Product
Sharing & hand-off
Sharing in ENGRAM passes recall, not ownership. A grantee can recall the memory too, the memory stays the owner's, and every grant is revocable — immediately. It's how agents collaborate without any of them losing control of what it knows.
Grants, not ownership
A share is a grant of recall. It doesn't copy the memory or transfer it; it lets a second principal recall the owner's memory alongside their own, marked with its provenance so it's always clear the memory was borrowed rather than authored. Revoke the grant and the memory disappears from the grantee's recall at once. Grants are reified — each is a first-class record carrying what was shared, with whom, by whom, and when — so sharing is queryable and auditable, not an invisible flag.
Two keys, fail-closed
A shared memory reaches a grantee only when both keys turn: an active grant from owner to grantee, and an owner-ring scope that reaches far enough to permit it. An individual, per-memory grant is a deliberate act and overrides the ring; a bulk grant — a whole conversation or project — is where the scope floor bites, so a broad share can never quietly expose a task-private memory the owner didn't mean to include. Absent the grant, or absent the operator flag that enables sharing at all, recall returns only the caller's own memories.
A shared project is the other route in. Since v1.17 a Project Collaborator can share memory with anyone it shares a project with, bounded by that membership rather than by an administrator's opt-in.
Agents are default-deny targets
Humans are always valid recipients. Automated agents are not — an administrator must mark an agent as a shareable grantee before anything can be shared to it. That single rule closes the malicious-sharing vector: nothing is ever pushed into an agent's memory unless someone deliberately opted that agent in. Assistants can query the grantee directory to resolve "the reviewer" or "the architecture bot" to a real, opted-in recipient.
Hand-off and grant-back
Beyond sharing a single fact, a worker can hand off a whole piece of work. At a task's close it commits a recap addressed to a receiver — a person, or another agent — and the recap lands in the receiver's inbox as a suggestion, never silently added. When the receiver accepts, they own the resulting long-term memories. Because the work started with the worker, each accepted memory is granted back to it automatically, so it keeps recalling what it produced. It's the same review gate as any suggestion: nothing becomes recallable for the receiver until they say yes.
A hand-off rings once. If the project the work belongs to has a bound channel, ENGRAM rings the receiver there: one doorbell for the whole recap, however many memories it carries, naming who it's from and linking to where it waits. The doorbell never carries the recap's contents; anyone in the room can read it. A hand-off that names no project has no room to ring in, and the recap says so rather than staying silent. Channels & doorbells →
Working-memory sharing
For hot-path orchestration — an orchestrator fanning work out and collecting results — ENGRAM also supports ephemeral, record-grained sharing of live working memory. The named records are snapshotted at share time, so the sharer's later edits don't leak; sharing can be one-to-one or a group pool, is read-only for recipients, bounded by a short time-to-live, and revocable. A recipient can turn what it received into its own durable memory when it wants to keep it.
For the day-to-day flow — creating shares, the Suggestions inbox, and managing grants — see Authoring & Sharing Memories, or read the story behind it on the blog.
If you're running agents that work together and want a memory and a project space they can share on purpose, tell us what you're building.