> ## 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.

# ConareDB

> ConareDB is an object-storage-native database with hybrid vector, BM25 keyword, property, and graph search across isolated namespaces.

<Note>ConareDB standalone is in **controlled beta**. The engine backs Conare AI Memory in production; direct database access is being opened to beta customers. Live status: [conare.betteruptime.com](https://conare.betteruptime.com/).</Note>

ConareDB is an object-storage-native search engine: durable local WAL plus an object-store mirror, hybrid retrieval (vector ANN + BM25 keyword + attribute ranking), typed filters, and binary bulk ingest — organized into fully isolated namespaces.

<Card title="ConareDB Console" icon="database" href="https://db.conare.ai">
  Sign in with your `cdb_` key to browse namespaces, usage, and metrics.
</Card>

## Two ways to buy the same engine

|                                          | You bring                 | Conare does                                                                    |
| ---------------------------------------- | ------------------------- | ------------------------------------------------------------------------------ |
| **Standalone ConareDB** (this section)   | Your own vectors and data | Stores, indexes, searches. Raw database API at `db.conare.ai`.                 |
| **[Conare AI Memory](/memory/overview)** | Raw text + an `endUserId` | Chunks, embeds, indexes, retrieves, synthesizes — the complete memory product. |

Standalone ConareDB never turns text into embeddings — pair it with the [Embeddings API](/embeddings/overview) if you want vectors from the same model family that powers Conare retrieval, or bring any model you like.

## What you get

* **Isolated namespaces** — each a complete store with its own WAL, persister, and object-store mirror. Created on first write; permanently deleted with a durable anti-restore tombstone.
* **Hybrid search** — vector, BM25 keyword, and chronological branches in one request, with a typed filter DSL. Vector scores are always exact: the ANN path reranks candidates against full-precision vectors before returning.
* **Scoped keys** — `cdb_...` bearers scoped to exact or prefix namespace patterns, with independent `read` / `write` / `delete` permissions, optional per-key rate limits and expiry. Secrets are shown once and stored only as SHA-256 digests.
* **Binary bulk ingest** — one binary fp16 frame per request with restart-safe conditional receipts, built for seeding tens of millions of rows.
* **Deterministic results** — for a fixed index state, identical queries return byte-identical hit lists at any concurrency. Continuous recall sampling checks ANN answers against brute-force ground truth in the background.

## Endpoints at a glance

| Method + path                           | Purpose                                          |
| --------------------------------------- | ------------------------------------------------ |
| `POST /v1/namespaces/{ns}/query`        | Writes and graph/property queries                |
| `POST /v1/namespaces/{ns}/search`       | Hybrid search (vector / keyword / chronological) |
| `POST /v1/namespaces/{ns}/bulk-vectors` | Binary fp16 bulk ingest                          |
| `GET /v1/namespaces/{ns}/metadata`      | Row count, size, generation, index status        |
| `GET /v1/namespaces/{ns}/metrics`       | That namespace's runtime metrics                 |
| `DELETE /v1/namespaces/{ns}`            | Permanent physical deletion                      |
| `GET /health`, `GET /ready`             | Liveness / safe-to-serve (credential-free)       |

Start with the [quickstart](/db/quickstart), or jump to [search](/db/search), [writes & ingest](/db/writes), [namespaces & keys](/db/namespaces), or [migrating from Turbopuffer](/db/migrate-turbopuffer).