projects
Interested in building at the infrastructure level
A demo for AI agents in aerospace operations. I simulated a rocket launch in Kerbal Space Program and piped its live flight data through kRPC into Foundry, where the vehicle is modeled as ontology objects. An agent named PROP watches the engines like a propulsion flight controller would, catches engine-out failures, and proposes a recovery command. The flight dynamics math for thrust-to-weight, delta-v, and orbit reachability is computed deterministically, so the agent decides what's wrong while the physics stays exact. A human approves every command before it reaches the vehicle. Point the same pipeline at a real telemetry feed and nothing downstream changes.
Like a producer reusing loops they have made before, mainstacks lets you extract patterns from past projects and drop them into new ones. Your agents get context on how you build things, so they stop guessing and start building the way you would
Wrap your LLM client with one line of Python and every call, token, cost, and source location shows up in your dashboard in real time. Built to make agentic AI costs visible per agent, per function, and per line of code before they surprise you.
Co-authored a paper accepted to ICML 2026 AI for Science Workshop: developed a multi-agent system (MAS) that orchestrates expert decision trees with Vision-Language Models (VLMs) for automated bias labeling in forestry remote sensing, outperforming supervised ML baselines while preserving interpretability
Automates medical referral intake, OCR to structured extraction to EMR auto-fill. Taught me more about customer discovery and what people actually pay for in the context of building a startup.
My Neovim configuration. Clean, fast setup focused on development with LSP support, fuzzy finding, and Treesitter. Uses Packer.
One of my first projects, built with some friends at the first AI Hackathon from UC Berkeley. Analyzes news article bias with GPT-4 scoring and Hume AI sentiment, then rewrites the piece from three perspectives.
