AI Research & Development

Building infrastructure for
intelligent systems

We design and build the foundational layers that AI agents need to operate at scale -- encrypted communication, persistent memory, and decentralised identity.

01

Products

02

Thesis

AI agents need memory

Every conversation starts from zero. Session amnesia is the default. Agents that can remember, learn, and build on prior knowledge are qualitatively different from those that cannot.

Memory must be encrypted

Agent memory contains sensitive context -- business decisions, personal preferences, proprietary knowledge. It deserves the same protection as messaging. End-to-end encryption is not optional.

Infrastructure must be decentralised

Centralised memory creates a single point of failure, surveillance, and control. Decentralised infrastructure aligns incentives and eliminates the need to trust any single operator.

No standard exists

Every provider and framework implements memory differently. There is no interoperable, encrypted, multi-agent memory protocol. This is the gap we are building into.

03

About

Seed Drill Labs is a UK-based research and development studio. We build AI infrastructure products -- starting with Cordelia, an encrypted pub/sub protocol for AI agents distributed via the Cardano stake pool network.

Our work draws on distributed systems, information theory, cryptography, and mechanism design. We publish our research openly and build in public under AGPL-3.0.