🔒 Agent Jail

Ephemeral Docker sandboxes for AI agents

Give your AI agent a jail, not your machine.

Live Demo · Pricing · API Docs

🎯 What is Agent Jail?

Agent Jail provides disposable, isolated Docker sandboxes for AI agents. Instead of letting agents run commands directly on your machine, Agent Jail creates ephemeral containers where agents can safely execute code.

Perfect for:

• 🤖 AI code execution (ChatGPT, Claude, etc.)

• 🧪 Testing untrusted code safely

• 🔬 Research environments

• 📚 Educational platforms

• 🏗️ CI/CD pipelines

Related MCP server: agent-sandbox-mcp

✨ Features

Core

• ✅ Disposable sandboxes — auto-cleanup after TTL

• ✅ Docker isolation — true containerization

• ✅ Resource limits — RAM/CPU caps per tier

• ✅ Network isolation — optional per sandbox

• ✅ TTL-based cleanup — automatic expiration

Multi-tenant Platform

• 🔐 Self-serve auth — email/password signup (no API key needed initially)

• 💎 3 tiers — Free / Pro / Enterprise with enforced quotas

• 💰 Crypto billing — pay with USDT/TON/BTC via NOWPayments

• ⚡ Auto-upgrade — webhook → instant tier activation

• 📊 Usage tracking — full audit log per user

Interfaces

• 🖥️ Web dashboard — manage sandboxes visually

• 🔌 REST API — full programmatic control

• 🤖 Telegram bot — bilingual (FA/EN) glass-button UI

• 🔧 MCP server — for AI clients (Claude Desktop, etc.)

🚀 Quick Start

1. Clone & Install

git clone https://github.com/idiscoord13-sketch/agent-jail-mcp.git
cd agent-jail-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt