coderunner

CodeRunner: A local sandbox for your AI agents

CodeRunner helps you sandbox your AI agents and its actions inside a sandbox.

Key use case: Run AI agent code in a sandbox with explicitly chosen host mounts and network access. Isolation reduces risk; it does not prevent all data loss or exfiltration.

For cloud managed VMs for agents, we have launched - InstaVM - Instant computers for AI agents

Quick Start

Prerequisites: Mac with macOS and Apple Silicon (M1/M2/M3/M4), Python 3.10+

Credentials

The installer generates the sandbox token in ~/.coderunner/api-token (or saves the CODERUNNER_API_TOKEN you exported). Clients send it as Authorization: Bearer <token>; cat ~/.coderunner/api-token prints it. Only GET /health is public, and a missing or weak token fails closed. The Claude Desktop proxy and the examples read the token from that file when the variable is not set. See authentication and network boundaries.

git clone https://github.com/instavm/coderunner.git
cd coderunner
chmod +x install.sh
./install.sh

Stop and resume

Stop the sandbox when you are done:

container stop coderunner

Resume the same sandbox later, preserving its filesystem. Python kernel state is volatile and does not survive a VM or server restart:

container start coderunner

To start over with a clean sandbox, delete the container and run the installer again:

container delete coderunner && ./install.sh

Resource limits and workspace mounts

CPU and memory limits can be set with installer options or the CODERUNNER_CPUS and CODERUNNER_MEMORY environment variables:

./install.sh --cpus 4 --memory 8g

Additional host directories must be mounted under /workspace. They are read-only by default; add :rw only when the sandbox needs to write to the host:

./install.sh \
  --mount "$HOME/projects/api:/workspace/api" \
  --mount "$HOME/projects/output:/workspace/output:rw"

Extra mounts default to none. Resource and mount settings are fixed when the container is created; delete the container before changing them.

Disable outbound network access

By default, code running in the sandbox has unrestricted network access. To run it on a host-only network with no internet access:

CODERUNNER_NETWORK=none ./install.sh

In this mode, the MCP server is available at http://127.0.0.1:8222/mcp. The setting is fixed when the container is created; the installer refuses to resume a container with a different network mode.

With Claude Code

Claude Code runs commands on your machine, as you, with permission prompts as the only boundary. Pointing it at CodeRunner's tools instead runs the code it writes in the VM: it can only touch the folders you mounted under /workspace, the network you allowed, and the sandbox's own filesystem, whatever it was told to do. Use the sandbox for code that handles untrusted input or that you would not run by hand, and for several agents that must not share state (named sessions). It does not protect anything you mount read-write.

Run Claude Code inside a Sandbox

./install.sh (if not already done)

container exec -it coderunner /bin/bash

root@coderunner:/app# npm install -g @anthropic-ai/claude-code

Other Integration Options

MCP server will be available at: http://coderunner.local:8222/mcp

The installer creates ~/.coderunner/venv for the Claude Desktop proxy. For the other Python examples, install their dependencies in your own virtualenv:

pip install -r examples/requirements.txt

1. Claude Desktop Integration

Configure Claude Desktop to use CodeRunner as an MCP server:

1. Copy the example configuration:

   cd examples
   cp claude_desktop/claude_desktop_config.example.json claude_desktop/claude_desktop_config.json
   

2. Edit the configuration file and replace the placeholder paths:

   • Replace /path/to/your/python with $HOME/.coderunner/venv/bin/python using the full path to your home directory
   • Replace /path/to/coderunner with the actual path to your cloned repository

   Example after editing:

   {
     "mcpServers": {
       "coderunner": {
         "command": "/Users/yourname/.coderunner/venv/bin/python",
         "args": ["/Users/yourname/coderunner/examples/claude_desktop/mcpproxy.py"]
       }
     }
   }
   

3. Update Claude Desktop configuration:

   • Open Claude Desktop
   • Go to Settings → Developer
   • Add the MCP server configuration
   • Restart Claude Desktop

4. Start using CodeRunner in Claude: Code Claude writes now runs in the sandbox.

   If the tool shows as "Disabled" in the chat's tool menu although the server is listed as running: quit Claude Desktop fully (Cmd-Q) and open it again, make sure command is the venv python the installer printed (it has fastmcp), and read ~/Library/Logs/Claude/mcp-server-coderunner.log for the proxy's error. The proxy needs the sandbox running (container list) and the token file ~/.coderunner/api-token.

2. Claude Code CLI

Use CodeRunner with Claude Code CLI for terminal-based AI assistance:

Quick Start:

# 1. Install and start CodeRunner (one-time setup; run as yourself, it asks for sudo when it needs it)
git clone https://github.com/instavm/coderunner.git
cd coderunner
./install.sh

# 2. Add the sandbox with its token (the installer prints this command)
claude mcp add --transport http coderunner http://coderunner.local:8222/mcp \
  --header "Authorization: Bearer $(cat ~/.coderunner/api-token)"

# 3. Reconnect to MCP servers
/mcp

The Claude Code plugin (claude plugin marketplace add https://github.com/instavm/coderunner-plugin) predates the token and gets 401 until it sends the same header; use the command above until the plugin is updated.

Installation Steps:

1. Navigate to Plugin Marketplace:

   

2. Add the InstaVM repository:

   

3. Execute Python code with Claude Code:

   

That's it! Claude Code now has access to all CodeRunner tools:

• execute_python_code - Run Python code in persistent Jupyter kernel
• start_python_session - Reserve an isolated kernel for a named session
• list_python_sessions - List active named sessions
• stop_python_session - Stop a session and discard its kernel state
• navigate_and_get_all_visible_text - Web scraping with Playwright
• list_skills - List available skills (docx, xlsx, pptx, pdf, image processing, etc.)
• get_skill_info - Get documentation for specific skills
• get_skill_file - Read skill files and examples

Pass the returned session_id to execute_python_code to keep state isolated between agents. Up to five named sessions can run concurrently.

Learn more: See the plugin repository for detailed documentation.

3. OpenCode Configuration

Configure OpenCode to use CodeRunner as an MCP server:

Create or edit ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "coderunner": {
      "type": "remote",
      "url": "http://coderunner.local:8222/mcp",
      "headers": { "Authorization": "Bearer <contents of ~/.coderunner/api-token>" },
      "enabled": true
    }
  }
}

After saving the configuration:

1. Restart OpenCode
2. CodeRunner tools will be available automatically
3. Start executing Python code with full access to the sandboxed environment

4. Python OpenAI Agents

Use CodeRunner with OpenAI's Python agents library:

1. Set your OpenAI API key:

   export OPENAI_API_KEY="your-openai-api-key-here"
   

2. Run the client:

   python examples/openai_agents/openai_client.py
   

3. Start coding: Enter prompts like "write python code to generate 100 prime numbers" and watch it execute safely in the sandbox!

5. Gemini-CLI

Gemini CLI is recently launched by Google.

~/.gemini/settings.json

{
  "theme": "Default",
  "selectedAuthType": "oauth-personal",
  "mcpServers": {
    "coderunner": {
      "httpUrl": "http://coderunner.local:8222/mcp",
      "headers": { "Authorization": "Bearer <contents of ~/.coderunner/api-token>" }
    }
  }
}

6. Kiro by Amazon

Kiro is recently launched by Amazon.

~/.kiro/settings/mcp.json

{
  "mcpServers": {
    "coderunner": {
      "command": "/path/to/venv/bin/python",
      "args": [
        "/path/to/coderunner/examples/claude_desktop/mcpproxy.py"
      ],
      "disabled": false,
      "autoApprove": [
        "execute_python_code"
      ]
    }
  }
}

7. Coderunner-UI (Offline AI Workspace)

Coderunner-UI is our own offline AI workspace tool designed for full privacy and local processing.

coderunner-ui

Security

Code runs in an isolated container with VM-level isolation. Your host system and files outside the sandbox remain protected.

From @apple/container:

Each container has the isolation properties of a full VM, using a minimal set of core utilities and dynamic libraries to reduce resource utilization and attack surface.

Skills System

CodeRunner includes a built-in skills system that provides pre-packaged tools for common tasks. Skills are organized into two categories:

Built-in Public Skills

The following skills are included in every CodeRunner installation:

• pdf-text-replace - Replace text in fillable PDF forms
• image-crop-rotate - Crop and rotate images

Using Skills

Skills are accessed through MCP tools:

# List all available skills
result = await list_skills()

# Get documentation for a specific skill
info = await get_skill_info("pdf-text-replace")

# Execute a skill's script
code = """
import subprocess
subprocess.run([
    'python',
    '/app/uploads/skills/public/pdf-text-replace/scripts/replace_text_in_pdf.py',
    '/app/uploads/input.pdf',
    'OLD TEXT',
    'NEW TEXT',
    '/app/uploads/output.pdf'
])
"""
result = await execute_python_code(code)

Adding Custom Skills

Users can add their own skills to the ~/.coderunner/assets/skills/user/ directory:

1. Create a directory for your skill (e.g., my-custom-skill/)
2. Add a SKILL.md file with documentation
3. Add your scripts in a scripts/ subdirectory
4. Skills will be automatically discovered by the list_skills() tool

Skill Structure: