AI Research & Development
Building infrastructure for
intelligent systems
We build the layer that lets people own their AI agents' memory: end-to-end encrypted, on every machine they use, shared only with the people they choose.
Products
Cordelia
Pre-releaseYour agent's memory on every machine you use
AI coding agents keep memory, but it lives in one folder on one machine. Cordelia keeps it in step across your devices: encrypted on the device that wrote it, carried by relays that hold no keys, and matched by project rather than by path. Version 1 syncs Claude Code's memory.
Thesis
Agent memory is stuck where it was written
Agents now remember preferences, decisions and the reasons behind them. But that memory is filed per machine and per path, so a second machine, or a second clone of the same project, starts from nothing.
Memory must be encrypted end to end
Agent memory holds business decisions, personal preferences and proprietary knowledge. It deserves the protection people expect of messaging: encrypted on the device, readable only by the people it belongs to.
Infrastructure should hold no keys
The services that carry memory should not be able to read it. Cordelia's relays store only ciphertext, anyone can run one, and no single operator, including us, is necessary.
Small, and exactly as claimed
We ship a narrow product that works, publish what it does and does not protect against, and describe only what is built. Open source under AGPL-3.0.
About
Seed Drill Labs is a UK-based research and development studio. We build AI infrastructure products, starting with Cordelia, which keeps an AI agent's memory in step across the machines its owner uses, end-to-end encrypted.
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.