JetBrains AI

Route JetBrains AI Assistant traffic through Axemere Gateway across IntelliJ IDEA, PyCharm, GoLand, WebStorm, and all other JetBrains IDEs. Configuration is done through the IDE settings UI; no config files required.

Table of Contents

• Prerequisites
• How It Works
• Setup
  • Anthropic (Claude)
  • OpenAI
• Verify Traffic Is Flowing
• Next Steps

Prerequisites

• JetBrains AI Assistant plugin installed (bundled in recent IDE versions, or install from the JetBrains Marketplace)
• A gateway key: created in Console → Gateway Keys
• A workload ID: from Console → Workloads

How It Works

JetBrains AI Assistant supports configuring any OpenAI-compatible or Anthropic-compatible endpoint as a custom model provider. Pointing it at Axemere Gateway routes all AI Assistant requests through the gateway's policy engine before forwarding to the provider.

Privacy: Axemere never stores, logs, or accesses the content of AI prompts or responses. Only request metadata (model, token counts, latency, attribution) is recorded. See Execution Records for exactly what is and isn't kept.

Setup

Open Settings (Cmd+, on macOS / Ctrl+Alt+S on Windows/Linux) → Tools → AI Assistant.

Anthropic (Claude)

1. Click Add model (or Manage models).
2. Select Anthropic as the provider.
3. Set Endpoint URL to your gateway's Anthropic proxy URL:

https://us.gw.axemere.ai/proxy/anthropic/k/mvgc_k_your-key-here/w/your-workload

4. Set API key to any placeholder value; the gateway authenticates via the key in the URL.
5. Select your model (e.g., claude-sonnet-4-6) and click Verify connection.

OpenAI

1. Click Add model.
2. Select OpenAI compatible as the provider.
3. Set Endpoint URL to your gateway's OpenAI proxy URL. Include the /v1 suffix:

https://us.gw.axemere.ai/proxy/openai/k/mvgc_k_your-key-here/w/your-workload/v1

4. Set API key to any placeholder value.
5. Enter the model name (e.g., gpt-4o) and click Verify connection.

Replace mvgc_k_your-key-here and your-workload with your values from the console.

Verify Traffic Is Flowing

1. After saving, open the AI Assistant chat panel and send any message.
2. Check Records in the Axemere console; the request should appear within a few seconds, attributed to your workload.

Next Steps