> ## Documentation Index
> Fetch the complete documentation index at: https://docs.51ultron.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Memory & Intelligence

> How Ultron learns from every session and builds a persistent knowledge base about your business.

Ultron doesn't reset between sessions. Every research output, every confirmed preference, every error and its fix — all of it is stored, organized, and recalled automatically.

Memory is what separates Ultron from a stateless chatbot. Agents get smarter with every run. Skills produce better output over time. The more you use Ultron, the more it knows about your business.

## What gets stored

```text theme={null}
~/.ultron/memory/
├── MEMORY.md                        — index file (max 200 lines, 25KB)
├── user_founder_context.md          — your role, background, preferences
├── feedback_email_style.md          — corrections and confirmed patterns
├── project_q2_launch.md             — business context, dates, constraints
├── reference_competitor_acme.md     — research outputs, external pointers
├── feedback_lesson_specter.md       — self-improvement logs from agent errors
└── reference_meeting_prep_linear.md — pre-call briefs, post-call outcomes
```

Memory entries are plain markdown files. Each is tagged with type, agent, and topic. The index (MEMORY.md) gives Ultron a fast overview of everything stored.

## Four memory types

| Type          | Stores                              | Example                                                   |
| ------------- | ----------------------------------- | --------------------------------------------------------- |
| **user**      | Your role, background, preferences  | "I'm a B2B SaaS founder, ICP is Series A CTOs"            |
| **feedback**  | Corrections AND confirmations       | "Don't use em-dashes" / "That cold email structure works" |
| **project**   | Non-code business context           | "Q2 freeze starts April 15, no new features after that"   |
| **reference** | Research outputs, external pointers | Competitive analysis on HubSpot, meeting prep for Stripe  |

<Info>
  Feedback memory stores both errors and validations. When you confirm something works, Ultron stores that too. This prevents behavior drift — Ultron doesn't unlearn what's working.
</Info>

## How memory is used

At the start of every agent turn, a separate Sonnet-powered side-query runs against the memory store. It selects the 5 most relevant entries for the current task. Those entries are injected into context before Kimi K2 sees the message.

You don't manage this. It happens automatically.

<CardGroup cols={2}>
  <Card title="Memory Layers" icon="layer-group" href="/memory/memory-layers">
    The four memory types and when each is created.
  </Card>

  <Card title="Brain Graph" icon="diagram-project" href="/memory/brain-graph">
    Visual map of everything Ultron knows about your business.
  </Card>

  <Card title="Memory Recall" icon="magnifying-glass" href="/memory/memory-recall">
    How Ultron selects the right memories per turn.
  </Card>

  <Card title="Compression Engine" icon="compress" href="/memory/compression-engine">
    Three-layer cascade that keeps sessions running indefinitely.
  </Card>
</CardGroup>