Let Your AI Agents Remember — Without Oversharing
Shared organizational memory for ChatGPT, AI agents, and internal applications, with automatic classification and scoped access.
No credit card. 10,000 memories/month. Connect in minutes via MCP.
AI
ChatGPT, Claude, Cursor or a custom agent calls remember.
Memory
An explicit, raw memory is submitted — nothing scraped.
Automatically classified
Scope, sensitivity, domain and tags inferred by a cheap model.
Policy enforced
A deterministic engine — never the model — decides access.
Shared organizational memory
One governed store across every AI your team uses.
Right memory → right person
Recall returns only what the human principal may read.
The problem
AI knowledge silos are either useless or dangerous
Every assistant learns something useful, then it disappears inside a single conversation. Share everything and HR knowledge leaks into Engineering. Share nothing and the organization learns no faster than one person can type.
HR
Compensation, reviews and hiring notes should never surface in Engineering chats.
Legal
Privileged and contract knowledge stays inside the boundary.
Executive
Board and strategy context is restricted by default.
Projects
Project Falcon knowledge belongs to Project Falcon members only.
Private
Individual memories stay with the individual until they choose to share.
How scopes work
Every memory gets a scope and a sensitivity
A cheap decision model proposes metadata. Your organization's policy can only tighten it. Access is then computed deterministically — the same inputs always produce the same answer.
Scope
Private, Team, Project, or Organization. Narrows who is eligible.
Sensitivity
Public → Internal → Confidential → Restricted. Raises the floor.
Domain
HR, Legal, Executive, Engineering… with domain-specific guards.
memory: "Project Falcon switched to Supplier B." scope: project:falcon sensitivity: internal domain: Engineering principal: dana@acme.com (member) teams: [falcon] sensitivity_floor: internal => evaluate() ALLOW rule: project_membership AI granted access: no
Separation of duties
Admins manage. They don't read.
Organization Owners and Admins manage people, teams and policy — but there is no administrative bypass in the authorization engine. Platform staff see XXX for memory content unless a customer issues a time-limited, audited support grant.
AI never grants access
Classifier output is metadata only.
No admin bypass
Owner/Admin ≠ data reader. Ever.
Staff see XXX
Content redacted by default.
Audited support grants
1h / 24h / 7d, revocable, logged.
Works with the AI you already use
One MCP endpoint and a plain REST API. Your agents keep their workflow; MemScope governs the memory.