How is this different from CLAUDE.md?

CLAUDE.md is a static file you edit by hand and loads in full every session. Kit for AI memory is written by Claude Code itself mid-session, retrieved by meaning only when relevant, deduplicated, and shared with your other AI tools.

Does Claude Code 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 Claude Code 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 Claude Code

Claude Code 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 Claude Code forgets

Every Claude Code session starts from zero — yesterday's architecture decision, the flag you always pass, the gotcha you hit last week are all gone. CLAUDE.md helps but it's static: you maintain it by hand and it can't be recalled by meaning. Persistent memory lets Claude Code save facts as it works and recall them in any later session, automatically.

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

1Install the Kit for AI plugin from the marketplace (one command, includes the MCP server and skills):
2Or add the raw MCP server instead: claude mcp add --transport http kit-for-ai https://kitforai.com/api/mcp --header "x-api-key: YOUR_API_KEY"
3Create a free API key at kitforai.com/app/settings and paste it when asked.
4That's it — Claude Code now has remember and recall tools it uses on its own.

/plugin marketplace add l33tcy/kitforai-claude

Give Claude Code a memory today

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

Start free How the MCP memory server works

FAQ

How is this different from CLAUDE.md?: CLAUDE.md is a static file you edit by hand and loads in full every session. Kit for AI memory is written by Claude Code itself mid-session, retrieved by meaning only when relevant, deduplicated, and shared with your other AI tools.
Does Claude Code 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 Claude Code 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.