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

# Conare Platform

> Conare gives your app custom retrieval infrastructure: per-user AI memory, a vector plus full-text database, hosted embeddings, and data connectors.

Conare gives your application its own retrieval stack: per-end-user **AI memory**, a **vector + full-text database**, and **embeddings** served from the same model that indexes your data — plus connectors that flow your users' tools into their memory.

## Products

<CardGroup cols={2}>
  <Card title="AI Memory" icon="brain" href="/memory/overview">
    Per-end-user persistent memory: save, hybrid search, LLM-synthesized deep recall, and proactive suggestions.
  </Card>

  <Card title="ConareDB" icon="database" href="/db/overview">
    Vector + full-text search engine with isolated namespaces. The substrate under AI Memory, also available standalone.
  </Card>

  <Card title="Embeddings" icon="binary" href="/embeddings/overview">
    Document-space vectors from the exact model Conare retrieves with. Stateless, unit-normalized, pinnable.
  </Card>

  <Card title="Integrations" icon="plug" href="/integrations/overview">
    Six first-class connectors plus a catalog of \~200 data sources your end users can connect in one click.
  </Card>
</CardGroup>

## Consumption modes

* **HTTP API** — your app embeds memory for *its* end users. Authenticate with an org-owned Integration key (`cint_...`); every request names an `endUserId`. Start with the [Quickstart](/platform/quickstart) or the [TypeScript SDK](/platform/sdk).
* **MCP** — coding agents (Claude Code, Codex, Cursor) use Conare directly as an MCP server at `https://api.conare.ai/mcp`. See [MCP tools](/memory/mcp).

## Custom models

For teams that want retrieval provably tuned to their own data, Conare trains and maintains custom embedding and reranking models, acceptance-gated on your golden query set. See [how the engagement works](/embeddings/custom-models) or [book a call](https://cal.com/amurzin/30min).

<Card title="API Reference" icon="code" href="/api-reference">
  Every endpoint, generated from the same OpenAPI 3.1 spec that production smoke tests verify.
</Card>