1. Conduid
  2. Developer Tools
  3. Sandboxed.sh
MCP server · Developer Tools

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.

72Good

Scored 3 hours ago · breakdown

About Sandboxed.sh

Sandboxed.sh is an MCP server published by Th0rgal in the Developer Tools category: 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. It has been installed 0 times through Conduid.

The repository has 261 stars and 30 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx sandboxed-sh

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Sandboxed.sh

Powered by Claude · Grounded in docs

I know everything about Sandboxed.sh. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v0.12.0v0.12.0 — Grok Build, Needs You, iOS UX · 16 May 2026v0.12.0 — Grok Build, Needs You, transcript streaming, iOS UX Grok Build — first-class backend Full xAI OAuth flow (device-auth), `~/.grok/auth.json` mirrored per mission workspace, container-aware `--cwd` translation, `grok-build` default…
v0.11.5v0.11.5 - Native Harness Loops & iOS Network Resilience · 14 May 2026Bundles PR #432 — clean reimplementation of the still-unique work from the abandoned #430 (Codex goal mode + iOS network resilience WIP). Features Native harness loops as Automation rows Claudecode and codex `/goal` continuation loops now…
v0.11.1v0.11.1 - Mission Workbench BugBot Fixes · 3 May 2026v0.11.1 highlights Patch release for the Mission Workbench and Needs You inbox rollout. Changes Aligns Mission Workbench running-state rendering with the header's effective running-state logic instead of treating any `RunningMissionInfo`…
v0.11.0v0.11.0 - Mission Workbench & Goal Mode · 3 May 2026v0.11.0 highlights (since v0.10.0) This release brings the dashboard mission-management workflow forward and includes the latest backend/runtime reliability work. Most important changes Added the Mission Workbench side panel on the control…
v0.10.0v0.10.0 · 23 Feb 2026v0.10.0 highlights (since v0.9.1) This release focused on mission reliability, automation control, and cross-client parity. Most important changes Hardened OpenCode/Codex execution paths: workspace-specific CLI/binary resolution, outdated…

README


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
  • Telegram Integration: Connect bots to missions for chat-based AI assistants with auto-mission creation per chat
  • Automations: Schedule recurring agent runs with cron-like triggers
  • Model Routing: Provider fallback chains with health checks and rate-limit handling
  • MCP Registry (optional): Extra tool servers (desktop/playwright/etc.) when needed
  • OpenAI-compatible Proxy Queue Mode: Optional deferred execution for /v1/chat/completions when all routed providers are temporarily rate-limited
  • 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: Anthropic's official coding agent with native skills support (.claude/skills/)
  • OpenCode: Open-source alternative via oh-my-opencode
  • Amp: 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


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)

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

Native (bare metal)

For production servers running Ubuntu 24.04 with maximum performance and native systemd-nspawn isolation.

Full native installation guide

First-time setup

After installation, follow the Getting Started Guide 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

Architecture & APIs

Setup Guides

Reference


Development

Setup git hooks

Enable pre-push formatting checks to catch CI failures locally:

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

README mirrored from the source repository 3 hours ago. The original is authoritative.

Questions

About Sandboxed.sh

How do I install Sandboxed.sh?

Run npx sandboxed-sh, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Sandboxed.sh safe to use with an AI agent?

Its trust score is 72 out of 100 (good). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Sandboxed.sh still maintained?

Yes — the latest release is v0.12.0 (16 May 2026), and the last commit was 6 months ago. The repository has 261 stars and 0 open issues.