As personal AI agents like OpenClaw become more powerful by leveraging intimate user data, privacy has emerged as a fundamental bottleneck.
We’re releasing HEVEC, a vector database built on homomorphic encryption, enabling end-to-end privacy with real-time search at scale.
HEVEC is designed as a drop-in alternative to plaintext vector databases and supports real-time encrypted search at scale (1M vectors in ~187 ms).
Key points:
- A secure, drop-in alternative to plaintext vector databases
- End-to-end homomorphic encryption for both data and queries
- Real-time encrypted search at scale (1M vectors in 187 ms)
As personal AI agents become deeply personalized, data ownership must belong to users.
HEVEC enforces this through privacy-by-design architecture.
We’d appreciate feedback from the AI, systems, and privacy communities.
Is this closer to Fully Homomorphic Encryption (FHE) or partial?