Claude Code

For AI Agents

Machine-readable docs: mnemoverse/llms.txt (works in all sandboxes)

Give Claude persistent memory. One command — it never forgets again.

Claude Code — add via CLI:

claude mcp add mnemoverse \
  -e MNEMOVERSE_API_KEY=mk_live_YOUR_KEY \
  -e MNEMOVERSE_API_URL=https://core.mnemoverse.com/api/v1 \
  -- npx -y @mnemoverse/mcp-memory-server@latest

That's it. Claude Code now has long-term memory across all sessions.

Get your API key at console.mnemoverse.com (free tier, no credit card).

Prefer no API key? Connect over one-click OAuth instead — sign in with your browser, nothing to paste.

Using the Claude apps, not the CLI?

Claude Desktop, claude.ai (web), and mobile set up differently — see Claude Desktop, Web & Mobile.

Try It

Make Claude actually use Mnemoverse

By default Claude answers from its own context — and Claude Code keeps its own CLAUDE.md notes — so it won't call Mnemoverse unless you tell it to. Set a one-line standing instruction first: Make Your Agent Use Memory.

With that in place, the point is one memory across tools. In Claude Code:

"Remember: staging deploys go through make deploy-staging, never Railway directly."

Later, in Cursor or ChatGPT — a different tool, even days later:

"How do I deploy staging here?"

It recalls the rule, because the memory lives in Mnemoverse, not in any single tool. (A single-tool "it remembers" demo wouldn't prove much — the tool's own memory could do that; cross-tool recall is what needs Mnemoverse.)

Tools

The MCP server gives Claude 6 core memory tools (the Beta shared-room tools are covered separately below):

memory_write — Store a memory

When Claude learns something worth keeping — a preference, a lesson, a decision — it stores it.

You: "I prefer Tailwind over CSS modules"
Claude: [calls memory_write]
    content: "User prefers Tailwind CSS over CSS modules for styling"
    concepts: ["tailwind", "css", "styling", "preferences"]
→ Stored (importance: 0.82)

Name	Type	Required	Description
content	string	Yes	What to remember (1-10,000 chars)
concepts	string[]	No	Key concepts for linking memories
domain	string	No	Namespace: "engineering", "user:alice"

memory_read — Recall memories

Before starting a task, Claude checks what it already knows.

You: "Set up the database"
Claude: [calls memory_read]
    query: "database setup preferences and history"
→ 1. [92%] Project uses PostgreSQL 15 + Prisma ORM (engineering)
  2. [87%] Always run migrations with --create-only first (lessons)
  3. [71%] DB hosted on Supabase, connection string in .env.local

Name	Type	Required	Description
query	string	Yes	Natural language search (1-5,000 chars)
top_k	integer	No	Max results (default: 5, max: 50)
domain	string	No	Filter by namespace

memory_feedback — Rate memories

After using a memory, Claude reports whether it helped. Good memories surface faster next time.

Claude: [calls memory_feedback]
    atom_ids: ["550e8400-..."]
    outcome: 1.0  // Very helpful!
→ Feedback recorded for 1 memory.

Name	Type	Required	Description
atom_ids	string[]	Yes	Memory IDs from read results
outcome	number	Yes	-1.0 (harmful) to 1.0 (very helpful)

memory_stats — Check status

Claude: [calls memory_stats]
→ Memories: 1,250 (500 episodes, 450 prototypes)
  Associations: 8,500 Hebbian edges
  Domains: engineering, user:alice, project:acme
  Avg quality: valence 0.65, importance 0.72

memory_delete — Forget one memory

For when Claude stored a wrong fact or the user explicitly asks to forget something specific.

You: "Forget what I said about Railway — we moved to Fly.io"
Claude: [calls memory_read to find the atom_id, then memory_delete]
    atom_id: "550e8400-e29b-41d4-a716-446655440000"
→ Deleted memory 550e8400-....

Name	Type	Required	Description
atom_id	string	Yes	The atom_id of the memory to delete (from memory_read results)

Idempotent — deleting an already-gone memory returns "No memory found with id ..." instead of an error.

memory_delete_domain — Wipe an entire topic

For broad cleanups when the user wants to forget everything in a namespace — e.g. "wipe my benchmark experiments". This is much more destructive than memory_delete, so Claude should only call it after an explicit user request, and the confirm: true parameter is a safety interlock enforced by the schema.

You: "Wipe everything about project:old-client"
Claude: [calls memory_delete_domain]
    domain: "project:old-client"
    confirm: true
→ Deleted 42 memories from domain "project:old-client".

Name	Type	Required	Description
domain	string	Yes	The domain namespace to wipe (must match exactly)
confirm	literal true	Yes	Safety interlock — must be exactly true

Shared rooms (Beta)

Beyond your private memory, Claude can share a memory pool with other people's assistants through a room. Three Beta tools — memory_create_room, memory_invite_to_room (which mints a one-time share code, mnvr_...), and memory_join_room — let Claude spin up a room, invite someone, and join one. Members then read and write the shared pool by passing domain: "xroom:<room_id>" on memory_write / memory_read. See Join a shared room for the full owner-and-joiner flow.

What to Remember

Category	Example
Preferences	"User prefers dark mode", "Always use pnpm, not npm"
Project context	"This repo uses PostgreSQL + Prisma", "Deploy target is Railway"
Lessons learned	"Never deploy on Fridays", "Run tests before push"
Decisions	"Chose REST over GraphQL for caching simplicity"
People	"Alice owns the design system", "Bob reviews all API changes"
Patterns	"Exponential backoff fixed timeout issues in this service"

Universal Memory

Same API key, same memories — across all tools.

                    ┌── Claude Code ← you are here
                    ├── Claude Desktop / web / mobile
   Mnemoverse API ──├── Cursor / VS Code / Windsurf
   (one memory)     ├── ChatGPT
                    └── Python SDK / REST

Write a memory in Claude Code → ChatGPT reads it. Learn something in Cursor → Claude Code recalls it.

Configuration

Variable	Required	Default
MNEMOVERSE_API_KEY	Yes	—
MNEMOVERSE_API_URL	No	https://core.mnemoverse.com/api/v1

Source & Distribution

The MCP server is also listed on the Official MCP Registry. Source on GitHub under MIT.

Related

• Make Your Agent Use Memory — the standing-instruction technique so Claude actually calls the tools
• Remote MCP Server — connect over one-click OAuth, no API key
• Cursor, VS Code & Windsurf — editor integrations
• ChatGPT — give any Custom GPT persistent memory
• Python SDK — for scripts and backends
• Rooms — share a memory pool across accounts (Beta)
• API Reference — full endpoint documentation