Persona memory
A distilled sense of who you are and how you work, not a transcript, a model of the person it is helping.
A member that remembers how you work
It remembers how you work, and it knows the code on your machine, and it answers using both at once, instead of asking you to explain yourself again every morning. Open source, and it runs on your computer: your memory stays yours.
Try the memory engine live demo · nothing to install
Open source
0
things it remembers: how you work, and what you are building
1
conversation grounded in both, not a chatbot with amnesia
0
of it leaves your computer: nobody else’s training set, ever
Open
source at the core: yours to run, yours to read, yours to keep
What it is
One library, whole, not a platform you rent
It knows your code
It reads the project on this machine, so its answers are about what you are actually building, not the average of everything on the internet.
Grounded conversation
Every reply is grounded in the persona and the code graph at once: memory and context, not one or the other.
Binds to localhost
It runs on your machine and holds your memory there. Nothing is shipped off to be someone else’s training set.
Open at the core
Open source. The member itself is yours to run and to read; the commercial control plane is a separate concern.
A team version, when you need it
AI Member Cloud adds the accounts, teams and permissions the local version deliberately leaves out, for when the memory stops being one person’s.
By the shape of it
A teammate who forgets you between conversations is a search box. Memory is the whole difference.
2 + 1
40% Persona
40% Code graph
20% Conversation
Two memories, one grounded conversation: persona, code graph, chat.
How it works
Three moves, in order
01
Point it at your code
It reads what is actually on this machine and builds its own picture of the project.
02
Distill
Over time it forms a persona. A compact model of who you are and how you like to work.
03
Ground
Ask it anything. The reply draws on both the persona and the code graph, and never leaves localhost.
ai-member.ts
import { remember, ground } from '@quxkit/ai-member';
// a hybrid vector + lexical graph of the code on THIS machine
await remember.index({ root: '~/code/app' });
// a reply grounded in the persona and the code graph — never leaves localhost
const reply = await ground(prompt, { persona, graph });“
A teammate who forgets you between conversations is a search box. Memory is the whole difference.