Google Jules

Google Jules is Google's AI coding agent. Since Jules operates as a cloud service backed by Gemini models, it connects to AgentXchain via the api_proxy adapter using Google's Generative AI API.

Which adapter?

api_proxy with provider: "google" — AgentXchain sends governed turn prompts directly to Google's Generative AI API using the same Gemini models that power Jules.

Prerequisites

• A Google AI API key (GOOGLE_API_KEY) — get one from Google AI Studio
• agentxchain CLI installed

Configuration

{
  "runtimes": {
    "google-dev": {
      "type": "api_proxy",
      "provider": "google",
      "model": "gemini-3.1-pro",
      "auth_env": "GOOGLE_API_KEY"
    }
  },
  "roles": {
    "dev": {
      "runtime": "google-dev",
      "mandate": "Implement features using best practices",
      "authority": "proposed"
    }
  }
}

Available models

Model	Best for
gemini-3.1-pro	Complex coding tasks, architecture decisions
gemini-3.0-flash	Fast iteration, simple tasks
gemini-3.1-flash-lite	High-volume, cost-sensitive roles (QA, linting)

Verify the connection

export GOOGLE_API_KEY="your-key-here"
agentxchain connector check

The connector probe sends a test request to the Google Generative AI API to verify your key and model access.

Gotchas

• Jules vs. Gemini API: Jules is a cloud-hosted agent product; this integration uses the Gemini API directly. You get the same underlying models but not Jules' full agent orchestration — AgentXchain provides the orchestration layer instead.
• API endpoint: AgentXchain uses https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent. If you need a different endpoint (e.g., Vertex AI), use the base_url field to override.
• Vertex AI: For enterprise Google Cloud setups using Vertex AI instead of the public API, set base_url to your Vertex endpoint and use the appropriate auth mechanism.