Project Info
NexSpend
An AI-powered personal finance companion for capturing expenses naturally and understanding where your money goes.
NexSpend helps users track expenses, understand spending habits, and make smarter financial decisions through AI-powered insights, voice expense tracking, and natural language expense entry.
Built with: Flutter · Riverpod · Supabase · PostgreSQL · FastAPI · Groq
Portfolio highlights
- A full-stack mobile product, not just a user interface: Flutter client, FastAPI service and Supabase-backed data layer.
- Three ways to log an expense: manual entry, voice input and plain-language input.
- An AI copilot and visual analytics turn recorded transactions into practical spending insights.
- Privacy controls, local preferences and Android APK support are included in the v1 scope.
Development note
GPT-5.6 (Codex) supported development, including Flutter implementation, Supabase integration, state management, debugging and UX iteration. The developer made the final product, integration, testing and architectural decisions.
Features
Smart Expense Tracking
- Manual expense entry
- Voice expense entry
- Natural language expense entry
- Automatic categorization
Examples:
- Spent ₹450 at Starbucks
- Uber ride ₹250
- Bought groceries for ₹1800
- Spent ₹1600 at H&M
AI Financial Copilot
Ask questions like:
- Where did I spend the most money this month?
- How much did I spend on food?
- Can I afford AirPods next month?
- Compare this month with last month.
Insights & Analytics
- Monthly spending trends
- Category breakdowns
- Top merchants
- Spending health indicators
- Budget tracking
Privacy & Security
- Privacy Mode
- Local settings persistence
- Theme customization
- Currency preferences
Tech Stack
Frontend
- Flutter
- Riverpod
- Material 3
Backend
- Supabase
- PostgreSQL
- FastAPI
AI
- Groq API
Installation
Frontend
cd frontend
flutter pub get
flutter run --dart-define-from-file=../.env
Backend
cd backend
pip install -r requirements.txt
uvicorn app.main:app --reload
Environment Variables
Create a root .env file containing:
SUPABASE_URL=
SUPABASE_ANON_KEY=
GROQ_API_KEY=
Project Status
Release v1 ✅
Core features complete:
- Authentication
- Expense Tracking
- Voice Entry
- Natural Language Parsing
- AI Copilot
- Insights Dashboard
- Privacy Mode
- Android APK
Analysis
View
Metric
- 8
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CIn code
- C++In code
- DartIn code
- FastAPIIn code
- HTMLIn code
- KotlinIn code
- PythonIn code
- SQLIn code
- SwiftIn code
- PostgreSQLClaimed
- SupabaseClaimed
9 of 11 appear in the indexed code. 2 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
250 KB
Source files
98
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
nehalsinghpunjabi/NexSpend
191 files · 663 KB · @ 5a4e029
Structure
Interface
13 files · 7%Screens, components and styles rendered to the user.
Application logic
99 files · 52%Domain rules, services and shared utilities.
+2 moreData & schema
12 files · 6%Schema definitions, migrations and data access.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Dart79%
- C++8%
- C3%
- XML2%
- YAML2%
- SQL1%
- Other (5)4%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
backend/requirements.txt
pypi · 2- fastapi
- uvicorn[standard]
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.