AI-powered nutrition & wellness tracker built for college students.

Runs 100% locally — no cloud accounts, no API keys, no internet required.

You need three terminals: one for the backend, one for the frontend, and one for the AI model.

git clone https://github.com/Arths17/CampusFuel.git
cd CampusFuel

✅ A .env file is already included — no extra configuration needed.

CampusFuel uses Ollama to run the AI chat locally. Install it, then pull the model:

# Pull the llama3.2 model (downloads ~2 GB, one-time only)
ollama pull llama3.2

Start the Ollama server (keep this running):

ollama serve

✅ Ollama runs at: http://localhost:11434
You can verify it's working: curl http://localhost:11434/api/tags

# Install Python dependencies (first time only)
pip install -r requirements.txt

# Start the FastAPI backend
python3 -m uvicorn main:app --host 0.0.0.0 --port 8000 --reload

✅ Backend running at: http://localhost:8000
📖 API docs at: http://localhost:8000/api/docs
🩺 Health check: curl http://localhost:8000/api/health

First time only — if you use a virtual environment:

python3 -m venv .venv
source .venv/bin/activate        # macOS/Linux
# .venv\Scripts\activate         # Windows
pip install -r requirements.txt
python3 -m uvicorn main:app --host 0.0.0.0 --port 8000 --reload

# Install Node dependencies (first time only)
npm install

# Start Next.js dev server
npm run dev

✅ Frontend running at: http://localhost:3000

Go to http://localhost:3000 in your browser.

This account works out of the box — no signup needed.

1. Click Sign Up → enter a username & password
2. Complete the onboarding survey (height, weight, diet goals, activity level)
3. You'll land on the Dashboard — fully personalized to your profile!

No internet or cloud accounts required. All data is stored locally in JSON files.

All user data is stored locally in the project folder — no database setup needed:

Backend won't start — ModuleNotFoundError

pip install -r requirements.txt

Port already in use

lsof -ti :8000 | xargs kill -9   # free backend port
lsof -ti :3000 | xargs kill -9   # free frontend port

AI chat not responding

# Make sure Ollama is running
ollama serve

# Verify the model is downloaded
ollama list   # should show llama3.2

"Cannot connect to backend" / all API calls fail
→ Make sure the backend is running in its terminal on port 8000.
→ Test: curl http://localhost:8000/api/health — should return {"status":"ok",...}

Login says "User not found" for a new account
→ The account may not have saved. Check that users.json exists in the project root and is writable.

Meals/water/workouts showing empty after refresh
→ Check that the user_profiles/ folder exists and is writable:

ls user_profiles/

• 🥗 Personalized nutrition goals — BMR + TDEE calculated from your survey answers
• 💧 Water tracker — click to log daily glasses
• 🍽 Meal logger — search & log from 5,797 USDA foods
• 💪 Workout tracker — log exercises & view weekly history
• 🤖 AI chat — local Ollama nutrition assistant (no API key needed)
• 📊 Weekly calorie chart — visualize your intake over 7 days
• 👤 Profile management — update goals and change password

Built at HackTAMS 2026 by the Elden Ring Committee 🗡️