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

# Introduction

> What Atlas is, why it exists, and how it fits into your AI stack.

## What is Atlas?

Atlas is a **production-grade memory backend** for AI agents. Instead of losing context between conversations or cramming everything into a single prompt, Atlas gives your agents three distinct, interconnected memory stores that mirror how human memory actually works.

<CardGroup cols={3}>
  <Card title="Episodic Memory" color="#6366F1" icon="clock-rotate-left">
    Stores raw conversation chunks as vector embeddings in **Qdrant**. Enables fast similarity search over past experiences.
  </Card>

  <Card title="Semantic Memory" color="#818CF8" icon="diagram-project">
    Extracts entities and relationships into a **Neo4j knowledge graph**. Supports multi-hop reasoning across facts.
  </Card>

  <Card title="Working Memory" color="#4F46E5" icon="bolt">
    A per-session sliding context cache in **Redis**. Tracks rolling topic vectors, recent entities, and hot facts.
  </Card>
</CardGroup>

***

## How it works

When you call `brain.add("Sarah is the Lead Engineer at Acme Corp.")`, Atlas:

1. **Chunks** the text using a semantic chunker (embedding-aware sentence grouping)
2. **Extracts** named entities and relationships via LLMGraphTransformer or spaCy
3. **Stores** vector embeddings in Qdrant (episodic) and graph triples in Neo4j (semantic)
4. **Updates** the session topic vector in Redis (working memory)

When you call `brain.search("Who manages engineering at Acme?")`, Atlas:

1. Runs **hybrid retrieval** across all three stores simultaneously
2. Scores results vector similarity, recency, frequency, graph strength
3. Returns ranked, de-duplicated facts ready to inject into your LLM system prompt

***

## Key features

<AccordionGroup>
  <Accordion title="Hybrid scoring — not just vector search">
    Atlas scores memories on four axes: **V**ector similarity, temporal **R**ecency (Ebbinghaus decay), access **F**requency, and graph **A**ssociation strength. This means recently-reinforced, highly-related facts always surface above stale noise.
  </Accordion>

  <Accordion title="Multi-hop graph reasoning">
    Ask complex relational questions across up to 5 hops in the knowledge graph. Atlas traverses entity relationships and grounds LLM answers in retrieved facts — no hallucination.
  </Accordion>

  <Accordion title="Memory lifecycle management">
    Memories decay over time via the Ebbinghaus forgetting curve. Consolidation compresses related clusters into abstractions. Pruning removes low-confidence nodes below a configurable threshold.
  </Accordion>

  <Accordion title="Tenant isolation built-in">
    Every memory write and read is scoped to a `user_id` derived server-side from your API key. No cross-tenant leakage is possible — even if a client sends the wrong `user_id`.
  </Accordion>

  <Accordion title="Zero-dependency Python SDK">
    The `atlas-mem` package requires only `requests`. Async support via `httpx` is available as an optional extra.
  </Accordion>
</AccordionGroup>

***

## Pricing & tiers

| Tier       | Monthly Ops | Batch Size | Graph QA | Prune |
| ---------- | ----------- | ---------- | -------- | ----- |
| Free       | 1,000       | 5          | ✗        | ✗     |
| Starter    | 50,000      | 20         | ✓        | ✗     |
| Pro        | 500,000     | 50         | ✓        | ✓     |
| Scale      | 5,000,000   | 100        | ✓        | ✓     |
| Enterprise | Unlimited   | 100        | ✓        | ✓     |

<Note>
  Operation costs: `ingest` = 5 ops, `retrieve` = 2 ops, `graph_qa` = 10 ops, `consolidate` = 3 ops, `prune` = 1 op, `stats`/`health` = free.
</Note>

***

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/getting-started/quickstart">
    Be up and running in under 5 minutes.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Full endpoint documentation with request/response schemas.
  </Card>
</CardGroup>