TradeSight – a Rust-powered market risk dashboard with AI analysis
I built TradeSight (https://tradesight.live) as a lightweight market risk indicator that combines real-time data with AI insights. The backend is written in Rust, with a vanilla JS frontend for maximum performance. It aggregates data from multiple sources (FRED API, Yahoo Finance) and uses Claude's API to provide detailed market analysis. Technical stack: - No login required - static page with hourly updates - Rust backend for efficient data aggregation - Vanilla JavaScript frontend for minimal overhead - Claude API integration for real-time market analysis - Data sources: FRED…
What it does
In the maker’s words, at launch
I built TradeSight (https://tradesight.live) as a lightweight market risk indicator that combines real-time data with AI insights. The backend is written in Rust, with a vanilla JS frontend for maximum performance. It aggregates data from multiple sources (FRED API, Yahoo Finance) and uses Claude's API to provide detailed market analysis. Technical stack: - No login required - static page with hourly updates - Rust backend for efficient data aggregation - Vanilla JavaScript frontend for minimal overhead - Claude API integration for real-time market analysis - Data sources: FRED economic data, Yahoo Finance, News API - Running on a small Digital Ocean droplet with Nginx reverse proxy for rate limiting - File-based caching system (Redis integration planned) The dashboard tracks multiple risk metrics like VIX, DXY, Treasury rates, manufacturing employment, and consumer sentiment, providing an AI-generated analysis of market conditions. Looking for beta testers and feedback on the platform's utility and performance.
Does the same job
all alternatives →
- TFtool for commodity traders, brokers and analysts.2011 · bullbear.ca · ▲107
CoreSight | Analyze any stock in secondsMar 2026 · ▲17Analyst-grade stock research, without the analyst cost
- SCSpot Canvas – AI-Powered trading charts for learning and automating TASep 2025 · spotcanvas.com · ▲8
Hi HN, About a year ago I started tinkering with drawing candlestick charts on an HTML canvas. What began as a small experiment turned into a full-blown crypto charting library. At some point I asked myself: could this actually become a competitor to TradingView? That felt overwhelming, since TradingView has an enormous feature set. Still, I kept building — partly because I enjoy side projects more than watching TV By the summer, I had a working SaaS version. But it felt like it was missing something that would make it truly stand out. Then I realized: the chart itself should be AI-powered.…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
