Products Approach R&D Docs Work With Us Request Access
Applied AI lab · Raleigh, NC

We build AI products with a memory that lasts.

Era HQ is an applied AI lab with a research spine. We turn hard problems in machine cognition into products people can use — starting with CRYSTAL.

Any model
provider-agnostic
Open core
inspectable, self-hostable
In beta
live & hosted now
CRYSTAL Flagship · the memory

A memory that curates itself.

Most AI forgets everything the moment a conversation ends. CRYSTAL is the layer that remembers — a drop-in proxy between your application and any model. It captures what matters, organizes it into structured, cited knowledge, notices the gaps in its own understanding, and fills them. Point your existing client at CRYSTAL and your app gains a persistent, compounding knowledge base with no code changes.

Self-curating

It finds holes in its own knowledge, researches them, and validates what it learns before committing it. The memory improves on its own.

Model-agnostic

Anthropic, OpenAI, Vertex — any provider, any model. Bring your own key, or let us handle inference. One switch.

Grounded & cited

Answers carry citations back to the exact knowledge they came from, with a tier that separates verified from provisional.

Open core, cost-transparent

Every model call lands in a ledger you can see. The self-host image ships the whole product — ungated and inspectable.

The family

CRYSTAL is the foundation. Two products build on the same memory.

CRYSThe agent

An agent that works on top of CRYSTAL's memory — planning, researching, and spinning up its own sub-agents through a multi-tier cognition workflow with information barriers built in. Coding is one mode among many.

InspectorThe console

The window into everything — browse crystals, watch agents work, resolve knowledge conflicts, and track cost per customer and session. Hosted for the platform, self-hostable alongside your own deployment.

Our thesis

Memory is the missing primitive for AI.

Bigger context windows and better models don't solve forgetting — they postpone it. We build the layer that makes knowledge accumulate, and the research that makes it possible.

The compounding ratchet

Every miss is captured as a gap and surfaced in future queries, so the cost of not-knowing decays over time instead of resetting each session.

Accommodate, don't migrate

CRYSTAL adapts to your data as it is. No schema normalization demanded, no rigid ontology imposed — it meets your knowledge where it lives.

Self-curation over static stores

A memory that only stores is a database. One that reviews, deduplicates, resolves contradictions, and fills its own gaps is infrastructure.

Epistemics as a signal

Not all knowledge is equal. CRYSTAL tracks how vetted each fact is and tells the model, so retrieval can reason about confidence, not just relevance.

Information barriers by design

In the cognition workflow, workers never see the acceptance criteria and the validator never sees the plan — the system can't grade its own homework.

Open where it counts

The moat is the platform and the network effect, not withheld features. The engine is inspectable — trust is earned by showing the work.

Research & Development

The deep work behind the product.

A memory that curates itself raises real questions about cognition. We do the R&D underneath — and publish what we find.

Input Signals · Wave Physics
Perception
Layer
Consciousness
Layer
Self-Organizing Substrate
PQ-PMMA Photorefractive Physics
Pathway
Formation
Memory
Replay
Selective
Attention
Research Project

Self-Organizing Cognitive Simulation

An experimental project exploring emergent cognition without designed behavior — a simulation inspired by photorefractive physics where memory, attention, and pathway formation emerge from material constraints alone. No loss functions, no gradient descent. We verified measurable self-organization across multiple iterations, with a published writeup.

48.1%
Pathways carved
19%
Connections pruned
+26.6
Emergence score
PythonWave SimulationEmergent SystemsCognitive ArchitectureResearch Paper
Self-curating memoryRetrieval proxySemantic crystalsCognition engineAgent harnessCited knowledgeEpistemic tiersGap-fillCost ledgerAny modelOpen core Self-curating memoryRetrieval proxySemantic crystalsCognition engineAgent harnessCited knowledgeEpistemic tiersGap-fillCost ledgerAny modelOpen core
Work With Us

Building something ambitious with AI?

Beyond our products, we take on a small number of engagements each quarter. Industry-agnostic, outcome-focused — we bring the same research depth and production discipline to your hardest AI problem.

Start a conversation
How We Work

From research question to shipped product.

One spine — memory, cognition, agents — feeding many products over time. Each thing we ship makes the next one better.

01

Probe

We start from the hard question underneath — what would a memory that curates itself actually require?

02

Prototype

Research becomes a working system fast. We build to learn, and let the experiments tell us what's real.

03

Productize

What survives contact with reality gets hardened into infrastructure — tested, deployed, inspectable.

04

Compound

Every product feeds the next. Memory, cognition, agents — one spine, many products over time.

Let's build the next era of AI, together.

CRYSTAL is in closed beta. Tell us what you're building and we'll be in touch within 24 hours.

We typically respond within 24 hours.