Integration Guide

JetBrains IDEs with Meridian

Connect Meridian's AI assistant directly into IntelliJ, PyCharm, GoLand, Rider, and every other JetBrains IDE. Use the CodeGPT plugin with a custom OpenAI-compatible endpoint — no middleware, no proxy, just your Meridian API key.

Prerequisites

Meridian API Key

Generate one from your dashboard. Requires an active subscription.

CodeGPT Plugin

Free plugin from the JetBrains Marketplace. Install via Settings → Plugins → Marketplace → search "CodeGPT".

Configuration

1

Open CodeGPT Settings

After installing, open Settings → Tools → CodeGPT. Under the Service tab, select Custom OpenAI as your provider.

2

Set the API Endpoint

Paste the Meridian chat completions endpoint into the URL field:

https://api.getnimbus.net/v1/chat/completions
3

Enter Your API Key

In the API key field, paste your Meridian key. It should start with sk-nimbus-:

sk-nimbus-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
4

Select Model & Test

Set the model to meridian-pro. Click Test Connection — you should see a green success indicator. Apply the settings and open any file. Select code, right-click, and choose Ask CodeGPT to start using Meridian inline.

Pro Tips

  • ▸Bind Ctrl+Shift+M (or Cmd+Shift+M on macOS) to "Ask CodeGPT" in Keymap settings for instant access without leaving the keyboard.
  • ▸Use the Diff View feature in CodeGPT to preview AI-suggested changes before applying them — Meridian streams token-by-token so you see results instantly.
  • ▸The endpoint is fully OpenAI-compatible. Any plugin or tool that accepts a custom base URL (Continue.dev, Cursor, Aider) works with Meridian using the same configuration pattern.

Ready to ship faster?

Meridian Pro unlocks unlimited completions, 128K context, and priority inference.

View Plans