Core concepts

Team Memory

Knowit is local-first. Project memory is a JSONL file you review in version control like source code — and a shared SQLite path covers everything else.

Git-reviewed JSONL

In project scope, .knowit/knowledge.jsonl is the canonical memory file. Because it's line-delimited JSON, every added rule or decision shows up as a clean diff. The workflow is the one your team already has:

An agent (or a teammate) stores a new decision during a session.
The change appears in .knowit/knowledge.jsonl and goes into the same branch and pull request as the code it explains.
Reviewers see the memory change next to the code change and approve both.
On pull, every teammate — and every agent they run — gets the updated memory automatically.

Migrating from SQLite projects

Existing projects with .knowit/knowit.db are migrated automatically on first project-scope initialization when .knowit/knowledge.jsonl does not exist. You can also run the conversion explicitly:

Terminal

$ knowit migrate-storage --sqlite-path .knowit/knowit.db --dry-run
$ knowit migrate-storage --sqlite-path .knowit/knowit.db

The command writes .knowit/knowledge.jsonl and .knowit/sources.json. It refuses to overwrite existing targets unless you pass --force.

Shared SQLite database

For private global memory, or a shared database that lives outside any repo, point everyone at the same SQLite database path:

Terminal

$ KNOWIT_DB_PATH=/shared/team/knowit.db npx knowit install --scope global --client claude

Every developer and every agent then reads and writes the same durable memory source — without adding a hosted dependency.