Health/WellnessEnglish

How My AI Family Friend is built

Visit My AI Family Friend My AI Family Friend in the collection

Measured numbers

Counted by the collection, not written by hand. A figure we cannot support is left out rather than shown as zero.

Pages: 12; 5th of 5 measured in Health/Wellness, by sitemap URLs
Page count over time: 11 → 12 pages measured, 30 Sep to 25 Oct
Languages: English
llms.txt: Published; llms.txt 5.2 KB · llms-full.txt 33 KB
Sitemap: Listed in robots.txt

Tech and AI search

Read from the live site on 2026-10-23: its homepage, robots.txt and llms.txt. A line we could not read is left out.

Built with: Next.js; Read from the homepage markup
Structured data: FAQPage, Organization, WebApplication, WebSite; schema.org types on the homepage
AI crawler access: Allows all 11 major AI crawlers; From the site’s robots.txt
llms.txt link depth: 11 page links; Markdown links in the site’s llms.txt

How it is built, by role

The same roles apply across the whole collection. Nothing in this block is specific to this site; what the site says about itself is quoted word for word below it.

1
Edge network
Visitors reach a site through an edge layer: a content delivery network with a web application firewall in front of it.
2
Application host
The edge talks to an application host that serves the site and renders its pages.
3
Data
What the pages show comes from a relational database or, for a site pre-rendered at build time, from data files built into its release.
4
Scheduled measurement
The collection measures its sites on a schedule: content dates and site health nightly, page counts read from each site’s sitemap weekly. Every reading is kept with its date. A site too large to re-walk is not re-measured, and shows no trend.
5
Public status feed
A monitoring panel sends a signed report on uptime, deploys and backups once a day, and the Operations page publishes it. A figure on this page that comes from that report says so.

In the site's own words

Each passage is copied unaltered from a page the site publishes, with the address it was taken from and the date we took it. We add nothing between them.

“My AI Family Friend is a privacy-first AI companion platform: a platonic friend with long-term memory you control, a growth partner for goals that take years, a shared memory keeper for your family, and a calm interface designed for every kind of mind.”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24

“An independent AI companion platform built and run by a small team, with infrastructure in the EU (Germany).”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24

“On our own server infrastructure in the EU (Germany). No third-party analytics, no ad networks, no tracking pixels.”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24

“Each account holds at most 400 active memories; past that, the lowest-ranked ones are archived to make room, and pinned memories are effectively exempt from all of this.”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24

“Every memory is visible in the Memory browser, where you can edit, pin, archive or delete it, and each one links back to the conversation it came from.”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24

“Your conversations and memories are yours: export them anytime as a single file, or erase them completely. No advertising, no selling data, ever.”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24

“Consent-first sharing: family spaces for stories, history, and light coordination across generations — where each person decides exactly what is shared and what stays private, right down to care notes needing the subject's own opt-in.”

Source: myaifamilyfriend.com/llms-full.txt · retrieved 2026-10-24