Memory
Salvage

stacc-brain

Stacc Brain — Karpathy llm-wiki at Telegram scale (Obsidian + holographic layer / leCore). Demo: https://brain.stacc.bio

Language
Gist
Pushed
Aug 2026
Size
7 files
License
unspecified
Open gist

Who this is for

Someone who wants Karpathy-style llm-wiki at Telegram scale (Obsidian + leCore), not another chatbot.

What worked

Product notes, marketing, monetization, and a demo URL (brain.stacc.bio) already exist.

What failed

A gist of strategy docs is not the running brain. Easy to confuse the memo with the machine.

Next three

  1. 1Point the SKU at the running demo or mark it instructive
  2. 2Separate strategy docs from the ingest oat
  3. 3Founder who will own the corpus

STACC will

Share the memos and the bind contract.

Will not

Be the full-time brain operator.

Shipped by —, oat by STACCoverflow. No forced face. No forced token.

Same lane

Live

openzoo-ingest

Everything your machine produces, bound into your own leCore memory. Local by default; the shared brain is the only egress.

Salvage

lecore-bm25

Okapi BM25 + RRF with the stoplist/stemming tokenizer that makes it beat stock BM25 out of the box. Vendored from leCore (MIT, AnOversizedMooseWithSocks).

Live

lecore-flash

Private

A founder who can live in HTML in the local memory and retrieval lane, taking a proved body rather than a blank repo.

Live

supercontext

Reproducible benchmarks for leCore retrieval: NIAH past the context window, MTEB, and cost-to-first-answer vs FAISS