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

# Reconstructive Recollection

> Active, context-aware memory retrieval and synthesis

Traditional search is passive: you type a query, and the system finds documents that match your words. **Reconstructive Recollection** is active: the Agent analyzes your current intent and *rebuilds* the necessary context from its memory store to best support the task at hand.

## Beyond Vector Similarity

Standard RAG systems rely heavily on vector similarity search (k-NN). While fast, this often fails in complex scenarios:

* **The "Lost in the Middle" Phenomenon**: Retrieving too many loose chunks confuses the LLM.
* **Lack of Context**: A retrieved chunk might be factually correct but irrelevant to the *current* nuance.

EverOS uses a **dual-process** approach:

1. **Scene Activation**: First, the system identifies which [MemScene](/cloud/concepts/memscene) (topic) is currently active.
2. **Agentic Walk**: The system then traverses the connections within that MemScene to find specific [MemCells](/cloud/concepts/memcell) that answer the query.

## The Reconstruction Process

When a user prompt arrives (e.g., *"Draft an email update for the project we discussed last week"*):

<Steps>
  <Step title="Intent Analysis">
    The system determines the user wants to write an email (Task) about "the project" (Topic) referencing "last week's discussion" (Time/Constraint).
  </Step>

  <Step title="Scene Loading">
    The relevant "Project" MemScene is loaded.
  </Step>

  <Step title="Context Synthesis">
    The system doesn't just return the raw transcript of last week's meeting. It **reconstructs** the memory:

    * It pulls the *Decisions Made* (Fact).
    * It pulls the *Action Items* assigned to the user (Fact).
    * It ignores the *Small Talk* about the weather (Irrelevant Episode).
  </Step>
</Steps>

## Adaptive Retrieval

Reconstructive Recollection is adaptive.

* **For factual queries** ("What is my API key?"), it performs a precise lookup of Atomic Facts.
* **For creative tasks** ("Brainstorm ideas based on my previous notes"), it retrieves broader episodic narratives to inspire the model.
* **For reasoning tasks** ("Why did we decide to switch databases?"), it traces the causal chain across multiple MemCells to explain the *history* of a decision.

<Tip>
  This mechanism mimics human recall. When you tell a story, you don't replay a video tape of your life; you reconstruct the narrative based on the key highlights relevant to your current listener.
</Tip>