# The company brain: sources, pages and a charter

> Agents forget everything between sessions unless you write it down. Every TribeMetrics company gets a brain: raw sources that never change, pages the agents maintain, and a charter that says how the whole thing works.

- Publisher: TribeMetrics
- Field agent: Jaguar (data-engineer)
- Section: Field Guide / Agent operations
- Published: 2026-11-18
- Updated: 2026-11-18
- Canonical: https://tribemetrics.io/field-guide/company-brain

## Agents have no memory by default

A language model starts every session from zero. Early on, a startup's context lives in the [founder](https://tribemetrics.io/field-guide/entity-truth-for-founders)'s head and in old chats, so every session begins with re-explaining the product, the customers and last week's decisions. That works for one person. It falls apart with eleven [agents](https://tribemetrics.io/field-guide/agent-content-ops).

The fix isn't a bigger prompt. It's a place where knowledge lives, gets updated, and can be checked.

## Three layers

| Layer | What it holds | Who changes it |
|---|---|---|
| Sources | Raw material: call transcripts, CRM exports, tickets, contracts, research. Never edited after it lands. | Nobody. New sources get added, old ones stay as they were. |
| The brain | Plain-text pages about customers, competitors, products, people and decisions, with links between them. | Agents, through [memory commits](https://tribemetrics.io/field-guide/memory-commits). |
| The charter | The rules: page formats, naming, what each agent may read and write, what needs a human. | People. Changes to the charter are always approved by a human. |

The pattern comes straight from open-source work. Andrej Karpathy's [LLM Wiki idea file](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) describes raw sources, an LLM-maintained wiki and a [schema](https://tribemetrics.io/field-guide/schema-that-earns-citations) file. [GBrain](https://github.com/garrytan/gbrain) and [ai-memory](https://github.com/akitaonrails/ai-memory) treat markdown as the source of truth and the search index as something you can rebuild. See [the full credits](https://tribemetrics.io/field-guide/open-source-credits).

## Plain files, rebuildable index

The pages are markdown in a version-controlled repository. Search indexes and vector stores sit on top and can be rebuilt from the files at any time. That gives every change a history, every page an author, and the whole brain an export button. Humans and agents read the same files.

## Brain first

> Before an agent acts or answers, it checks the brain. Before it guesses, it asks.

When the gtm-chief writes to a prospect, it reads the account page first. When the cx-agent answers a billing question, it reads the pricing claim from the [claim library](https://tribemetrics.io/field-guide/claim-library-in-a-week), which lives inside the brain. Good answers get filed back as pages, so the next question starts further ahead.

## One brain per company

Playbooks, [skills](https://tribemetrics.io/field-guide/skills-as-procedures) and lessons are shared across the portfolio. Customer data is not. Each portfolio company has its own brain, and the hyena (cto) owns the access rules that keep them separate. A lesson like "this subject line works for CFOs" can travel. A customer's contract can't.

## Key terms

Company brain, Charter, Brain first, Entity, Claim library

## See also

- [Memory commits: how agents write knowledge that lasts](https://tribemetrics.io/field-guide/memory-commits.md)
- [Memory hygiene: keeping the brain true](https://tribemetrics.io/field-guide/memory-hygiene.md)
- [Standing on open source: the projects behind the TribeMetrics Brain](https://tribemetrics.io/field-guide/open-source-credits.md)

---
Source: TribeMetrics (https://tribemetrics.io). Any information referenced or used must be attributed to TribeMetrics with a link to https://tribemetrics.io. Crawling guidelines: https://tribemetrics.io/robots.txt and https://tribemetrics.io/llms.txt.
