One shared memory for every AI tool your team uses, with access decided by your rules
MemScope is shared memory for your team’s AI coding agents. Each person’s agent gets back only what that person is allowed to see. Agents save over MCP or a REST API; AI only suggests labels, and a deterministic policy decides who can read each memory, so sharing knowledge never means oversharing it.
Explicit memory writes
Your agent saves a raw memory with save_memory. No scraping, no transcript ingestion: only what you choose to store.
AI labeling
When you turn AI labeling on, a fast AI model suggests sensitivity, topic and tags, with confidence scores and a review queue. Who can see a memory is decided by your organization’s policy, never by AI.
Access decided by policy
One fixed set of rules decides who can read a memory. AI labeling only adds labels and can never grant access.
Versioned, correctable memory
Corrections create immutable new versions. Changes to who can see a memory, or how sensitive it is, are recorded in the audit log.
Search that respects access
Your agent searches memory with search_memories. MemScope searches by meaning and keywords, checks access on every result first, then ranks. You only ever see what you may read.
OAuth connections
MCP clients connect with OAuth 2.1 and act as the authenticated human — never as a privileged robot.
Built for agents, governed for people
A client saves something. MemScope labels it, applies your organization’s rules, and stores it. Later, any client searches memory and receives only the memories its person is allowed to see.
- Raw memory is immutable per version
- Forget is restorable for 30 days, then erased for good
- Every organization’s memory is kept separate
- Memory content never appears in logs
Works with Claude Code, Cursor, ChatGPT and moreCompare with repo files and built-in memory
Interfaces & tools
- Connection address
- mcp.memscope.ai/mcp
- REST API
- api.memscope.ai
- Tools
- save_memory · search_memories · 14 more