< What I Do />
Focused engineering around one idea: systems that are predictable, observable, and hard to misconfigure.
Configuration & Validation
Schema-driven layers that catch bad config before it runs.
AI Workflow Reliability
Deterministic, observable LLM pipelines that don't silently break.
Developer Tooling
CLIs and internal tools that reduce friction for engineers.
Scientific Software
Python tooling & configuration systems for simulation and research.
Security & Forensics Tooling
Evidence-traceable incident reconstruction that never guesses.
Systems Architecture
Building maintainable software foundations that scale with teams, products, and research.
🔶 LLM Workflow Router
A deterministic engine that stops AI workflows from silently breaking in production — YAML-driven, cycle-safe, with built-in tracing and an OpenAI Agents SDK integration. Free MIT core, with optional commercial security licensing.
pip install llm-workflow-router🔶 Nimbus Vestige
A forensic reconstruction engine for cloud & identity incidents — rebuilds the most likely attack path from fragmented telemetry, with calibrated, evidence-traceable confidence. Fully self-hosted, so your incident data never leaves your estate. Free open core, with a one-time perpetual commercial license.
git clone https://gitlab.com/dobybaxter127/nimbus-vestige< Professional Endorsement />
"Doby has demonstrated strong technical skills, thoughtful system-level thinking, and a clear focus on usability and maintainability. He played a key role in developing innovative tooling driven by real user and community needs. He is proactive, reliable, and communicates clearly, particularly when working on complex or cross-cutting features."
