$GIGGLEnew
$INVISIBLEnew
$STOCKEDnew
$Cnew
$INVISIBLEnew
$VOSFnew
$NEX Ainew
$UInew
$HOUTAXInew
$Capybaranew
$FEDERAL OIL new
$BRKCMPnew
$INVISIBLEnew
$Memebooknew
$DIGITnew
$USDFnew
$VEIL
$PAID
$BATON
$DARK
$XTO
$MISTAKE
$HOOKED
$E/ACC
Website blueprint · 26 Oct 2026
mem0x.com
“mem0x — The universal memory layer for AI”
Tech check
What the site says about itself, next to what its public page actually loads. Facts only, no verdict: you decide.
Nothing found on the public page
AI / agents
“…erstand? reconstruct? rediscover? One memory for every AI. Save, recall and inspect what it knows. All memory ↵…”E21
No matching code, calls or services in what loaded for us.
What it is
- The Internet Archive has never saved this site, so it is probably new.E22
- The site describes itself as: “Save, recall and explore one persistent memory for every AI. Intelligence shouldn't reset.”E2
- It's built with React (common tools for building web apps).E9
- Notable building blocks in its code: Supabase client.E10
- In your browser it can copy text to your clipboard and saves small bits of data in your browser.E11E12
- It has sections such as /memory, /atlas, /replay, /capsules, /connections and /passport.E18
- While loading, it called 1 endpoint on its own servers, such as /__l5e/trackevents.E14
Where your data goes
Crypto and wallets
How key features work
Connecting your wallet
It connects to crypto wallets using personal_sign and eth_requestAccounts. Connecting shows the site your wallet address; it doesn't move funds by itself.E19
personal_signeth_requestAccountsLoading its content
Its content loads from its own API while you browse (/__l5e/trackevents).E14
/__l5e/trackeventsSaving data on your device
It saves data in your browser (localStorage), so some things persist between visits.E12
local_storageCookies and storage
Names only. We never store the values.
Pages and API calls
Evidence
Every sentence above points to one of these. Code references show the file, line:column and the short identifier that matched, never the site's code itself.
E1
Page title: mem0x — The universal memory layer for AI
page title · https://mem0x.com/
E2
Page description: Save, recall and explore one persistent memory for every AI. Intelligence shouldn't reset.
page description · https://mem0x.com/
E3
Main heading: What would you like to
remember?
recollect?
understand?
reconstruct?
rediscover?
remember?
recollect?
understand?
reconstruct?
rediscover?
page h1 · https://mem0x.com/
E4
66 request(s) to mem0x.com
types: 60 script, 3 fetch, 1 document
GET https://mem0x.com/ · script · 66 requests · network recording
E5
1 request(s) to fonts.googleapis.com
types: 1 stylesheet
GET https://fonts.googleapis.com/css2 · stylesheet · network recording
E6
3 request(s) to fonts.gstatic.com
types: 3 font
GET https://fonts.gstatic.com/s/geist/v5/gyByhwUxId8gMEwcGFU.woff2 · font · 3 requests · network recording
E7
Cookie '__dpl' set for mem0x.com
kept for about 1 days
cookie __dpl on mem0x.com · value not stored
E8
Cookie '__cf_bm' set for mem0x.com
kept for about 0 days
cookie __cf_bm on mem0x.com · value not stored
E9
React detected by REA (react-runtime)
confidence: medium
mem0x.com/assets/index-C2Apj2HK.js · “react-runtime” · REA analyze-web-bundle 6.4.0
E10
Supabase client found in the code
mem0x.com/assets/index-C2Apj2HK.js @ 11:100256 · “supabase.co” · pattern scan
E11
Uses the browser ability: clipboard_write
can copy text to your clipboard
mem0x.com/assets/index-C2Apj2HK.js @ 11:98959 · “clipboard.writeText(” · pattern scan
E12
Uses the browser ability: local_storage
saves small bits of data in your browser
mem0x.com/assets/utils-DCpUPDq1.js @ 8:2491 · “localStorage.setItem(” · pattern scan
E13
Uses the browser ability: web_worker
runs work in a background thread
mem0x.com/assets/utils-DCpUPDq1.js @ 7:6124 · “new Worker(” · pattern scan
E14
The page called /__l5e/trackevents on mem0x.com (POST)
POST https://mem0x.com/__l5e/trackevents · fetch · network recording
E15
REA found the endpoint /api/memory-import
how: call:fetch
mem0x.com/assets/index-C2Apj2HK.js @ 12:6532 · “/api/memory-import” · REA analyze-web-bundle 6.4.0
E16
REA found the endpoint /api/memory-extract
how: call:fetch
mem0x.com/assets/index-C2Apj2HK.js @ 12:7548 · “/api/memory-extract” · REA analyze-web-bundle 6.4.0
E17
The code names the endpoint /api/broadcast
mem0x.com/assets/utils-DCpUPDq1.js @ 1:27898 · “/api/broadcast” · pattern scan
E18
9 links to pages on the same site
page links · https://mem0x.com/ · /, /memory, /atlas, /replay, /capsules, /connections, /passport, /settings, /activity
E19
Wallet request in code: eth_requestAccounts
asks to connect your wallet, which shows the site your address
mem0x.com/assets/utils-DCpUPDq1.js @ 10:23288 · “eth_requestAccounts” · pattern scan
E20
Wallet request in code: personal_sign
asks you to sign a text message (often to log in; moves no funds by itself)
mem0x.com/assets/utils-DCpUPDq1.js @ 10:24009 · “personal_sign” · pattern scan
E21
The site says: “…erstand? reconstruct? rediscover? One memory for every AI. Save, recall and inspect what it knows. All memory ↵…”
page text · https://mem0x.com/ · …erstand? reconstruct? rediscover? One memory for every AI. Save, recall and inspect what it knows. All memory ↵…
E22
The Internet Archive has no saved copy of mem0x.com
page web archive · https://web.archive.org/web/*/mem0x.com
Limits
- We only see what your browser sees: code and requests on a first visit, without logging in or accepting cookie banners. What the servers do with data is invisible from outside.
- Site code is usually minified (compressed), so names are partly lost and some code may be only partly analysed.
- Some trackers only load after you accept cookies or log in, so the real list can be longer.
- We visited from a server in the United States. Sites load different trackers and cookie banners in different countries (visitors in the EU usually get a consent banner first).
- The tech check compares the site's own words with what its public page loads. Work done on servers, in private code or in separate apps isn't visible here, so 'nothing found' means not visible on the public page, not that it doesn't exist.
- This text was written from fixed templates because no AI writer was available. It uses exactly the same evidence.
- REA hit its size budget on parts of 51 large bundle file(s); those parts weren't fully analysed.
Facts, not judgements: this page describes what the code and traffic show, not anyone's intent. Not financial advice. Case id t6qcz29W.