Data and Privacy

Origin is designed so the durable context your agents use lives locally first. That context can include project decisions, private constraints, preferences, and work history.

Connected AI tools may still send prompts to their own model providers. Origin's job is to keep the memory layer itself local, inspectable, and shared across tools.

Origin exposes human-facing artifacts under ~/.origin. The daemon database lives under the macOS application support directory and is linked from ~/.origin/db for convenience.

The important files are readable without a special app: pages are Markdown, session logs are Markdown, and project status is stored beside the session records.

Markdown is the record you can read. The database is the index agents use to retrieve quickly.

This avoids treating the database as an opaque source of truth. Search can be fast and structured while the important artifacts remain inspectable.

Origin stores, embeds, deduplicates, and serves hybrid search without requiring a local model download or Anthropic API key.

Optional model and API paths can add heavier language features, but they are not required for the basic memory loop.

If a memory is wrong, capture the correction with why it supersedes the old fact. If a memory should be removed entirely, use /forget with the memory ID.

For distilled pages, inspect the Markdown directly. User-edited pages are treated carefully so automated distillation does not overwrite human work casually.