※ a personal archive for the way you actually communicate

You know exactly the meme you mean.
Now find it before the moment passes.

Memex is a personal meme archive with natural-language search. Upload anything. Skip the tags, skip the folders. Type what you remember (“guy looking back at girl”, “dog calm in fire”) — get the meme back.

The name is a nod to Vannevar Bush’s 1945 essay on a machine that augments memory. Same idea — applied to how people actually talk now.

live · search
// 0 results · cosine ≥ 0.30
No memes matched.
try: · ·

The whole product is one loop.

01
Upload

Pick a file. That’s it. No title, no tags, no description, no confirmation screen. The meme appears in your library instantly.

POST /api/memes
├ accept: image/* + gif
└ → meme.id (status: pending)
02
Embed

A background job runs the file through CLIP and writes the embedding to a vector store. You watch the status flip pending → ready in real time.

job.run()
├ validate → CLIP encode
├ pgvector upsert
└ → status: ready
03
Search

Type what you remember. Top 10 results above the relevance threshold, ranked by cosine similarity to your query embedding.

GET /api/search?q=…
├ encode(q) · CLIP
├ ANN · cosine · k=10
└ → ranked results

§ 02 · principle

The AI is the organization.

Folders are a 1980s answer to a 1980s problem. We don’t write down what memes are about — we just know. Memex maps every image into the same embedding space as language, so the question “what was that one with the dog and the fire?” returns the dog with the fire.

No tagging. No retroactive cleanup. No “I’ll organize it later.” The whole point is that you don’t.

0
tags written, ever
across the entire product surface

Coming soon.

Voice search
Q3

Hold the mic, describe the meme out loud. Speech-to-text feeds the same embedding pipeline — no LLM in between.

URL / link saving
Q3

Paste a tweet or post. We extract the image, embed it, and search-it works the same as anything you upload.

Public API
Q4

Programmatic access to your library and the search service. Keyboard extensions, MCP servers, anything you can wire up.

AI auto-clusters
$1/mo

Premium tier. Memex finds groupings in embedding space — recurring formats, emotional tones, visual themes you never named.

★ premium
Gmail sign-in
Q3

Per-user libraries replace the v0 stubbed test account. Bring your own data, leave with your own data.

Multilingual
later

SigLIP 2 upgrade adds 100+ languages. Search Japanese memes in English; the embedding space already lines up.


§ 04 · architecture

Search is a service, not a feature.

Natural-language → meme matching is the value. It lives behind a clean API boundary the web app already consumes. When auth ships, the same endpoints become public — no rewrite, no migration.

$ curl https://api.memex.so/search \
   -H "Authorization: Bearer $KEY" \
   --data '{"q": "dog calm in fire", "k": 10}'

{
  "model":     "clip-vit-l/14",
  "threshold": 0.30,
  "results": [
    { "id": "m_4f2a", "score": 0.91, "url": "..." },
    { "id": "m_91be", "score": 0.74, "url": "..." },
    { "id": "m_2c3d", "score": 0.61, "url": "..." }
  ]
}