Skip to content
| Marketplace
Sign in
Visual Studio Code>Machine Learning>Darwin Router for AntigravityNew to Visual Studio Code? Get it now.
Darwin Router for Antigravity

Darwin Router for Antigravity

Krishnakanth J

|
2 installs
| (0) | Free
Self-improving semantic LLM router — monitor, manage, and visualize Darwin Router directly inside VS Code / Antigravity.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

Darwin Router for Antigravity

Self-improving semantic LLM router — monitor, manage, and visualize Darwin Router directly inside VS Code / Antigravity.

Version Publisher


Features

🟢 Real-Time Status Bar Monitoring

A persistent status bar item shows whether your local Darwin Router proxy is online or offline, polling the /healthz endpoint every 5 seconds.

  • Active: ✓ Darwin: Active — click to open the live dashboard
  • Offline: ⊘ Darwin: Offline — highlights with a warning background

📊 Embedded Stats Dashboard (Sidebar Webview)

An activity bar panel displays live telemetry fetched from /stats:

  • Total requests and exemplar count
  • Route distribution with animated bar charts (simple / reasoning / vision)
  • Cost savings — actual vs. counterfactual baseline
  • Self-improvement metrics — judge evaluations & exemplars auto-inserted
  • Recent request log with route badges, query previews, latency, and timestamps

🚀 Server Process Management

Start and stop the Darwin Router backend directly from the command palette or the sidebar toolbar — no terminal required.

Command Description
Darwin: Start Server Launches uv run uvicorn router.proxy:app --port 8787 in your AI-Summit repo
Darwin: Stop Server Gracefully terminates the running proxy subprocess
Darwin: Open Dashboard Opens http://127.0.0.1:8787/ in your default browser
Darwin: Check Status Force-refreshes health and shows a notification
Darwin: View Stats Panel Focuses the sidebar stats webview

⚙️ Configurable Settings

Setting Default Description
darwin.serverUrl http://127.0.0.1:8787 Base URL for the proxy server
darwin.pollingInterval 5000 Health-check interval in ms
darwin.autoStartBackend false Auto-start the backend on activation
darwin.backendPath "" Path to AI-Summit repo (prompts on first use)

Getting Started

Prerequisites

  • VS Code ≥ 1.80.0 (or Antigravity)
  • The AI-Summit repository cloned locally
  • uv installed for Python dependency management
  • Ollama running locally with at least qwen3:4b pulled

Install from VSIX

code --install-extension darwin-router-antigravity-0.1.0.vsix

First Run

  1. Open the Command Palette (Ctrl+Shift+P)
  2. Run Darwin: Start Server
  3. Select your AI-Summit repository folder when prompted
  4. The status bar will turn green when the backend is ready
  5. Open the Darwin Router sidebar to see live stats

Development

# Install dependencies
npm install

# Compile TypeScript
npm run compile

# Watch mode
npm run watch

# Package .vsix
npm run package

Architecture

darwin-router-antigravity/
├── src/
│   ├── extension.ts          # Lifecycle, commands, status bar, subprocess
│   └── statsViewProvider.ts  # Sidebar webview with live dashboard
├── package.json              # Extension manifest
├── tsconfig.json             # TypeScript config
├── .vscodeignore             # Files excluded from .vsix
└── README.md

The extension communicates with the Darwin Router Python backend via HTTP:

  • GET /healthz — health check (polled every N seconds)
  • GET /stats — aggregated telemetry for the dashboard
  • POST /v1/chat/completions — OpenAI-compatible completions endpoint

License

MIT © KrishnakanthJ

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
  • Your Privacy Choices
  • Consumer Health Privacy
© 2026 Microsoft