Hybrid memory recall

The idea

Recall ranks memories with full-text and trigram search, plus vectors where embeddings exist. It says which arms ran and why vectors are off, and it gives the worker its readable memory as files.

The problem
Keyword recall missed identifiers and paraphrases, and nobody could tell why.
Why it matters
Recall finds identifiers without embeddings and states its own limits.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

Where it lives in the product

  • Adaptive per-turn context

    Typed decisions say which optional sections a turn needs and how to retrieve. Code plans the slots under a ceiling, with a reduction ladder that never cuts more than before, and limits the queries.

  • Frozen context-recall baseline gate

    A frozen offline set of 36 cases plants facts and records where each one shows in the next request and whether it can be read back. A change to context, memory or compaction must beat this baseline.

  • Area notes and knowledge that stays current

    Research writes a note for each package or folder it touches, kept while the files do not change. Facts tied to a page or ticket go stale when it changes, and pushes to the default branch update ties and notes.

  • Forget reaches derived copies

    When a person forgets a note, the platform also rewrites the copies that work made from it: briefs, plans, findings, logs and outputs. It also cancels approvals and holds outreach that quote the note.

  • Own computer by default, one command

    A person connects their own computer with one pre-approved command; the official Claude Code and Codex CLIs run there under the person's own login, which the platform never opens.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.