> ## Documentation Index > Fetch the complete documentation index at: https://docs.cyborg.co/llms.txt > Use this file to discover all available pages before exploring further. # CyborgDB Docs
CyborgDB
The vector database
that never sees your data.
Similarity search directly on encrypted embeddings — self-hosted in your VPC or on-prem, with no decryption, no TEE exit, and no plaintext in memory.
**CyborgDB** is an encrypted vector database — similarity search directly on encrypted embeddings, with no decryption, no TEE exit, and no plaintext in memory. It runs as a proxy layer over Postgres or Redis, exposes a familiar API that slots into existing AI pipelines, and can be [GPU-accelerated with NVIDIA cuVS](https://developer.nvidia.com/blog/bringing-confidentiality-to-vector-search-with-cyborg-and-nvidia-cuvs/).
\<5ms
p95 encrypted query latency
100M+
vectors per index
Zero
data leaves your boundary
### Choose Your Path Understand the architecture and principles behind encrypted vector search Get hands-on with CyborgDB in minutes using our quickstart guide Discover embedded libraries, managed service, and custom deployment options ### Documentation Structure Core concepts, deployment models, and getting started guides CyborgDB self-hosted with REST API and client SDKs Self-hosted, embedded deployments with Python and C++ bindings LangChain and other framework integrations for seamless adoption Navigation tips and conventions used throughout these docs