https://github.com/th0rgal/sandboxed.sh
Self-hosted orchestrator for AI autonomous agents. Run Claude Code & Open Code in isolated linux workspaces. Manage your skills, configs and encrypted secrets with a git repo.
https://github.com/th0rgal/sandboxed.sh
ai-agents autonomous-agents claude claude-code coding-assistant containerization developer-tools llm mcp opencode orchestration self-hosted workspace-isoaltion
Last synced: about 19 hours ago
JSON representation
Self-hosted orchestrator for AI autonomous agents. Run Claude Code & Open Code in isolated linux workspaces. Manage your skills, configs and encrypted secrets with a git repo.
- Host: GitHub
- URL: https://github.com/th0rgal/sandboxed.sh
- Owner: Th0rgal
- Created: 2025-12-15T10:15:26.000Z (2 months ago)
- Default Branch: master
- Last Pushed: 2026-02-15T00:12:18.000Z (1 day ago)
- Last Synced: 2026-02-15T01:34:13.370Z (1 day ago)
- Topics: ai-agents, autonomous-agents, claude, claude-code, coding-assistant, containerization, developer-tools, llm, mcp, opencode, orchestration, self-hosted, workspace-isoaltion
- Language: Rust
- Homepage: https://sandboxed.sh
- Size: 183 MB
- Stars: 222
- Watchers: 3
- Forks: 22
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- Agents: agents.md
Awesome Lists containing this project
README
sandboxed.sh
Self-hosted cloud orchestrator for AI coding agents
Isolated Linux workspaces with Claude Code, OpenCode & Amp runtimes
Formerly known as "Sandboxed.sh"
Website ·
Discord ·
Vision ·
Features ·
Ecosystem ·
Screenshots ·
Getting Started
Ready to deploy? Jump to the installation comparison, or go straight to the Docker guide / native guide.
---
## 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, or Amp agents in the same
infrastructure
- **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 (optional)**: Extra tool servers (desktop/playwright/etc.) when
needed
- **Multi-platform**: Web dashboard (Next.js) and iOS app (SwiftUI) with
Picture-in-Picture
---
## Ecosystem
sandboxed.sh orchestrates multiple AI coding agent runtimes:
- **[Claude Code](https://docs.anthropic.com/en/docs/claude-code)**: Anthropic's
official coding agent with native skills support (`.claude/skills/`)
- **[OpenCode](https://github.com/anomalyco/opencode)**: Open-source alternative
via [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode)
- **[Amp](https://ampcode.com)**: Sourcegraph's frontier coding agent with
multi-model support
Each runtime executes inside isolated workspaces, so bash commands and file
operations are scoped correctly. sandboxed.sh handles orchestration, workspace
isolation, and Library-based configuration management.
---
## Screenshots
Real-time monitoring with CPU, memory, network graphs and mission timeline
Git-backed Library with skills, commands, rules, and inline editing
MCP server management with runtime status and Library integration
---
## Getting Started
### Choose your installation method
| | Docker (recommended) | Native (bare metal) |
| ------------------------ | ---------------------------------------------- | --------------------------------------------------- |
| **Best for** | Getting started, macOS users, quick deployment | Production servers, maximum performance |
| **Platform** | Any OS with Docker | Ubuntu 24.04 LTS |
| **Setup time** | ~5 minutes | ~30 minutes |
| **Container workspaces** | Yes (with `privileged: true`) | Yes (native systemd-nspawn) |
| **Desktop automation** | Yes (headless Xvfb inside Docker) | Yes (native X11 or Xvfb) |
| **Performance** | Good (slight overhead on macOS) | Best (native Linux) |
| **Updates** | `docker compose pull` / rebuild | Git pull + cargo build, or one-click from dashboard |
### Docker (recommended for most users)
```bash
git clone https://github.com/Th0rgal/sandboxed.sh.git
cd sandboxed.sh
cp .env.example .env
# Edit .env with your settings
docker compose up -d
```
Open `http://localhost:3000` — that's it.
For container workspace isolation (recommended), uncomment `privileged: true` in
`docker-compose.yml`.
→ **[Full Docker setup guide](docs/install-docker.md)**
### Native (bare metal)
For production servers running Ubuntu 24.04 with maximum performance and native
systemd-nspawn isolation.
→ **[Full native installation guide](docs/install-native.md)**
### First-time setup
After installation, follow the **[Getting Started Guide](docs/getting-started.md)** for:
- Configuring your backend connection
- Setting up your library repository
- Exploring skills and tools
- Creating your first mission
### AI-assisted setup
Point your coding agent at the installation guide and let it handle the
deployment:
> "Deploy Sandboxed.sh on my server at `1.2.3.4` with domain `agent.example.com`"
---
## Documentation
### User Guides
- **[Getting Started](docs/getting-started.md)** - First-time setup and usage
- **[Docker Installation](docs/install-docker.md)** - Recommended installation method
- **[Native Installation](docs/install-native.md)** - Bare metal Ubuntu setup
### Architecture & APIs
- **[Harness System](docs/HARNESS_SYSTEM.md)** - Backend integration architecture
- **[Workspaces](docs/WORKSPACES.md)** - Isolated execution environments
- **[Mission API](docs/MISSION_API.md)** - Mission lifecycle and control
- **[Workspace API](docs/WORKSPACE_API.md)** - Workspace management endpoints
- **[Backend API](docs/BACKEND_API.md)** - Backend configuration
### Setup Guides
- **[Desktop Setup](docs/DESKTOP_SETUP.md)** - X11/Xvfb configuration for GUI automation
- **[Amp Proxy Setup](docs/AMP_PROXY_SETUP.md)** - Amp backend proxy configuration
### Reference
- **[agents.md](agents.md)** - Agent configuration and harness details
- **[Persistent Sessions Design](PERSISTENT_SESSIONS_DESIGN.md)** - Claude CLI session management
- **[Debugging Guide](DEBUGGING.md)** - Troubleshooting and debug workflows
- **[Docker Analysis](docs/DOCKER_ANALYSIS.md)** - Docker setup deep dive
---
## Development
### Setup git hooks
Enable pre-push formatting checks to catch CI failures locally:
```bash
git config core.hooksPath .githooks
```
This runs `cargo fmt --check` before each push. If formatting issues are found,
run `cargo fmt --all` to fix them.
---
## Status
**Work in Progress** — This project is under active development. Contributions
and feedback welcome.
## License
MIT