Expense Tracker

---

✨ Overview

Expense Tracker is a modern, open-source platform to manage your expenses with conversational AI. Self-host and own your data, powered by FastAPI, Supabase, and LangGraph.

---

🚀 Self-Hosting Guide

1. Clone & Install

git clone <repo-url>
cd expense_tracker
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

2. Get API Keys

• Sign up at Supabase
• Create a new project
• Go to Project Settings → API
• Copy your SUPABASE_URL and SUPABASE_KEY
• Create a .env file in the root:

SUPABASE_URL=your_supabase_url
SUPABASE_KEY=your_supabase_key

3. Setup Supabase Database

Create the following tables in Supabase:

user

Column	Type	Notes
user_id	uuid	Primary Key
user_name	text
email	text	Unique
password	text	Hashed
thread_id	uuid	Nullable

category

Column	Type	Notes
category_id	uuid	Primary Key
user_id	uuid	FK → user
name	text
description	text	Nullable

expense

Column	Type	Notes
expense_id	uuid	Primary Key
user_id	uuid	FK → user
category_id	uuid	FK → category
amount	float
created_at	timestamptz	Default now()

---

🔑 Authentication Flow

1. Sign Up:
   • POST /auth/signup — Register a new user
2. Sign In:
   • POST /auth/signin — Login and receive a token
3. Start Conversation:
   • POST /user/start — Begin a chat session with a prompt
4. Human Feedback Loop:
   • If response contains human_feedback: true, call POST /user/continue with your prompt to continue the conversation

---

📚 API Endpoints

User Endpoints (/auth, /user)

• POST /auth/signup — Register
• POST /auth/signin — Login
• POST /user/start — Start conversation
• POST /user/continue — Continue conversation (if human_feedback: true)

Category Endpoints (/category)

• POST /category/add — Add a new category
• GET /category/get — List your categories

Expense Endpoints (/expense)

• POST /expense/add — Add an expense
• GET /expense/get — List expenses (implement as needed)

---

🛠️ Technologies Used

• FastAPI — Modern Python web framework
• Supabase — Postgres DB & Auth
• LangGraph — Conversational AI workflow
• Pydantic — Data validation
• Docker (optional) — Containerization

---

🖼️ Example Usage

# Signup
curl -X POST http://localhost:8000/auth/signup -H "Content-Type: application/json" -d '{"user_name": "alice", "email": "alice@example.com", "password": "password123"}'

# Signin
curl -X POST http://localhost:8000/auth/signin -H "Content-Type: application/json" -d '{"email": "alice@example.com", "password": "password123"}'

# Start conversation
curl -X POST http://localhost:8000/user/start -H "Authorization: Bearer <token>" -H "Content-Type: application/json" -d '{"prompt": "Track my coffee expense"}'

---

🤝 Contributing

Contributions welcome! Please open issues or PRs.

---

📄 License

MIT