use cases

A local second brain you own — organized, deduped, recallable

dig files your notes by policy, collapses duplicates, and retrieves across everything with hybrid search and recall — running fully on your machine, every change reversible.

A second brain is only useful if it stays in order and gives back what you put in. dig does the librarian's whole job over your knowledge — organize, dedupe, retrieve, recall — on disk, under your control.

How it works

  1. Index your knowledge. dig init ~/brain && dig scan builds a content-addressed store and a search index over your files — notes, PDFs, docs.
  2. Keep it organized. Declare [[rule]] policy (folders, naming, labels); dig org files everything to match and dig drift flags what wanders. dig dedup collapses identical files, never the last copy.
  3. Retrieve and recall. dig find "<query>" --mode hybrid --json ranks across full-text and semantics; dig recall "<query>" --budget 2000 hands an agent a token-budgeted, provenance-tagged pack.
dig init ~/brain
dig scan
dig org --dry-run                          # preview filing
dig dedup                                  # collapse duplicates
dig recall "that idea about pricing" --budget 2000

Why dig

  • You own it. Runs fully on-device, no telemetry; with no model configured, zero network calls.
  • Stays in order. Policy plus drift detection keep the structure converged instead of decaying.
  • Reversible. Every move, collapse, and capture is journaled — dig undo reverses any of it.

Organize by PARA / GTD / Zettelkasten · Agent memory