TNTaha Naseem

Real-time AI trading

Le Flux

A multi-model trading arena that turns live crowd positioning and market data into scheduled AI decisions.

Professional product

Privacy-safe interface composition based on the shipped product.

My contribution

Built the complete arena platform: TypeScript API, PostgreSQL model, real-time services, LLM orchestration, dashboard, monitor, and deployment.

The challenge

What the system had to solve

Live market data, crowd behavior, multiple AI models, cost controls, and trading-session rules had to stay synchronized in one observable system.

Product surface

Modules and functionality

  1. 01

    AI model seats and scheduled cycles

  2. 02

    Live crowd-position ingestion

  3. 03

    Market bars and session controls

  4. 04

    Leaderboard, trades, and P&L history

  5. 05

    Prompt registry and cost tracking

  6. 06

    Live risk monitor and WebSocket updates

Engineering

Decisions that shaped the build

  1. Orchestrated multiple OpenRouter models from one controlled scheduler.
  2. Combined position polling, market-data WebSockets, bar aggregation, and PostgreSQL persistence.
  3. Kept long-lived API credentials out of the browser through a server-side PHP proxy.
  4. Preserved an existing monitor contract while adding the new Arena API surface.

Outcome

What the work delivered

  • Created one live environment for comparing model decisions against the same market context.
  • Made model behavior, costs, trades, and rankings observable from a dedicated dashboard.
  • Deployed independent server and dashboard surfaces with automated restart and delivery workflows.

Technology

Core stack

  • TypeScript
  • Fastify
  • PostgreSQL
  • OpenRouter
  • WebSockets
  • PHP