What I care about
- Agent orchestration with durable state
- Local AI infrastructure and worker safety
- Evidence-grounded automation
- Queue systems that fail loudly instead of hanging silently
- Human-visible provenance for generated artifacts
Agentic research infrastructure · local AI systems · evidence workflows
I build control planes for AI-assisted research systems.
My work focuses on queue safety, worker orchestration, evidence capture, provenance, and publication-style packaging for AI-generated research artifacts.
120AI-generated research artifacts
2public launch repos
0human authorship claims on generated papers
Featured project
Enoch: Agentic Research Control Plane
Enoch is an open-source control plane for running bounded AI research workflows end to end. It coordinates idea intake, queue state, pause and maintenance controls, worker preflight, single-lane safety, evidence synchronization, dashboard status, alerting, and publication-style artifact packaging.
The project was built around LangGraph-era control-plane boundaries and operated with Codex plus oh-my-codex/OMX-assisted development workflows.
Architecture
From idea queue to auditable artifact.
Enoch is framed as infrastructure first: state, safety, evidence, and review boundaries before generated output.
Current stack
- Python, FastAPI, SQLite-backed control state
- LangGraph-era orchestration boundaries
- GitHub Actions, branch protections, release packaging
- Wake-gated local worker execution
- Codex-assisted development and oh-my-codex/OMX operations
Provenance matters
The generated papers in the Enoch corpus are released as AI-generated research artifacts. I am not claiming human authorship of the paper prose, arguments, or generated results. The release is about the surrounding system: control-plane design, workflow reliability, evidence capture, provenance metadata, and public packaging.