# CEREBROs

<figure><img src="/files/9TnDKrSXLTAOsQBTpF4u" alt=""><figcaption></figcaption></figure>

CEREBRO

**/sə-REE-broʊ/** • *noun* • plural **CEREBROs**

**1.** *(computing, AI agents)* A modular **temporal knowledge graph** and API that plugs into an AI agent to provide **structured, persistent memory**, **pedagogical logic** (prerequisites, mastery, reinforcement), and **explainable reasoning paths**.\
→ In practice, a “brain module” that returns structured answers and traces (concepts, rules, sources, paths) and updates a learner/user’s mastery over time.

**2.** *(by extension)* Any curated, domain-specific “brain” package that can be composed with others to specialize an agent (e.g., a Math CEREBRO + a Physics CEREBRO).

**Etymology.** Backronym of **C**omposable **E**ducational **R**eusable **E**xplainable **B**rain **R**esource for **O**perations; also echoes Spanish *cerebro* “brain.”

#### **Key Components**&#x20;

* **Knowledge graph core**: Concepts, relations, temporal metadata, provenance.
* **Pedagogical layer**: Prerequisites, mastery thresholds, adaptive reinforcement.
* **Explainability & trace layer**: Reasoning paths with sources.
* **Interface layer**: REST, function calling, MCP.

#### **Usage**

* Plug the **Calculus CEREBRO** into the tutor agent so it can explain derivatives with traceable sources.
* Our research assistant runs multiple **CEREBROs** and switches between them by intent.

**See also:** knowledge graph; RAG (retrieval-augmented generation); LLM; AI agent.

***

<hola@cerebros.dev>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://cerebros.gitbook.io/cerebros/cerebros.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.