Question 1

What is an AI memory layer?

Accepted Answer

An AI memory layer is a single, portable store of who you are and how your AI behaves — your context plus the AI's voice, values and conventions — that any AI assistant can read. aiperson keeps yours in a signed, local-first file you own, so the same persona is present in ChatGPT, Claude, Gemini, local models and 30+ editor and chat surfaces instead of being trapped inside one vendor.

Question 2

How is this different from ChatGPT memory or Claude memory?

Accepted Answer

Vendor memory lives on the vendor's servers, in the vendor's format, and only inside that one app. The March-2026 import features let you copy it out once, lossily, into the next app. aiperson is different: the persona is a file you hold, signed by your own key, present across every AI at once — not a one-time copy. You can export it any time and self-host it.

Question 3

Do you store my data?

Accepted Answer

By default, no. Your persona lives in a git repo you own and your corpus is a local SQLite file at ~/.dotperson/corpus.db. The relay handles sign-in, GitHub brokerage and synthesis — it is not a copy of your conversations. You choose, per data kind, what (if anything) is mirrored for cross-device sync.

Question 4

Does it work with local models like Llama or Ollama?

Accepted Answer

Yes. Because the persona is a plain file you own — not a vendor feature — you can cultivate an AI under Claude and move it intact to a locally-hosted Llama, persona and all. Local models are a first-class audience, not an afterthought.

Question 5

What does it cost?

Accepted Answer

It is free while we build toward our first 100 Founding Members. No credit card. Sign in with GitHub, run two commands, and your existing AI tools gain a shared memory in under ten minutes.

Your AI has a
memory. You own it.

Live capture health

Persona

Connectors

Recent activity

Observers watching

Corpus

Privacy

Sign in to aiperson

Your AI has amemory. You own it.