(The cinematic version needs WebGL — here's the same cascade, stage by stage.)
Structured filters and full-text search light up exact, explainable matches — type, tags, entities, dates, and ranked keyword hits over what your memories literally say. No model in the loop.
From those hits, MENTIONS and LINKS_TO edges pull in what the matches are connected to — one or two hops, no guessing.
score(m) = Σ 1/(60 + rank). A memory two lanes agree on beats any single lane's favorite.
A full semantic traversal across everything you've stored — automatic when the fast lanes come up short, instant on deep=true. In embedding space related memories live near one another, so a hit doesn't just find one point — it lights up the whole neighborhood. Always accounted for in the telemetry.
No card, no invite code, no queue. Your GitHub account is the account.
https://openbrainstore.com/mcp
Connecting means you accept our Terms. What we store, where it lives, and how to delete it: Privacy Policy.