research

Our active research
vectors.

We design, analyze, and build security layers for autonomous agents. Our research targets first-principles vulnerabilities in tool execution, retrieval, and reasoning loops.

// In Progress

Project Black Monolith

A unified agentic AI security middleware system. Monitoring, filtering, and grounding agent tool executions in real-time.

Examine Details
Emergent Vectors

Future Directions

// Exploratory

Project Hollow Choir

Coordination without instruction.

Multi-agent systems research studying how LLM agents develop emergent roles and division of labor without being explicitly assigned them.

// Exploratory

Project Amber Room

Memory that doesn't reset.

Long-context memory architecture research aimed at making an agent's memory feel continuous rather than retrieved.

// Exploratory

Project Fathom

Looking inside small models.

Interpretability research focused on fine-tuned small language models, examining what actually changes internally when a base model is adapted via LoRA/QLoRA.

// Exploratory

Project Undertow

How models get to the answer.

Reasoning trace analysis studying the process models use to arrive at outputs, not just whether the final answer is correct.

// Exploratory

Project Halflight

What synthetic data does to a model over time.

Studies the compounding effects of synthetic data on model behavior across successive fine-tuning rounds.

// Exploratory

Project Marrow

How much intelligence survives compression.

Efficiency research measuring how much of a model's capability survives quantization, pruning, and distillation.

// Exploratory

Project Nocturne

Intelligence that doesn't need the cloud.

On-device and local inference research studying latency, resource tradeoffs, and behavior consistency when running LLMs locally.