Skip to content

Self-hosted control plane for AI autonomous agents. Run Claude Code & Open Code in isolated linux workspaces with a git-based Library configuration and secret management.

Notifications You must be signed in to change notification settings

Th0rgal/openagent

Repository files navigation

Open Agent

Open Agent

Self-hosted control plane for AI autonomous agents
Isolated Linux workspaces and git-backed Library configuration

Vision · Features · Ecosystem · Screenshots · Getting Started


Open Agent Dashboard

Ready to deploy? Ask your local AI agent to check out INSTALL.md it'll guide you through everything.


Vision

What if you could:

Hand off entire dev cycles. Point an agent at a GitHub issue, let it write code, test by launching a Minecraft server, 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

  • Mission Control: Start, stop, and monitor agents remotely with real-time streaming
  • Isolated Workspaces: Containerized Linux environments (systemd-nspawn) with per-mission directories
  • Git-backed Library: Skills, tools, rules, agents, and MCPs versioned in a single repo
  • MCP Registry: Global MCP servers running on the host, available to all workspaces
  • Multi-platform: Web dashboard (Next.js) and iOS app (SwiftUI) with Picture-in-Picture

Ecosystem

Open Agent is a control plane for OpenCode, the open-source AI coding agent. It delegates all model inference and autonomous execution to OpenCode while handling orchestration, workspace isolation, and configuration management.

Works great with oh-my-opencode for enhanced agent capabilities and prebuilt skill packs.


Screenshots

Dashboard Overview

Real-time monitoring with CPU, memory, network graphs and mission timeline


Library Skills Editor

Git-backed Library with skills, commands, rules, and inline editing


MCP Servers

MCP server management with runtime status and Library integration


Getting Started

Production Setup (the easy way)

  1. Get a dedicated server (e.g., Hetzner, Ubuntu 24.04)
  2. Point a domain to your server IP
  3. Clone this repo locally
  4. Ask Claude to set it up:

    "Please deploy Open Agent on my server at <IP> with domain agent.example.com"

That's it. Claude will handle nginx, SSL, systemd services, and everything else.

If you feel smarter than the AI, check out INSTALL.md.

Local Development

Backend:

export OPENCODE_BASE_URL="http://127.0.0.1:4096"
cargo run

Dashboard:

cd dashboard
bun install
bun dev

Open http://localhost:3001


Status

Work in Progress — This project is under active development. Contributions and feedback welcome.

License

MIT

About

Self-hosted control plane for AI autonomous agents. Run Claude Code & Open Code in isolated linux workspaces with a git-based Library configuration and secret management.

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published