Tenure

Persistent, governable, scoped state for AI systems.

Architecture

Why Memory Is a State Management Problem, Not a Search Problem The dominant paradigm in AI memory treats persistence as a search index. That framing produces approximate retrieval, probabilistic isolation, and compounding noise. The alternative is simpler: treat memory as typed, scoped, versioned state.

Jun 2026 →
Why Precision Is All That Matters in AI Memory Retrieval precision is the difference between a memory system that works and one that only appears to. Why noise accumulation destroys value at scale, and why no downstream model can compensate for bad retrieval forever.

Jun 2026 →
Why Vector Search Became the Default for AI Memory (And Why That Was a Mistake) Vector search is the right tool for document retrieval and the wrong tool for memory. Here's how the field made that mistake, what it costs in practice, and what a precision-first design looks like instead.

Jun 2026 →
How AI Memory Systems Break at Scale The failure modes are structural, not incidental. At scale, similarity search accumulates noise faster than any model can filter it. Here is exactly what breaks, and how we designed around each failure.

Jun 2026 →
How the alias enrichment flywheel works BM25 retrieval is only as good as the alias set it searches against. The flywheel is how that set grows, passively, continuously, and without any effort from the user.

Jun 2026 →
Why MCP is the wrong abstraction for memory MCP treats memory as a tool call. Memory isn't something you invoke, it's something that should already be there. A technical argument for why the abstraction matters.

Jun 2026 →

Benchmarks

Teams

Tenure

GroundEval