A visually stunning AI-powered trading workstation that streams live market data, simulates portfolio trading, and integrates an LLM chat assistant that can analyze positions and execute trades via natural language.
Built entirely by coding agents as a capstone project for an agentic AI coding course.
- Live price streaming via SSE with green/red flash animations
- Simulated portfolio — $10k virtual cash, market orders, instant fills
- Portfolio visualizations — heatmap (treemap), P&L chart, positions table
- AI chat assistant — analyzes holdings, suggests and auto-executes trades
- Watchlist management — track tickers manually or via AI
- Dark terminal aesthetic — Bloomberg-inspired, data-dense layout
Single Docker container serving everything on port 8000:
- Frontend: Next.js (static export) with TypeScript and Tailwind CSS
- Backend: FastAPI (Python/uv) with SSE streaming
- Database: SQLite with lazy initialization
- AI: OpenAI GPT-5.4 mini with structured outputs
- Market data: Built-in GBM simulator (default) or Massive/Polygon.io API (optional)
# Clone and configure
cp .env.example .env
# Add your OPENAI_API_KEY to .env
# macOS/Linux
./scripts/start_mac.sh
# Windows
./scripts/start_windows.ps1
# Or run directly with Docker
docker build -t finally .
docker run -v finally-data:/app/db -p 8000:8000 --env-file .env finallyOpen http://localhost:8000.
| Variable | Required | Description |
|---|---|---|
OPENAI_API_KEY |
Yes | OpenAI API key for AI chat |
MASSIVE_API_KEY |
No | Polygon.io key for real market data; omit to use the built-in simulator |
LLM_MOCK |
No | Set true for deterministic mock LLM responses (testing) |
finally/
├── frontend/ # Next.js static export
├── backend/ # FastAPI uv project
├── planning/ # Project documentation and agent contracts
├── scripts/ # Start/stop helpers (Mac and Windows)
├── test/ # Playwright E2E tests
└── db/ # SQLite volume mount (runtime)
See LICENSE.