What you can build with dig

Real workflows running on dig locally — agent memory, RAG over your files, dedupe, and organizing a knowledge base to your own rules.

Give your coding agent persistent memory with dig

Wire dig into Claude Code, Codex, or any MCP agent so it remembers across sessions — finished sessions are captured automatically and recalled on demand, locally and reversibly.

Collapse duplicates across a document library — reversibly

dig detects identical files by content hash, keeps the copy your policy chooses, and never deletes the last copy — every collapse is journaled and undoable.

Retain meeting transcripts and recall the moment later

Capture meeting transcripts into a dig knowledge base, then find the exact decision or action item weeks later with hybrid search and token-budgeted recall — locally and reversibly.

Keep your Obsidian vault filed, deduped, and searchable

Point dig at your vault directory and it files notes by policy, collapses duplicate markdown, and gives your agent hybrid search and recall over the files — locally and reversibly.

Organize a knowledge base by PARA, GTD, or Zettelkasten

Encode your method as declarative dig org rules — folders, naming, labels — and dig files every note to match, reversibly. The mental model becomes policy, not manual upkeep.

RAG over your local files — no vector service, no upload

Point dig at a directory and your agent can retrieve across it with hybrid search — PDFs, notes, and docs included, indexed locally, nothing uploaded to a cloud vector store.

Retrieve and recall across your research notes

dig indexes a folder of research notes for hybrid search and hands your agent a token-budgeted, provenance-tagged recall pack — so it answers from your sources, locally.

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.