business-os/doctor
knowledge core

Doctor

pillar health — live roster + runs + SOP coverage
SALESFINANCESCLIENTSMARKETINGTECHCOMMUNICATIONS
—/ 100 health
doctor — unreachableno agent runs yet
hybrid search degradedlocal fallback active
TOOLS · 36SOPS · 35AGENTS · 30ORG · 6PEOPLE · 5—HEALTH / 100GBRAIN V0.41BRAIN-STORE · 112 PAGESZEROENTROPY · EMBEDDINGSSUPABASE · 1240 PAGES · PAUSED
Storage layers
gbrain CLI
v0.41 · gbrain CLI · doctor --fast
UNREACHABLE
brain-store/
/data/brain-store · markdown knowledge
112 pages
ZeroEntropy
hybrid-search embeddings · key in ~/.config/knowledge
LIVE
Supabase Second Brain
1240 pages / 15k chunks · free tier idle-pause
PAUSED
doctor — health —/100offline
Pipeline112 pages on disk
1

Markdown brain-store

/data/brain-store
112 pages on disk, plain .md files — the source of truth. gbrain sync walks the git repo and pushes changed pages up.
  • agents30
  • org6
  • people5
  • sops35
  • tools36
sync · import→
2

gbrain CLI

chunk · embed · route — the engine between disk and database
—/ 100 health · CLI unreachable
  • doctor offline — spawn gbrain ENOENT
putgetquerysearchsyncimportexportdoctor
embed · upsert→
3

Supabase Postgres + pgvector

"Second Brain" · ZeroEntropy embeddings
1240
pages · last known
15k
chunks · last known

Each page is split into chunks; every chunk gets a ZeroEntropy embedding stored in a vector column. Postgres holds both the text (tsvector) and the vectors, so one database answers keyword and semantic queries.

Free tier pauses on idle — when hybrid queries fail, unpause from the Supabase dashboard. The brain-store on disk keeps working regardless.

Query path

What happens when an agent calls gbrain query — hybrid retrieval with an honest fallback.

Question
Natural-language query from you or an agent run.
expand→
Query expansion
The CLI rewrites the question into search variants (skip with --no-expand).
fan out→
Keyword search
Postgres tsvector full-text match over chunk text.
Vector search
pgvector nearest-neighbor over ZeroEntropy embeddings.
merge→
RRF fusion
Reciprocal-rank fusion merges both result lists into one ranking.
answer→
Ranked snippets
Top pages with snippets, returned to the agent.
Fallback: local grep
If Supabase is paused or unreachable, FOUNDER OS greps the markdown brain-store directly — fewer smarts, zero downtime.