work / seo-graph · Live · real client work
SEO Graph
My own SEO lab: keyword graphs to client-ready reports.
A seven-day free trial ended and the tool wanted A$160 a month, for keyword research I would run twice a month. I was renting a platform for two searches, and the audit half was something Claude could already do. So I split it: buy keyword data per request from an API, let the model handle the audit. That research now costs me under a dollar per client. The second half was wanting the report to be mine, branded, with their Search Console data live rather than pasted into a slide deck.
Agency-grade SEO tooling is expensive, and almost none of it treats AI search (AI Overviews, ChatGPT, Perplexity) as a first-class citizen.
A research engine that crawls autocomplete and Google Search Console, builds a keyword co-occurrence graph with cluster detection, surfaces content gaps, runs 32-check page audits with AI-search scoring, and renders branded, client-ready site reports. An AI-visibility panel measures share of voice inside grounded LLM answers.
- Python
- FastAPI
- Supabase Postgres
- Cytoscape.js
- Gemini
- Search Console API
- Vercel
- Seven-category health score with an impact-by-effort matrix, in the report format my agency ships to clients
- An InfraNodus-style physics graph for exploring keyword clusters and gaps
- Produces the actual deliverables PTK Digital Labs sells: this tool pays for itself
Serverless has no disk. Porting SQLite to Postgres behind one dialect layer beat a rewrite.
A pure-frontend replica with mock data: nothing is saved, nothing leaves the page. The real app is richer; this is the feel of it.
loading the demo…
The thinking
user · pains · gap · tools
PTK Digital Labs first (me as the operator), and by design any freelance SEO or small agency that cannot justify enterprise tool subscriptions.
Target user
- Agency-grade keyword and audit tooling costs hundreds a month
- Classic SEO tools treat AI search (AI Overviews, ChatGPT, Perplexity) as an afterthought
- Deliverables still need hours of manual assembly after the research
Pain points
Nothing combined graph-based keyword research, a weighted audit engine and AI-search visibility measurement in one tool that outputs a branded, client-ready report. Open-source pieces exist on GitHub, but nobody has packaged them for a freelancer who needs pay-per-use rather than another monthly subscription, which is the commercial opening I think is real here.
Gap in the market
- Gemini (enrichment + grounded AI-visibility checks)
- Claude Code (build)
- Google Search Console API
- Louvain clustering
- Cytoscape.js
- FastAPI + Supabase
AI + tooling
- Network theory: keyword co-occurrence graphs surface structure lists cannot
- Topical authority + content-gap theory for what to write next
- Search-intent classification (informational, commercial, transactional)
- E-E-A-T content lens + AIEO scorecard (own)
- 7-category weighted health score with impact by effort matrix
Frameworks
- Used on two real client engagements, returning live data I made actual decisions from
- Keyword research cost per client: under A$1, against the A$160 a month subscription it replaced
- Produces the actual PTK client deliverables
- Full-site report from crawl to PDF in minutes
- TBD: paid report count once productised
Success metrics
A local-first gym tracker that knows what you did last time.