Open Source · MIT Licensed

Monitor your AI visibility

Developers discover tools by asking AI. GeoStorm monitors how GPT, Claude, Gemini, and Perplexity perceive and recommend your software — and alerts you when a competitor appears, your ranking drops, or a model stops mentioning you.

terminal
$ docker run -d -p 8080:8080 -v geostorm-data:/app/data
--name geostorm ghcr.io/geostorm-ai/geostorm
✓ GeoStorm running at http://localhost:8080
✓ Demo data loaded (90 days)

Everything you need to monitor AI perception

One container, one command. GeoStorm gives you complete visibility into how AI systems perceive and recommend your software.

Perception Tracking
Monitor how AI models describe and position your software relative to competitors. Track your recommendation share across GPT, Claude, Gemini, Perplexity, and more.
Smart Alerts
Get notified when a new competitor appears, your software disappears from recommendations, your share drops, your ranking degrades, or models diverge in their perception.
Perception Charts
Track your recommendation share and positioning across models over time with interactive charts. See trends at a glance and spot changes early.
Signal Panel
A unified feed of alerts, ranked by severity and recency. See critical signals at a glance with full context on what changed and why it matters.
MCP Integration
Connect Claude Code to query your perception data conversationally. Ask things like "Show me perception scores" or "Are there any alerts I should know about?"
Self-Hosted & Private
One container, one port, one volume mount. Runs entirely on your infrastructure with Docker. Your data stays yours — no external dependencies beyond OpenRouter.

Up and running in minutes

GeoStorm is designed to be simple. No external services, no complex setup — just Docker.

Step 01

Deploy with Docker

One command and you're live. No git clone, no build step, no API keys needed upfront. A demo project with 90 days of synthetic monitoring data is ready to explore immediately.

Step 02

Configure Monitoring

Add your OpenRouter API key in the settings page — one key gives you access to GPT, Claude, Gemini, and more. Create a project and GeoStorm starts monitoring.

Step 03

Track Perception

GeoStorm automatically polls AI models on a schedule, tracking your recommendation share and positioning over time. Deterministic code, predictable costs.

Step 04

Get Alerted

Receive alerts via Slack, email, or webhooks when something changes — a new competitor appears, your ranking drops, or a model stops mentioning you.

Quickstart

Get GeoStorm running locally in under a minute. All you need is Docker.

1

Run GeoStorm

bash
docker run -d -p 8080:8080 -v geostorm-data:/app/data --name geostorm ghcr.io/geostorm-ai/geostorm
2

Open the dashboard

Visit http://localhost:8080 — a demo project with 90 days of synthetic monitoring data is ready to explore immediately.

3

Start monitoring

Add your OpenRouter API key in the settings page, create a project, and GeoStorm starts monitoring on a schedule. One key gives you access to GPT, Claude, Gemini, and more.

4

Connect Claude Code (optional)

Query your perception data conversationally — ask things like "Show me perception scores" or "Are there any alerts I should know about?"

bash
claude mcp add --transport http geostorm http://localhost:8080/mcp/

Requirements

  • Docker
  • OpenRouter API key (for monitoring)
  • No other external dependencies

Built with

A focused stack with no unnecessary complexity. Everything runs in a single container.

FastAPIPythonAstroReactTailwindCSSRechartsSQLiteDockerAPSchedulerOpenRouter

Frequently Asked Questions

Common questions about GeoStorm, how it works, and what it costs.

Why would I want this?

More developers discover tools by asking AI — "what's the best library for X?" If a model stops recommending your project or starts favoring a competitor, you'd never know unless you manually checked. GeoStorm automates that and alerts you when something changes.

Why OpenRouter?

OpenRouter gives you access to GPT, Claude, Gemini, Llama, and dozens of other models through a single API key. Instead of managing separate keys for OpenAI, Anthropic, and Google, you sign up once and GeoStorm can query all of them. You can also use direct provider keys if you prefer.

Is there a hosted version?

Not yet. GeoStorm is self-hosted only for now. The Docker container is designed to be easy to run anywhere — your laptop, a VPS, or a cloud VM. A hosted version is on the roadmap.

Why SQLite?

GeoStorm is a single-user monitoring tool, not a multi-tenant SaaS. SQLite keeps things simple — no database server to run, no connection strings to configure. Your data lives in a single file on a mounted volume. For GeoStorm's query patterns, SQLite is more than fast enough.

How much does it cost to run?

GeoStorm itself is free. The only cost is the AI API usage through OpenRouter. A typical monitoring run queries 3 models with a few prompts each — roughly $0.01–0.05 per run depending on the models you choose. Running daily, that's about $1–2/month.

Couldn't I do this with OpenClaw?

You could wire up an OpenClaw agent with a cron job to query AI models daily and store the results somewhere. But then you're building GeoStorm from scratch — prompt engineering for consistent structured responses, parsing and normalizing across models, calculating recommendation share and position rankings, detecting changes over time, generating alerts, and building a UI to make sense of it all. GeoStorm does all of that out of the box. It's also cheaper and more predictable — deterministic code on a fixed schedule, so you know what queries run and what they cost.

How do I disable telemetry?

Set the NO_TELEMETRY=true environment variable. This completely disables all analytics — no PostHog client is created and no events are sent. See our privacy policy for full details on what is (and isn't) collected.

Know what AI says about your software

GeoStorm is free, open source, and self-hosted. One container, one command — deploy in under a minute with Docker.