Mind · Long-term memory
The memory your agents bring to every session.
Mind is the personal knowledge layer — the long-term memory your agents draw on across sessions. Documents, notes, chats, code snippets, structured facts all land here, embedded and indexed locally. Cloud only when you turn it on.
What it does
Local-first ingestion
Documents are chunked, embedded, and indexed on your machine. Cloud sync is opt-in. Your data sits on your hardware by default.
Hybrid search
Vector similarity + BM25 + structured field filters in one query. Returns the right thing for fuzzy + exact + filtered queries.
Connectors
Slack, Gmail, Drive, Notion, GitHub, plus a generic webhook connector. Every sync runs through Conscience policy scrubbing first.
EKB1 envelope crypto
AES-256-GCM at rest with per-tenant KEKs and per-purpose data keys. Same crypto layer as Project Vault.
When to reach for it
- You want agents that remember context from prior sessions without you re-pasting.
- You need to search across documents, code, and conversations in one query.
- You're bringing institutional knowledge into AI workflows but data residency matters.
- You want connectors that route through a policy scrubber before indexing.
Deep dives
- Personal Knowledge Base — the long-form pitch for Mind, including the DLP + crypto + spaces story.
Pricing
This product is included starting from the Starter tier ($19 CAD/mo). Every higher tier includes it automatically. See the tier & product mapping for the full picture.
Read more
- Mind docs
- Memory & instructions concept
- Conscience — policy gates that govern Mind connectors.