Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

Public results and task definitions for FrontierHarness Eval

From thought to skill. From signal to structure.

Research and scraping agent skeleton: tool loop, loadable skills, fallback chains. No data included, configured via .env.