Smoky Agent
Smoky Agent is an advanced, modern AI coding assistant directly integrated into VS Code. With full support for Model Context Protocol (MCP) servers, Smoky gives your AI agent complete, secure access to terminal operations, filesystem operations, and Chrome DevTools, turning it into a fully capable, autonomous coding partner!
Features
- Modern Webview Interface: A sleek, dark-themed, highly responsive chat UI supporting markdown, code syntax highlighting, streaming, and a custom model selector.
- MCP Integration: By default, the agent has built-in integration with
forge-terminal-mcp (for powerful, headless terminal execution) and chrome-devtools-mcp (for browser inspection), along with filesystem tools.
- Dynamic Configuration: Configure custom system messages, core rules, multiple LLM providers, and additional MCP servers effortlessly using your workspace
config.json.
- Intelligent Abort: Safely cancel long-running AI generations natively from the interface with the push of a button.
Configuration (config.json)
Smoky Agent is fully configurable via a config.json file located at the root of your VS Code workspace.
How to Edit the Config
- Open the Command Palette (
Ctrl+Shift+P / Cmd+Shift+P).
- Type and run
Smoky: Open Configuration (or access it from the settings icon in the webview title menu).
- This will open the
config.json file in your editor.
Configuration Schema
Here is an example config.json you can use:
{
"systemMessage": "You are a helpful and intelligent AI assistant.",
"rules": [
"Always provide concise answers.",
"Use markdown for all your responses."
],
"models": [
{
"name": "Gemma-2.7",
"url": "http://192.168.1.37:3002/v1",
"apiKey": "your-api-key-here",
"model": "Gemma-2.7"
},
{
"name": "OpenAI GPT-4",
"url": "https://api.openai.com/v1",
"apiKey": "your-openai-api-key",
"model": "gpt-4-turbo"
}
],
"mcpServers": {
"my-custom-server": {
"command": "npx",
"args": ["-y", "some-mcp-server@latest"]
}
}
}
Configuration Options
systemMessage (string): The core directive given to the agent.
rules (string[]): An array of strict guidelines the agent must follow.
models (array): A list of supported LLMs to use. You can easily switch between these models from the dropdown inside the Smoky Chat view.
name: Display name in the dropdown UI.
url: The base URL for the OpenAI-compatible API endpoint (e.g., local endpoints like Ollama/vLLM or external APIs).
apiKey: API Key for the model.
model: The exact model identifier.
mcpServers (object): Add any custom MCP servers you want the agent to use in your workspace. (Smoky will automatically load builtin tools like the forge-terminal-mcp so you don't need to add them here).
Usage
- Open the Smoky Agent view from the Activity Bar (or run
Smoky: Start).
- Use the dropdown to select your configured model.
- Chat with the agent! It can execute commands, edit files, and build apps for you!