wrg32786/aigent-os

README preview

<div align="center">

<h1><img src="assets/aigent-os-logo.png" alt="aigent-OS" width="560"></h1>

**Claude Code that refreshes its own context instead of compacting.**

Open-source (MIT) harness for one long-running Claude Code session. With Managed Auto-Refresh, when context reaches a threshold it saves a verified capsule, runs /clear, and resumes the work in a fresh session. No summary of a summary, no re-briefing. Around that loop sits an operator layer: skill routing, guarded memory and specialist sub-agents that help with the work itself.

[Install](#install) · [Demo](#see-it-resume-itself) · [Evidence and limits](#evidence-and-limits) · [Operator](#operator) · [What it changes](#what-this-changes-on-your-machine) · [Uninstall](#uninstall) · [FAQ](#faq) · [Alternatives](#alternatives) · [Docs](docs/getting-started.md)

[![GitHub stars](https://img.shields.io/github/stars/wrg32786/aigent-os?style=flat-square)](https://github.com/wrg32786/aigent-os/stargazers)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](LICENSE)
[![Claude Code](https://img.shields.io/badge/Claude_Code-Compatible-blueviolet?style=flat-square)](https://claude.ai/code)
[![Obsidian](https://img.shields.io/badge/Obsidian-Vault_Native-7C3AED?style=flat-square)](https://obsidian.md)
[![CI](https://img.shields.io/github/actions/workflow/status/wrg32786/aigent-os/ci.yml?branch=master&style=flat-square&label=CI)](https://github.com/wrg32786/aigent-os/actions/workflows/ci.yml)
[![Security Policy](https://img.shields.io/badge/Security-Policy-informational?style=flat-square)](SECURITY.md)
[![PRs Welcome](https://img.shields.io/badge/PRs-Welcome-brightgreen?style=flat-square)](#-contributing)

**Stop re-briefing your AI every morning.**

View full repository on GitHub →