Finance & Business2 weeks ago
StatEdge AI
AI-powered sports analytics to inform betting decisions.
@Griffithjade626 · X
The full gallery
Tech stack
60 projects
AI-powered sports analytics to inform betting decisions.
@Griffithjade626 · X
Analyze stocks with AI forecasts, live prices, and company comparison tools.
@brucewayne18457 · X
Get years of Knowledge & prediction within seconds with IntegraX Predict Stock Prices upto 60 days suggest action,top insights Stocks recommender Compare stocks Top 5 stocks of day Visit IntegraXai looking for genuine reviews
A visualization language designed for AI agents to create and interact with charts.
chenglong-hn · HN
Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple
Embeddable AI chat widget that answers customer support questions using your documentation with cited sources.
@dhruvkumar1805 · X
AI-powered cryptocurrency analysis tool with scoring, opportunity radar, and alerts for swing traders.
@luiz_santo78412 · X
Check out what I just built with Lovable!
AI risk management for Tradovate that automatically blocks orders when triggered by your own risk rules.
@SanuCodes · X
still building-
Compare AI coding models on real tasks with live previews, cost tracking, and ELO rankings.
@intheworldofai · X
On the World of AI Bench (vibe-coding composite): Claude Fable 5 → 85.2 GPT-5.6-sol → 82.4 kimi-k3 → 81.5 Moonshot’s K3 just walked in and claimed bronze on one of the toughest coding-focused leaderboards out there.
Scan receipts to automatically track warranties, file claims, and monitor coverage.
@Keevora_ · X
Likewise. Hi, just shipped this week. Finally reached the stage where Keevora works end-to-end. ✅Scan receipt 📷 Store warranty 📷 Track brand replies & auto revert Live:
Scan grocery receipts to find savings opportunities like price gaps and discounts.
@Qintarisapp · X
Benchmark AI models by having them animate a 3D banana plant's full lifecycle.
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.
Analyzes handwritten student work to provide AI-powered feedback and identify misconceptions.
@WachangaWinston · X
An algebra crisis at home became TeachMap: teacher-reviewed AI feedback and misconception maps from handwritten work. Built with Codex + GPT-5.6 Sol for OpenAI Build Week.
Generate startup ideas, identify launch markets, and validate demand before investing.
@thegetideascout · X
We are building a set of tools for founders who want to stop guessing. Find an idea → pick the right market → validate demand. Before you waste money and time. try it for free here