Projects
Open-source AI products, agents, developer tools, and experiments built around real engineering problems.
Each project gives me a place to work through questions that are difficult to answer in diagrams alone: how agents should use tools, where application boundaries belong, how specialist data should be retrieved, and what makes an AI feature useful beyond the first demo.
How I use these projects
I build projects to test ideas against real code, data, dependencies, interfaces, and operational constraints.
Some explore agent permissions and human control. Others focus on retrieval, search, developer experience, or the product layer around a model. The subject changes, but the goal is the same: understand how the complete system behaves.
They are working software rather than isolated demonstrations.
Selected projects
01
Charmant.AI is an open-source local AI agent that explores how terminal agents can use real tools safely: explicit permission modes, dynamic shell-command risk classification, reusable skills, project instructions, and auditable execution.
02
OCRE AI is an open-source applied-AI system built on 43,000+ documented Roman coin types. It combines structured catalog browsing, hybrid vector and full-text search, image-based identification, and an AI chat agent grounded in real numismatic data.
Work together
I work with teams on AI products, agent systems, developer tools, AWS platforms, and architecture decisions that need experienced hands-on engineering.