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

# Overview

> Core capabilities that make MemWire unique.

MemWire is built around a set of distinct primitives that go beyond basic memory storage. Each feature is composable, you can use all of them together or only the ones your application needs.

<CardGroup cols={2}>
  <Card title="Graph Memory" icon="diagram-project" href="/features/graph-memory">
    Token-level displacement graph connects memories through semantic relationships for multi-hop recall.
  </Card>

  <Card title="Multi-Tenancy" icon="building" href="/features/multi-tenancy">
    Native four-level hierarchy isolates memory across orgs, workspaces, apps, and users.
  </Card>

  <Card title="Knowledge Base" icon="book-open" href="/features/knowledge-base">
    Ingest documents and chunks that are searched alongside episodic memories at recall time.
  </Card>

  <Card title="Hybrid Search" icon="magnifying-glass" href="/features/hybrid-search">
    Dense and sparse (SPLADE) vectors combined for retrieval that catches both semantic and exact matches.
  </Card>

  <Card title="LLM-Free Classification" icon="tag" href="/features/llm-free-classification">
    Every memory is auto-tagged by category using smart anchor similarity with zero external LLM API calls.
  </Card>

  <Card title="Adaptive Feedback Loop" icon="arrow-rotate-right" href="/features/adaptive-feedback">
    Edge weights update from real LLM responses, so the memory graph improves with every conversation.
  </Card>
</CardGroup>