HN Showcase
Back to browse
GitHub Repository

Monitor how AI systems perceive and recommend your software across GPT, Claude, Gemini, and more.

31 starsPython

Geostorm.ai – Monitor what AI chatbots say about your software

by barticz·Mar 1, 2026·4 points·2 comments
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemBig BrainDark Horse

First Google Search Console for AI recommendations—tracks GPT, Claude, Gemini mentions.

Strengths
  • •Solves a genuinely new problem: AI discovery is measurable but unmeasured. Before this, no tool existed.
  • •Single Docker container with zero external dependencies shows excellent constraint discipline.
  • •Scheduled polling + alert thresholds mean real-time visibility into competitor positioning shifts.
Weaknesses
  • •Depends entirely on OpenRouter API stability and pricing—if the service changes, monitoring breaks.
  • •Early-stage: only 3 stars, so real-world usage patterns and edge cases remain unvalidated.
Target Audience

SaaS and open-source founders, product managers tracking AI-driven discovery

Post Description

We've been building dev tools and noticed more and more users tell us they found us because "ChatGPT recommended it" or "Claude suggested it". Not Google, but AI.

There's no Google Search Console for this. No way to know if e.g. GPT-5.2 is recommending your library, where it ranks you, or whether Gemini even knows you exist. We couldn't find a tool that solved this, so we built one.

GeoStorm monitors multiple AI models on a schedule. You define search terms (e.g., "best Python async framework"), and it queries ChatGPT, Claude, Gemini, etc. via OpenRouter. It then parses the responses, tracks your brand mentions, calculates recommendation share, and alerts you when things change - a new competitor appears, your ranking drops, a model stops mentioning you.

Technically: it's a single Docker container. FastAPI backend, Astro/React frontend, SQLite, APScheduler running in-process. No Redis, no workers, no external dependencies. One OpenRouter API key gives you access to all models.

> docker run -d -p 8080:8080 -v geostorm-data:/app/data --name geostorm ghcr.io/geostorm-ai/geostorm

That gives you a working instance with 90 days of demo data so you can explore everything immediately. Add your OpenRouter key to start monitoring your own project.

MIT licensed. Would love feedback on the approach - especially from anyone who's already thinking about AI-driven discovery for their tools.

GitHub: https://github.com/geostorm-ai/geostorm Webiste: https://geostorm.ai/

Similar Projects