JoNino
JoNino is a multi-agent AI trading command centre that solves information overload for day traders.
Core trick
Natural-language rules are evaluated by Gemini against live transcripts, chart screenshots and news sentiment, firing trade actions on match.
Description
JoNino is a multi-agent AI trading command centre that solves information overload for day traders. It consolidates live earnings calls, stock charts, SEC filings, and news into a Bloomberg-style tiled workspace where six Gemini-powered AI agents watch, analyse, and act in parallel.
Set rules in plain English — "if sentiment turns negative about Intel, set a stop-loss" or "if double top on AAPL, sell" — and the system monitors all sources autonomously. Gemini Live transcribes video in real-time, Gemini Pro analyses SEC filings and chart screenshots via vision, and Gemini Flash scores news sentiment. When a rule fires, an action card appears with reasoning and confidence. Execute trades to Alpaca paper trading manually or on auto.
Every trade flows through a learning loop: a reflection agent classifies decisions using Van Tharp's process-outcome matrix and extracts lessons that tune future thresholds — so the system improves with every trade it makes.
README excerpt
# JoNino
A multimodal, multi-agent AI trading command centre that reduces information overload for day traders. Drag heterogeneous live data sources into a Bloomberg-style tiling workspace and orchestrate specialist AI agents via natural language commands.
Built for the **Gemini 3 Singapore Hackathon** (Cerebral Valley + Google DeepMind, March 2026).
**[Watch the demo](https://www.youtube.com/watch?v=SYbmdHXjNwQ)**
## The Problem
Day traders juggle dozens of tabs, feeds, and tools simultaneously -- live earnings calls, real-time tickers, SEC filings, news articles, and social sentiment. Existing tools are siloed: Bloomberg is text-heavy and locked to its own data universe, retail platforms lack AI-native workflows, and current AI copilots only handle one modality at a time.
## What JoNino Does
- **Live multimodal orchestration** -- drag YouTube streams, stock tickers, SEC filings, and news feeds into a single tiled workspace
- **Natural language rules** -- type "if sentiment turns negative about finances, set a stop-loss at 5% below current price" and the system parses, monitors, and executes
- **Six specialist AI agents** working in parallel: Transcription, Sentiment, Filing Analyst, News, Chart Analyst, and Reflection
- **Real-time trade execution** via Alpaca paper trading with visible reasoning chains
- **Learning loop** using Van Tharp's 2x2 process-outcome classification to extract lessons from every trade
## Architecture
```
Next.js Fronten