Projects
Systems shipped, or close to it.
A small portfolio of projects we are actively developing or researching. Each one is designed to be the kind of system we would defend in front of a regulated industry.
Enterprise Legal AI
In DevelopmentRavin
A contract intelligence platform that turns dense legal corpora into verifiable, citation-grounded answers.
- Next.js
- TypeScript
- Python
- pgvector
AI Security Operations Center
In ResearchAO-SOC
An autonomous SOC analyst that triages, investigates, and documents alerts while a human stays in the loop.
- Python
- FastAPI
- PostgreSQL
- OpenTelemetry
Passive Vortex Air Purification Tower
In ResearchAir to Live
A passive, energy-minimal tower concept that purifies city-scale volumes of air using natural-draft aerodynamics instead of mechanical fans.
- Computational Fluid Dynamics
- Natural-Draft Aerodynamics
- Electrostatic Precipitation
- Structural Engineering
Automated Digital Forensics
In DevelopmentForensic Intelligence Engine
An evidence analysis system that ingests large heterogeneous corpora and produces structured forensic intelligence reports with minimal manual review.
- Python
- FastAPI
- Computer Vision
- OCR
On-Premise Legal AI Ecosystem
In DevelopmentEnterprise Domain-Adaptive Legal AI Platform
A fully on-premise platform for understanding, generating, and comparing legal documents — domain-independent at the core, with swappable knowledge packs for regulated industries.
- Python
- FastAPI
- PostgreSQL
- pgvector
Post-Exhaustion Password Search
In ResearchChaosWalker
A post-exhaustion architecture that explores massive password spaces through pseudorandom, non-repeating sampling rather than linear brute force.
- C
- Feistel Networks
- Bloom Filters
- Hashcat
AI-Driven Crypto Trading
In DevelopmentCryptoTrade
A local-first, AI-driven crypto trading system with deterministic governance and paper trading capabilities.
- Python
- Ollama
- LLM Agents
- ccxt
Synthetic Community Knowledge Graphs
In ResearchKinGraph
A toolkit for generating synthetic human community datasets with rich, temporally-consistent knowledge graph structures for graph ML and database pipelines.
- Python
- Ollama
- Neo4j
- Pandas
Al Brooks Price Action Trading Engine
In DevelopmentPAI-Lab
An adaptive, multi-timeframe trading engine that translates Al Brooks' discretionary price-action methodology into quantified, risk-gated execution logic.
- Python
- Pandas
- Logistic Regression
- Monte Carlo Simulation
Engagements
Have a problem worth our calendar?
We take on a small number of engagements at a time. Each starts with a conversation, not a contract.