Fundamentals
Memory Model
Neutron AI organizes memory by tenant and scope. This keeps integrations predictable across products, agents, workspaces, and users.
Core Terms
| Term | Meaning |
|---|---|
tenantId | Your top-level customer, workspace, organization, or application partition. |
scopeId | A narrower memory boundary such as user:<id>, workspace:<id>, project:<id>, or agent:<id>. |
| Memory record | A durable fact, preference, instruction, summary, or outcome that may improve future agent work. |
| Context pack | A bounded set of relevant memory returned for one task. |
| Privacy class | A label that helps your integration decide what can be recalled, cached, shown, or omitted. |
| Tombstone | A deletion marker that prevents removed memory from reappearing. |
Recommended Scope Design
Choose scopes that match how your product grants access.
| Product need | Example scope |
|---|---|
| Personal assistant memory | user:<user-id> |
| Team shared knowledge | workspace:<workspace-id> |
| Project-specific agent context | project:<project-id> |
| Support account history | account:<account-id> |
| Short-lived workflow memory | session:<session-id> |
You can request multiple scopes for an agent task. Keep the list explicit and only include scopes the current user or agent is allowed to access.
Memory Types
Use memory type labels consistently so recall quality improves over time.
| Type | Use for |
|---|---|
preference | Stable user or workspace preferences. |
fact | Lasting product, account, or workflow facts. |
instruction | Standing rules that should guide future agent behavior. |
summary | Condensed history from a conversation, document, or workflow. |
outcome | What happened after a task, decision, or tool run. |
Lifecycle
flowchart LR
A["remember"] --> B["recall"]
B --> C["agent context"]
C --> D["reflect"]
D --> A
B --> E["forget"]
Use forget for deletion, correction, user privacy controls, and stale or unsafe memory. Deletions should be treated as final in your integration logic.