Copilot App

Add Fireworks models and Nexus Auto to the GitHub Copilot desktop app with the Nexus CLI or manual setup.

The copilot command is set up separately in Copilot CLI.

​

Quick start

1. Install and sign in

   curl -fsSL https://nexus.fireworks.ai/install.sh | bash
   

   You need Node.js 22 or later, git, and bash. On Windows, run the installer from Git Bash. PowerShell breaks the script’s line endings.

   nexus login
   

   Sign in with your browser, or paste a Fireworks API key (fw_...).

   If the Nexus CLI is already installed and signed in, skip to step 2.

2. Quit the app

   Quit the app before you connect or run off. A running app overwrites the change from memory. If it’s open, Nexus CLI waits until you quit.

3. Connect the Copilot App

   nexus copilot-app
   

   Nexus Auto is the default model. To pick another one, run nexus copilot-app --model <id>, such as --model glm-latest.

4. Reopen and pick a model

   Reopen the app and pick a model under Fireworks in the model picker.

To restore your original settings, quit the app and run nexus copilot-app off.

​

Use Nexus Auto

• Anthropic and OpenAI model turns need a Provider Key from your admin. Without one, Nexus Auto serves every turn with open models.
• Image input, the hover-card Context row, and AI-credits pricing don’t work with the app’s bring-your-own-key path.

​

MCP and tools

• Nexus CLI doesn’t change your MCP servers.
• Nexus CLI doesn’t add web search to the Copilot App.

​

Troubleshooting

Fixes for issues that affect every harness are in Nexus Auto troubleshooting.

​

Manual setup (advanced)

In Settings → Model providers, add a provider with the values Nexus CLI uses:

Field	Value
Base URL	https://api.fireworks.ai/inference/v1
API key	Your Fireworks key
Models	Fireworks IDs, such as glm-latest or kimi-latest

Without the Nexus CLI, you take over the tasks it otherwise performs, such as undo and updates.