CyborgDB Docs

• Introduces a novel architecture to keep confidential inference data secure through zero-trust design.
• Keeps vector embeddings end-to-end encrypted throughout their lifecycle (including at search time).
• Exposes a familiar API, making it easy to integrate with existing AI workflows.
• Provides high-performance indexing and retrieval which can be GPU-accelerated with CUDA.
• Works with DBs such as Postgres and Redis, transforming traditional DBs into Confidential Vector DBs.

​

Choose Your Path

​

Documentation Structure