
Independent exploration
ChronoBench
LLM benchmark measuring how far frontier models progress through Chrono Trigger using an autonomous, vision-based game agent. Live leaderboard with per-run telemetry, checkpoints, and cost tracking.
The work / An ongoing collection
Independent experiments and professional systems. Different environments, the same curiosity about how things work.
13 projects

Independent exploration
LLM benchmark measuring how far frontier models progress through Chrono Trigger using an autonomous, vision-based game agent. Live leaderboard with per-run telemetry, checkpoints, and cost tracking.
Round 1 map
Independent exploration
LLM commanders draft tank squads, fight multi-round domination matches, and evolve between rounds — self-chosen identities, coach-driven edits, and opponent intel. ELO leaderboard and full match telemetry.
Independent exploration
Python library for threaded "director" layers that enqueue LLM tool actions; host runs validation on the sim thread. No game engine dependency — tool calling, memory, persona markdown, multi-layer architecture.
Independent exploration
Framework for building and testing AI agents in game environments. Supports multi-agent orchestration and evaluation harnesses.
Independent exploration
Classic control and reinforcement learning experiments. Benchmarking agent architectures against standard control problems.
Independent exploration
AI-driven game project exploring procedural narrative generation and world-building with LLM-powered systems.
Independent exploration
Game project built with AI agent integration — combining classic gameplay mechanics with modern AI techniques.
Independent exploration
Research workspace for game AI experimentation — prototyping agent behaviors, decision systems, and simulation architectures.
Professional / FranData
Multi-stage AI pipeline that converts dense franchise disclosure documents into structured, machine-readable data at scale.
Professional / FranData
Research tooling that surfaces findings across a large disclosure-document corpus, pairing retrieval with an AI validation layer and analyst-ready outputs.
Professional / FranData
Automated AI extraction and classification of company, franchisee, and technology signals from documents and public sources, feeding the franchise intelligence platform.
Professional / FranData
Automation that ingests analyst-completed research and proprietary scoring data into the central data platform, validating everything on the way in.
Professional / FranData
Internal query, upload, and operations utilities supporting the franchise intelligence data platform.