Th0rgal/openagent

Registry

Summary

OpenAgent is a self-hosted orchestrator for AI autonomous agents, enabling the execution of Claude Code and Open Code within isolated Linux workspaces. It provides centralized management of skills, configurations, and encrypted secrets through a Git repository.

Key features

• Self-hosted orchestrator for AI autonomous agents
• Isolated Linux workspace execution for Claude Code & Open Code
• Centralized management via Git repository
• Skill, configuration, and encrypted secret management
• Built with Rust for performance and reliability

Use cases

• Running AI coding assistants in secure, isolated environments
• Managing multiple AI agent configurations and skills
• Self-hosting autonomous agent workflows for development
• Secure secret management for AI agent operations
• Orchestrating Claude Code and Open Code execution

README excerpt

<p align="center"> <img src="dashboard/public/favicon.svg" width="120" alt="sandboxed.sh" /> </p> <h1 align="center">sandboxed.sh</h1> <p align="center"> <strong>Self-hosted cloud orchestrator for AI coding agents</strong><br/> Isolated Linux workspaces with Claude Code, OpenCode, Codex, Gemini, and Grok runtimes </p> <p align="center"> <em>Formerly known as Open Agent</em> </p> <p align="center"> <a href="https://sandboxed.sh">Website</a> · <a href="https://relens.ai/community">Discord</a> · <a href="#vision">Vision</a> · <a href="#features">Features</a> · <a href="#ecosystem">Ecosystem</a> · <a href="#screenshots">Screenshots</a> · <a href="#getting-started">Getting Started</a> </p> <br/> <p align="center"> <img src="screenshots/hero.webp" alt="sandboxed.sh Dashboard" width="100%" /> </p> <p align="center"> <strong>Ready to deploy?</strong> Jump to the <a href="#choose-your-installation-method">installation comparison</a>, or go straight to the <a href="docs/install-docker.md">Docker guide</a> / <a href="docs/install-native.md">native guide</a>. </p> --- ## Vision What if you could: **Hand off entire dev cycles.** Point an agent at a GitHub issue, let it write code, test by launching desktop applications, and open a PR when tests pass. You review the diff, not the process. **Run multi-day operations unattended.** Give an agent SSH access to your home GPU through a VPN. It reads Nvidia docs, sets up training, fine-tunes models while you sleep. **Keep sensitive data local.** Analyze your sequenced DNA against scientific literature. Local inference, isolated containers, nothing leaves your machines. --- ## Features - **Multi-Runtime Support**: Run Claude Code, OpenCode, Codex, Gemini, and Grok agents in the same infrastructure

Topics