Skip to main content

Memory

You might still wonder what sets Clatri apart from ChatGPT and whether ChatGPT counts as an agent. Well, ChatGPT is, in fact, an agent. Claude.ai is too. Same with Gemini App. But GPT is not an agent, Claude is not an agent, and Gemini is not an agent.

What does that mean? The companies behind the large language models -- OpenAI, Anthropic, Google -- offer them for consumption through APIs. A developer can call GPT, Claude, or Gemini from their code and get text responses back. That's a model, not an agent. But those same companies also build consumer products -- ChatGPT, Claude.ai, Gemini App -- and they've been adding agentic capabilities to them: they can generate Python code and run it, create Excel files, search the web, generate images, and connect to external services. Over time, these chatbots gain more tools and behave more like agents.

All of them remember things about you -- preferences, past conversations, context. But the way they remember has concrete limits that determine what they can and can't do with your information. Clatri remembers differently, and that difference changes what's possible.

Three ways of knowing you​

Structured memory​

When you send a message to ChatGPT, Claude.ai, or Gemini App, the model might remember that in some conversation you mentioned an expense at a restaurant. But it can't sum up your transactions for the month, because it doesn't store them in a structured way. There's no expense table with date, amount, category, and account. There's only remembered text -- approximate, incomplete.

Clatri stores every piece of data you log -- an expense, an income, a medication, a task, an appointment -- in a PostgreSQL database with defined tables, columns, and relationships. When you ask "how much did I spend on restaurants in January?", the agent doesn't search through past conversations: it runs a SQL query against your actual transactions, filtered by category, date, and entity. The result is exact, not approximate.

Clatri operates on over 60 structured tables across 8 PostgreSQL schemas. Each table has relationships, constraints, and security rules. When the agent acts, it works on real data with accounting-grade precision.

Semantic memory​

Structured memory solves for precision, but it doesn't cover everything. Some things don't fit in a table: the context of a past conversation, a decision you made days ago, a thread that was left open.

For that, Clatri uses semantic memory with RAG (Retrieval-Augmented Generation). The system periodically creates compressed summaries of your conversations and stores them as embeddings -- numerical representations that capture the meaning of what was said, not the exact words. When you send a message, the agent retrieves the fragments from past conversations that are semantically relevant to what you're asking -- without you having to repeat the context.

This means that if last week you were discussing the details of your trip to Japan in September, the agent can pick that thread back up without you having to explain everything again. And since it complements structured memory, it doesn't just remember what you talked about -- it can also access the destinations, dates, flights, and hotels that were explicitly recorded in your data.

Entity description​

There are things you want the agent to always know -- who you are, what you do, what your situation is -- but that you shouldn't have to repeat every time you talk to it.

The entity description is a free-text field in each entity's settings where you write context you want the agent to keep in mind at all times. It's injected into every message you send -- it's simply a way to give it persistent, useful context from the settings.

Think of the description as a permanent introduction. You don't need to remind the agent that you have diabetes every time you ask something about health, or tell it that your business operates in Colombian pesos every time you log an expense. You write it once and the agent always has it.

Personal description examples:

I live in Mexico City. I'm 32, freelance designer.
I take metformin 850mg twice a day for type 2 diabetes.
My monthly food budget is $8,000 MXN.
I'm saving for an apartment -- my goal is $500,000 MXN by December 2026.
My main income comes from UX design projects.

Business description examples:

Coffee shop "El Grano" in Bogota. 3 employees.
Main currency: COP. Opened in 2022.
We sell specialty coffee and artisan pastries.
Our main supplier is Cafe de Colombia S.A.
Hours: Monday to Saturday, 7am to 7pm.
Average monthly revenue: $12,000,000 COP.

The description is entity-specific. You can have a detailed personal description and a business one with completely different context.

The combination of these three forms -- structured data for precision, conversational memory for continuity, and explicit description for permanent context -- is what lets Clatri know you in a way that a general-purpose chatbot can't replicate.

A single chat​

In ChatGPT, Claude.ai, or Gemini App, you create separate chat sessions: one to get help with an email, another to talk about cooking, another for code. Each session is an independent thread with its own context, and if you want to revisit something you said in another conversation, you have to find it yourself.

Clatri works differently. Since its purpose is to be your agent for everything -- finances, health, tasks, projects -- it uses a single continuous chat per entity. There are no sessions to open and close. You talk to it and the agent keeps your recent messages plus the relevant fragments it retrieves from your semantic memory, which gives it continuity without you having to repeat context. It doesn't need separate sessions because its tools operate on your database: the real context isn't in the conversation, it's in your data.