Agentic OS

TL;DR: An agentic personal operating system built to automate high-leverage workflows across Claude Code, Codex, Pi, OpenClaw, and other coding agents/runtime platforms.

Quick Start

1. Clone this repo

2. Run setup

3. Start using
   This automates high-leverage execution end-to-end: it converts raw backlog into prioritized, goal-aligned, verification-enforced action plans.

Quick Links

Build Your Personal OS · Workflows · Canonical Skills · Evals · Tutorials (index)

Architecture

Agent Compatibility

Personal OS is designed to work with Claude Code, Codex, Pi, OpenClaw, and similar coding agent runtimes.

- Shared behavior: AGENTS.md
- Claude wrapper: CLAUDE.md
- Codex wrapper: CODEX.md
- Pi wrapper: PI.md
- OpenClaw wrapper: OPENCLAW.md
- Canonical runtime skills: .agents/skills/*/SKILL.md
- Skills in this repo follow the Agent Skills open standard.
- This repo uses skills with progressive disclosure to manage context efficiently: agents begin with each skill's metadata (name, description, file path, plus agents/openai.yaml), and load full SKILL.md instructions only when a skill is selected. Canonical skills live in .agents/skills/, with bridge paths for Claude, Pi, and OpenClaw.
- Optional subagents are supported when the runtime provides agent delegation features (not required for core repo operation).
- Claude bridge path: .claude/skills -> ../.agents/skills (symlink)
- Pi bridge: configure Pi to point to this repo and use .agents/skills/ as its skill source
- OpenClaw bridge: create skills -> .agents/skills symlink (or load .agents/skills via OpenClaw config)

Bridge bootstrap (run once from repo root):

For Codex/OpenAI-style routing metadata, this repo includes:
- .agents/skills//agents/openai.yaml
  (Claude, Pi, and OpenClaw primarily use SKILL.md and do…