

Why SerpApi Is Used

SerpApi provides current web information about the product.

Python  → Personal purchase decision
SerpApi → Current web information
Gemma   → Explanation

The search results provide additional context but do not change the personal verdict.

Example

Product: Headphones
Price: ₹30,000
Budget: ₹50,000
Usage: 15 times/month
Need: 4/5
Similar product: No
Impulse: 2/5
Cheaper alternative: No

Verdict: BUY

Changing the inputs can produce WAIT or BYE.

Technology Stack

Python
Streamlit
Gemma 3:1b
Ollama
SerpApi
Requests
python-dotenv

Project Structure

buy-or-bye/
├── app.py
├── README.md
├── LICENSE
├── requirements.txt
├── .gitignore
└── screenshots/
    ├── main-interface.png
    ├── purchase-reality-check.png
    ├── web-information.png
    └── gemmas-verdict.png

Running the Project Locally

Prerequisites

Python
Ollama
Gemma 3:1b
SerpApi API key

Install Dependencies

pip install -r requirements.txt

Install Gemma

ollama pull gemma3:1b

Configure SerpApi

Create .env:

SERPAPI_KEY=your_serpapi_api_key

Run the Application

streamlit run app.py

Design Philosophy

Each component has a clear role:

Python — decision logic
Gemma — natural-language explanation
SerpApi — current web context

This keeps the system simple and transparent.

Limitations

Buy or Bye is a decision-support tool, not financial advice.

The verdict depends on the user's provided information and does not account for their complete financial situation.

Future Improvements

Price tracking
Product comparison
Better alternative discovery
Purchase history
Personalized spending insights
Additional open-weight models

Prize Categories

Gemma

Uses Gemma 3:1b as the core open-weight AI explanation layer through Ollama.

SerpApi

Uses SerpApi for current web information about products.

License

This project is released under the MIT License.

Final Thought

"Is this product worth buying?"

Maybe the better question is:

"Is this purchase worth it for me?"
Yes.

DEV Community: Meghana

MindEase: A Local AI Mental Wellness Check-In Assistant

What I Built

Key Features

Demo

Code

How I Built It

Why Does Open Innovation Matter?

Buy or Bye — An AI Purchase Reality Check for My Impulse-Buying Friend

Why Does Open Innovation Matter?

🎥 Demo

🔗 Project

How the Decision Works

Decision Logic

Why Gemma Is Used

Why SerpApi Is Used

Example

Technology Stack

Project Structure

Running the Project Locally

Prerequisites

Install Dependencies

Install Gemma

Configure SerpApi

Run the Application

Design Philosophy

Limitations

Future Improvements

Prize Categories

Gemma

SerpApi

License

Final Thought