Autonomous agents, local LLM infrastructure, research tools. Built to work. Not to demo well and break on real tasks. Every project here is something I needed and nobody had built.
Every autonomous web agent I tried worked on demo sites and collapsed on anything real: Cloudflare, dynamic JS, anti-bot measures, login walls. So I built one that doesn't.
ReAct loop. A DOM walker that extracts semantic structure the LLM can actually reason about instead of drowning in raw HTML. Stealth Playwright. 2,904 tests because autonomous agents fail silently and I needed to trust it.
52GB cross-cultural mythology and history corpus. 84,000+ files across Norse, Greek, Egyptian, Minoan, Sanskrit, Semitic, and Chinese traditions. Built as the training substrate for models that need real historical depth.
View project →Autonomous agent loop engine. Runs Claude Code sessions iteratively against real completion criteria: tests, file checks, grep assertions. Runs until done or escalates. Solves the "always in beta" problem.
View project →I build autonomous agents, LLM pipelines, and research infrastructure. If you're working on something that needs to run locally, handle adversarial web environments, or coordinate multiple AI systems without cloud dependency. That's the area.