Skip to main content
The copilot command (@github/copilot) reads plain JSON under ~/.copilot. It shares the folder with the desktop app but no settings, so you can connect either one, both, or neither. For the desktop app, see Copilot App. Preview OpenAI Chat Completions Nexus Auto

Quick start

Install and sign in

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.
Sign in with your browser, or paste a Fireworks API key (fw_...).Already set up? Skip to step 2.

Connect Copilot CLI

Start a session and pick a model

Start a new copilot session. The default is fireworks/auto. Switch models with copilot --model fireworks/<name> or /model. To change the default, run nexus copilot-cli --model glm-latest.
Copilot CLI model picker showing Auto selected and Fireworks DeepSeek, GLM, Kimi, and MiniMax models

Copilot CLI model picker after Nexus CLI, with Auto selected

nexus copilot-cli status shows the provider, where the key comes from, and the configured model.
Image input works on models that support it. Copilot CLI doesn’t show context, reasoning, or pricing details for bring-your-own-key models.

Use Nexus Auto

Nexus Auto (auto) is supported on the Chat Completions API.
  • Anthropic and OpenAI model turns: save a key with nexus auto --anthropic-api-key or --openai-api-key (each prompts for the key), then run nexus copilot-cli again. Nexus CLI adds the saved key to the fireworks provider headers in providers.json. Or connect a Provider Key, which needs nothing saved locally.
  • Environment keys: Nexus CLI never sends ANTHROPIC_API_KEY or OPENAI_API_KEY from your environment.
  • Manual setup: send x-anthropic-api-key and x-openai-api-key headers yourself. See Manual setup (advanced).

MCP and tools

Nexus CLI doesn’t touch MCP. Set up servers in Copilot CLI as usual. Nexus CLI does not add web search to Copilot CLI. See Web Search.

Microsoft Foundry

Nexus CLI doesn’t connect Copilot CLI to Microsoft Foundry. For other options, see Nexus for Microsoft Foundry.

Troubleshooting

  • A model switch doesn’t take effect: use provider-prefixed model IDs such as fireworks/glm-latest. Copilot CLI rejects a bare glm-latest and silently falls back to its configured model.
See Nexus Auto for issues that affect every harness.

Manual setup (advanced)

~/.copilot/providers.json
A bring-your-own-key provider has no default model, and Copilot CLI won’t start without one. Select it in settings.json:
~/.copilot/settings.json
To use Nexus Auto with Anthropic or OpenAI model turns, add a headers map to the provider, such as "headers": { "x-anthropic-api-key": "sk-ant-..." }, and use auto as the model id and wireModel. The harness setup generates the full file.
Running nexus copilot-cli again rewrites the fireworks provider entry. It keeps x-anthropic-api-key and x-openai-api-key headers you added by hand, but removes any other headers you added. Add those again after you reconnect.
See what changes without the Nexus CLI.

What the Nexus CLI writes

Providers and models you added yourself stay in place. providers.json is saved with mode 0600. The x-anthropic-api-key and x-openai-api-key headers appear only for keys you saved with nexus auto.off restores both files byte-for-byte from the snapshots under ~/.nexus/copilot-cli/, or deletes them if Nexus CLI created them. COPILOT_HOME moves both files. Use --providers-path for a non-default providers.json.