How is this different from Cursor rules (.cursorrules)?

Rules are static instructions you write and maintain. Kit for AI memory is dynamic: the agent writes it as it learns, retrieval is by meaning, near-duplicates are merged, and the same store follows you to other tools.

Does Cursor save memories automatically?

Yes — once connected, the agent has remember and recall as callable tools and uses them on its own: it saves decisions and preferences mid-conversation and retrieves them when they're relevant. You can also tell it explicitly to remember something.

Memories are owner-scoped to your account, served over HTTPS, with encryption at rest for stored content and an audit trail of what agents wrote. You can review, edit, and delete every memory from the dashboard.

Can my other AI tools share this memory?

Yes — that's the point. The same store is reachable from every MCP client and over REST, so what Cursor learns, Claude, Cursor, and your own code can recall too.

There's a free plan — an account and API key cost nothing, and setup takes about two minutes. Paid plans add higher quotas and team features.

Memory for every AI tool

Persistent memory for Cursor

Cursor forgets everything between sessions. Connect it to Kit for AI and it saves what matters as it works — and recalls it in any later session, on any machine.

Why Cursor forgets

Cursor's agent is sharp in the moment and amnesiac across sessions — project conventions, past refactors, and decisions vanish between chats. Rules files are static and hand-maintained. With a memory MCP server, Cursor saves what matters while it works and recalls it next time without being told.

What you get

remember / recall as tools the agent calls on its own — no manual note-keeping.
Retrieval by meaning: "what did we decide about auth?" finds the JWT decision.
One shared store: what this tool learns, Claude, Cursor, and your code can recall too.
Near-duplicate detection and versioning keep months of memories clean.
Same account ingests documents and URLs — memory and knowledge in one retrieval system.

Set it up in about 2 minutes

1Open Cursor → Settings → MCP → Add new global MCP server (or create .cursor/mcp.json in your project).
2Paste the kit-for-ai config (below).
3Create a free API key at kitforai.com/app/settings and replace YOUR_API_KEY.
4Reload — Cursor's agent now has remember, recall, and knowledge-base search tools.

{
  "mcpServers": {
    "kit-for-ai": {
      "type": "http",
      "url": "https://kitforai.com/api/mcp",
      "headers": { "x-api-key": "YOUR_API_KEY" }
    }
  }
}

Give Cursor a memory today

Free account, one API key, one config block. What Cursor learns today, every AI tool you use can recall tomorrow.

Start free How the MCP memory server works

FAQ

How is this different from Cursor rules (.cursorrules)?: Rules are static instructions you write and maintain. Kit for AI memory is dynamic: the agent writes it as it learns, retrieval is by meaning, near-duplicates are merged, and the same store follows you to other tools.
Does Cursor save memories automatically?: Yes — once connected, the agent has remember and recall as callable tools and uses them on its own: it saves decisions and preferences mid-conversation and retrieves them when they're relevant. You can also tell it explicitly to remember something.
Is my data private?: Memories are owner-scoped to your account, served over HTTPS, with encryption at rest for stored content and an audit trail of what agents wrote. You can review, edit, and delete every memory from the dashboard.
Can my other AI tools share this memory?: Yes — that's the point. The same store is reachable from every MCP client and over REST, so what Cursor learns, Claude, Cursor, and your own code can recall too.
Is it free?: There's a free plan — an account and API key cost nothing, and setup takes about two minutes. Paid plans add higher quotas and team features.

Memory for your other tools

Deep dive: how to share one memory across all your AI models.