# Penny

> Secure, portable memory for the AI tools you use.

## About
Penny is a private memory layer for AI tools, made by Helper Labs; mypenny.ai is its
web address. You save memories and notes once, and any AI assistant you authorize can
read and write them over the Model Context Protocol, so you don't start over each time
you switch tools. Penny works with Claude, ChatGPT, Perplexity, Cursor, Codex, and
Claude Code.

Your memories and notes are encrypted with AES-256-GCM under a key unique to you, held
in a separate hardware-backed account. Every time Penny's service decrypts your memory,
it's on record in your dashboard and sealed into a public, tamper-evident log. Penny is
not end-to-end encrypted: AI tools need your memory in plain text to use it, so we don't
claim we can't read it; we commit that we won't.

We don't sell your data, don't serve ads, and don't train models on your memory, and we
only use AI providers that don't train on it either.

## Pages
- [Home](/)
- [How it works](/how-it-works)
- [About](/about)
- [For engineers](/for/engineers)
- [For families](/for/families)
- [For professionals](/for/professionals)
- [For students](/for/students)
- [Privacy & Security](/privacy)
- [Transparency](/transparency)
- [MCP connector docs](/docs/mcp)
- [Blog](/blog)
- [Get started](/get-started)
- [Contact](/contact)
- [Terms](/terms)