# Your AI remembers you. You decide what. > Your AI remembers you: what changes, how a memory is saved, how memory moves from one model to another, where your files stay and how to try it in one click. *designed version: https://illaira.com/en/voglio-usarla · index: https://illaira.com/en/llms.txt* --- [Skip to content](#contenuto) I want to use it Without learning anything technical: open the WebApp, take the free module, and from there your AI knows who you are, what it remembers about you and how you want it to behave. The files stay yours, on your device. [Open the WebApp](https://illaira.com/en/webapp) ## The problem: every conversation starts from scratch Close the chat and your AI has already forgotten you. What you explained yesterday must be explained again tomorrow, and if you change service you start over. The memory the provider gives you is theirs: written by them, usable only there. [“But my AI already has memory”: what it really does](https://illaira.com/en/come-funziona.md#obiezione-memoria) ## What changes: an AI that recognises you Who your AI is, what it remembers about you and how you want it to behave are written in files of yours. You load them at the start, and the conversation picks up where you left it — same tone, same rules, same memories. [What the app does, gesture by gesture](https://illaira.com/en/clm.md#funzioni) ## Save this memory: the MemoKen At the end of a conversation you ask your AI for the summary of what matters — it writes it, with a free module. You select it, one click on MemoKen, and the memory lands in the right diary, with the date. You always confirm: nothing writes itself. On the App the tile also has the DROP face: it hands your files to the chat in your provider’s app, in batches — or the other ways your AI takes files. In the browser MemoKen is an extension you install from the WebApp (capture). On the phone it is a tile that stays on the edge of the screen while you are in the chat, and it has two faces: MEMO files the log, DROP hands your files to the other app in batches, toward a quick chat. [The MemoKen in the WebApp and on the App](https://illaira.com/en/webapp-info.md) How you use it ## Three steps, and the first one is a click. 1. ### Open the WebApp and take the Loom It opens in your browser, free with an account. The Loom is the starting Reminder: it is born empty on purpose, and the free modules from the Bazar are added from inside. [Open the CLM WebApp](https://illaira.com/en/webapp) 2. ### Write who your AI is Identity, rules, memories: every module is a node on the Sphere Grid. You switch it on with a click and the rest stays where it was — no walls of text to rewrite. And the memories aren't yours to write: the model hands them to you, and MemoKen files them with one tap. [The method, in full](https://illaira.com/en/come-funziona.md) 3. ### Load it into your model You export the file and put it where your model keeps its documents — your AI’s chat, the place for files. From there it rereads it at every conversation. It is Markdown, the Standard is open: no engine is left out. [Where it goes, model by model](https://illaira.com/en/approfondimenti/dove-caricare.md) It works with any model that accepts a file or a permanent instruction, including: - Gemini Notebook - Claude - ChatGPT - Gemini - Copilot - Grok - Perplexity - Le Chat - local models These are the names in use as we write: they change, the gesture doesn’t. It pays off most where the model has a place to keep files: a Claude, ChatGPT or Grok Project, a Gem with Gemini Notebook as its library. You load the base matrix once and find it in every conversation, and you can keep several specialised notebooks with only the modules they need. With coding agents, the files are local and they read them by themselves. [Where it pays off most →](https://illaira.com/en/come-funziona.md#progetti) ## Your files, under your control They are text files on your device, in a folder you choose or in the browser’s storage. The WebApp talks to the server only to know who you are and which modules you can download: what you write never leaves. - Ownership: the files are yours, and they stay where you put them even if IllAIra closed down. - Privacy: nothing you write goes to our servers, and no hidden tracking. - Portability: it is Markdown, an open standard — ZIP export whenever you like, and any model reads the same file. - Inspectability: you can read every line of what your AI remembers, and delete it. [The Privacy, in full](https://illaira.com/en/privacy.md) ## Try it, and install it if you like The WebApp opens in the browser, free with an account. The Android App is in beta and installs by hand from the site. Same account, same files: what you do on one side you find on the other. [Open the WebApp](https://illaira.com/en/webapp) · [Download the Android App](https://illaira.com/en/download.md) ## When you want to look underneath In the WebApp, Advanced mode shows the technical names and every command: Reminder, modules, Markdown, search by meaning, encryption. You switch from Settings › Mode, and nothing is lost going from one to the other. [The technical path: how it is built underneath](https://illaira.com/en/voglio-capire.md) Two paths, one base - ### I want to use it You are here Your AI remembers you, from one conversation to the next and from one model to another. What changes for you, how a memory is saved, where your files stay, and how to try it in one click. - ### [I want to understand it](https://illaira.com/en/voglio-capire.md) Markdown and parser, Nuclei and modules, search by meaning, provenance, Sphere Grid, compatibility: how it is built underneath, with the documentation and the table of the two names of every thing. [The technical path](https://illaira.com/en/voglio-capire.md) Same files, same engine: only the words we tell it with change. In the WebApp too: Simplified, Intermediate and Advanced mode, and you switch whenever you like.