English

Opal: Private Memory for Personal AI

Cryptography and Security 2026-04-06 v1 Artificial Intelligence

Abstract

Personal AI systems increasingly retain long-term memory of user activity, including documents, emails, messages, meetings, and ambient recordings. Trusted hardware can keep this data private, but struggles to scale with a growing datastore. This pushes the data to external storage, which exposes retrieval access patterns that leak private information to the application provider. Oblivious RAM (ORAM) is a cryptographic primitive that can hide these patterns, but it requires a fixed access budget, precluding the query-dependent traversals that agentic memory systems rely on for accuracy. We present Opal, a private memory system for personal AI. Our key insight is to decouple all data-dependent reasoning from the bulk of personal data, confining it to the trusted enclave. Untrusted disk then sees only fixed, oblivious memory accesses. This enclave-resident component uses a lightweight knowledge graph to capture personal context that semantic search alone misses and handles continuous ingestion by piggybacking reindexing and capacity management on every ORAM access. Evaluated on a comprehensive synthetic personal-data pipeline driven by stochastic communication models, Opal improves retrieval accuracy by 13 percentage points over semantic search and achieves 29x higher throughput with 15x lower infrastructure cost than a secure baseline. Opal is under consideration for deployment to millions of users at a major AI provider.

Keywords

Cite

@article{arxiv.2604.02522,
  title  = {Opal: Private Memory for Personal AI},
  author = {Darya Kaviani and Alp Eren Ozdarendeli and Jinhao Zhu and Yu Ding and Raluca Ada Popa},
  journal= {arXiv preprint arXiv:2604.02522},
  year   = {2026}
}
R2 v1 2026-07-01T11:51:57.910Z