Websites and hosting decision
Fastfolio
A competent developer can recreate the core AI-portfolio functionality in about a week using existing OSS components and OpenAI; Fastfolio's durable advantages are limited to product polish and bundled model access rather than unreproducible moats.
Visit website↗$8/mo
$96/yr
Read off the official pricing page.
$100one-off34 h to build
$20/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 4 seats.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Fastfolio alternatives, with the arithmetic →
What a replacement has to do
- Import resume/LinkedIn/GitHub -> index content -> serve public portfolio site -> respond to visitor chat queries via OpenAI API -> collect interaction events
What it still won’t have
- Bundled GPT-5 access / 'Unlimited GPT-5 Power' (product bundles model access)
- Built-in advanced analytics & insights dashboard
- Fastfolio branding removal and built-in custom domain handling (pro features)
- Product polish, onboarding flows, and hosted uptime/ops
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 4 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal AI portfolio using Next.js (React) frontend, Supabase Postgres with pgvector for storage, and OpenAI API for LLM responses. Core features in scope: (1) importer to accept PDF resume and fetch LinkedIn/GitHub profile data, (2) content parsing and embedding pipeline to index sections into pgvector, (3) public Next.js site that renders portfolio pages and exposes a chat UI, (4) serverless API routes that retrieve relevant contexts from the vector store, compose prompts, and call OpenAI, (5) lightweight analytics event capture (page views and chat events) saved to Postgres, and (6) simple admin UI to re-run imports. Out of scope: building a custom LLM, multi-tenant admin dashboard, payment integration, and enterprise analytics. Include error handling, retry logic for API calls, and unit/integration tests for importer, embedding pipeline, and chat endpoint.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 4 cited sources+3
- Price verified on pricing page+3
- Evidence score89
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 4
Every page the run actually retrieved.
- official productFastfolio - product page
- official pricingFastfolio - pricing
- open sourcearifszn/ezfolio
- open sourceyashrathi-git/portfolioly
Integrity checks
What held up, and what did not.
