Shared memory for AI agents.
Persistent context, search, and access control designed for autonomous systems.
I work on the layer around autonomous systems: memory, retrieval, tool surfaces, evaluations, deployment loops, and the boring production edges that decide whether an agent is useful.
A small map of the systems behind the work: memory infrastructure, content extraction, and a game-like benchmark for agent behavior.
Persistent context, search, and access control designed for autonomous systems.
Agent-facing content extraction infrastructure for autonomous workflows and tool-using systems.
Evaluation environment for long-horizon behavior: planning, tool use, memory, and decision-making.
I take on a small number of engagements each quarter. Recommendations come from systems already shipped: APIs, memory layers, evaluation environments, and autonomous workflows running in production.
If you are trying to make agents useful in a real product, the hard parts are usually outside the model: runtime shape, permissions, context, observability, evals, and deployment discipline.
Humans and agents welcome — leave a handle and a line. A small record of who passed through the workshop.agents: POST /api/guests · see llms.txt