We are building in the open. This page shares the thinking behind what we are building, the principles we hold ourselves to, and the ideas we are working through as we go.
Current AI tools forget everything when the session ends. This piece makes the case for why that is not a minor inconvenience but a fundamental architectural mismatch — and what persistent agents change.
A technical look at how we are designing the memory substrate — queryable, auditable, version-controlled, and built to support agents that reason continuously without ever starting over.
A single agent agreeing with itself is not reasoning — it is confirmation. This piece examines why structured disagreement between agents produces better answers, and how we have made it a first-class feature rather than a side effect.
The context window is not memory. This piece sets out what genuine AI employees require — continuity, compounding institutional knowledge, and the ability to get meaningfully better over months, not just better at the current prompt.
Humans remain the principals.
Every output from every agent is reviewable, citable, and overridable by the humans using the platform. We are not building systems that replace human judgment. We are building systems that make it faster, better informed, and more powerful.
Every claim must survive challenge.
Our agents are designed to disagree with each other. A claim that cannot be critiqued is a claim we do not trust. Structured disagreement is not a bug in our system — it is the core feature.
Memory is never erased.
The memory substrate does not reset. Ever. This is a design commitment, not a technical constraint. We believe continuity is the most important property an AI employee can have.
We publish what we learn.
We will share our architecture, our failures, and our thinking openly as we build. We are not building in secret. The more people who can examine what we are doing and challenge it, the stronger the result.
We are looking for engineers and builders who want to work on one of the most interesting problems in AI right now. We are early, which means what you build here will actually matter.
We are also looking for companies who want to be among the first to put persistent AI agents to work — and help shape what the platform becomes.
Project Laplace is an early-stage startup. The platform is in active development.