AI coding agent toolkit - process management, reverse proxy with traffic logging, browser instrumentation, and sketch mode
npx claudepluginhub standardbeagle/agntMCP server for AI coding agents: process management, reverse proxy with traffic logging, frontend instrumentation with 50+ diagnostic functions, sketch mode for wireframing, and session scheduling
Give your AI coding agent browser superpowers.
agnt is a new kind of tool designed for the age of AI-assisted development. It acts as a bridge between your AI coding agent and the browser, extending what's possible during vibe coding sessions.
When you're in the flow with Claude Code, Cursor, or other AI coding tools, agnt lets your agent:

Draw wireframes directly on your running app, then send them to your AI agent
Traditional AI coding assistants are blind to what's happening in the browser. They can write code, but they can't:
agnt changes this. It creates a bidirectional channel between your browser and your AI agent:
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Your Browser │ ←──► │ agnt │ ←──► │ AI Agent │
│ │ │ │ │ │
│ - See changes │ │ - Proxy traffic│ │ - Receives │
│ - Send notes │ │ - Capture errors│ │ context │
│ - Draw sketches│ │ - Inject tools │ │ - Acts on │
│ - Click to log │ │ - Route messages│ │ feedback │
└─────────────────┘ └─────────────────┘ └─────────────────┘
npm (recommended):
npm install -g @standardbeagle/agnt
pip/uv:
pip install agnt
# or
uv pip install agnt
From source:
git clone https://github.com/standardbeagle/agnt.git
cd agnt
make build && make install-local
Add to your MCP configuration:
{
"mcpServers": {
"agnt": {
"command": "agnt",
"args": ["mcp"]
}
}
}
Or install as a Claude Code plugin:
/plugin marketplace add standardbeagle/agnt
/plugin install agnt@agnt
Wrap your AI tool for overlay features:
agnt run claude --dangerously-skip-permissions
agnt run cursor
agnt run aider
This adds a terminal overlay menu (Ctrl+P) and enables the browser-to-terminal message bridge.
Start a proxy and your agent gains eyes into the browser:
proxy {action: "start", id: "app", target_url: "http://localhost:3000"}
Now your agent can:
// Take screenshots
proxy {action: "exec", id: "app", code: "__devtool.screenshot('current-state')"}
// Inspect any element
proxy {action: "exec", id: "app", code: "__devtool.inspect('#submit-button')"}
// Audit accessibility
proxy {action: "exec", id: "app", code: "__devtool.auditAccessibility()"}
// Check what the user clicked
proxy {action: "exec", id: "app", code: "__devtool.interactions.getLastClickContext()"}
Every proxied page gets a small floating bug icon. Click it to:
No more alt-tabbing to describe what you see - just click and send.
Press the sketch button and draw directly on your UI:
Perfect for saying "I want a button here" or "this layout is wrong" without typing a word.
JavaScript errors are automatically captured and available to your agent:
proxylog {proxy_id: "app", types: ["error"]}
→ {message: "TypeError: Cannot read property 'map' of undefined",
stack: "at ProductList (products.js:42)",
timestamp: "..."}
Your agent sees errors as they happen, not when you remember to mention them.