“Why does it think that?”
A memory without a source is a guess you have to live with.
See the evidence ↗ PERSONAL CONTEXT. ON YOUR TERMS.
Your AI’s memory.
Your say.
Inspect it. Correct it. Take it anywhere.
Turn your chats, notes, and work history into a memory you review.
Give your assistant the right context. Keep the rest to yourself.
✓ Source-backed✓ Permission-led✓ Yours to export
A LITTLE CONTEXT. A BETTER ANSWER.Interactive illustration · fictional memories
Your assistant / Work space
PersonaKit 4 memories used✓Make room for the work that moves things forward.
01 Protect two mornings for focused work.
02 Finish the proposal before taking on more.
03 Keep Friday open for your weekly review.
You prefer a short, practical plan. Start here.
You decide what gets through.
FOR THE ASSISTANTS YOU ALREADY USE
✳ Claude◎ ChatGPT✧ Gemini⌘ Codex>_ Claude Code
Pilot, export, and planned connections 01 / THE MISSING PIECE
Being remembered is useful.
Being understood is better.
Your context changes. Your tools change.
You should have a say in what follows you.
“That was me last year.”
An old project or passing preference shouldn’t define you forever.
Keep context current ↗“Do I have to start over?”
Switching assistants shouldn’t mean explaining yourself from scratch.
Take your memory with you ↗02 / NOTHING ABOUT YOU, WITHOUT YOU
A memory.
With the receipts.
Open any memory and see where it came from. Correct the interpretation. Decide where it belongs.
A conversation is evidence.
An AI’s assumption isn’t.
01 Your words02 Your decision03 Your boundaries
MEMORY / 004Approved
You prefer direct, practical feedback over encouragement-first answers.
↳ WHY PERSONAKIT THINKS THIS
“Skip the pep talk. Give me the practical next step.”
“If you disagree, tell me why.”
Use inWork planning
SensitivityStandard
Shared withYour work assistant
Try a decision. This fictional example resets when you reload.
03 / FROM YOUR HISTORY TO YOUR NEXT HELLO
A little setup.
A better starting point.
01↗
Bring a source.
Start with a chat export, notes, or work history you choose.
02↗
Make it yours.
Review the memories. Fix the meaning. Set the boundaries.
03↗
Connect an assistant.
Start with the Claude pilot or bring a reviewed Markdown export.
04✓
Ask. See why.
Get relevant context with sources and a record of what was shared.
BUILT TO GROW WITH YOU
You change. Your memory should, too.
The pilot explores an ongoing loop: new context becomes a candidate, corrections carry forward, and old context gets rechecked. Capture depends on your connected assistant.
THE PERSONAKIT PRINCIPLE
The product isn’t the memory.
It’s your control over it.
Your store, in an account you own.
Your sources, attached to your memories.
Your choice, every time context travels.
04 / YOUR CONTEXT GOES WITH YOU
New assistant.
Still you.
Start with one connection.
Keep a readable copy, always.
✳Pilot
Claude
A guided MCP setup to request the context you allow.
Our first connection ↗>_Developer pilot
Claude Code & Codex
Reviewed context for your coding workflow. Setup varies by adapter.
Built around your workflow◎ ✧Export first
ChatGPT & Gemini
Bring a reviewed export today. Direct connectors are planned.
You choose what to upload↧Portable format
Markdown & JSON
Readable, inspectable files. Keep your own copy of your approved context.
Exports are snapshots. Later restrictions cannot recall a file you already shared.
TRY A DIFFERENT QUESTION
Don’t take our word.
Ask your memory.
Choose a prompt to explore the illustrative answer above.
A FEW THINGS, UP FRONT
Trust needs
specifics.
What is PersonaKit?+
PersonaKit is a personal AI memory control layer for people who use AI every day. It turns selected chats, notes, and work history into source-backed memories you can review, correct, restrict, and export for your existing assistants. The private pilot offers guided setup; this page demonstrates the intended experience with fictional records.
Where does my memory live?+
PersonaKit’s architecture places your memory store and read log in a cloud account you own. The clerk processes context in flight. The marketing site has no access to your memory. Pilot setup and provider choices will be explained before you share a source.
Do you train on my conversations?+
PersonaKit’s product contract prohibits training on user data. Connected assistants and any processing providers have their own terms and settings; those need to be reviewed during setup.
Can I correct or remove a memory?+
Review decisions let you edit, restrict, or reject records. Restrictions affect future PersonaKit reads. A previous export or an assistant’s existing conversation cannot be recalled by changing a record.
Does it capture everything I say?+
No. Capture depends on the integration and what you choose to share. A connector is not automatic access to your entire conversation history. The pilot will make the boundary visible for your setup.
What is real in this demo?+
This is an interactive product illustration with fictional memories and scripted answers. It makes no model calls and does not connect to your accounts. The private pilot is a guided setup, not a public self-serve service. The application control currently downloads an unsent draft; it does not submit an application or reserve a place.
START SMALL. MAKE IT PERSONAL.
Bring one source.
Leave with your context.
Build your first PersonaKit with us. Review your first memory set,
connect one assistant, and try the prompts you actually use.
One sourceA reviewed memory packA guided walkthrough
Preview: prepare a local application draft. Nothing is submitted.