Gemini CLI Setup

::: warning Gemini CLI is being discontinued Google is retiring account login for Gemini CLI (Pro / Ultra / free tiers) on June 18, 2026. Google states Gemini CLI stays accessible via a paid Gemini API key. See Gemini CLI Discontinuation & Migration. :::

Gemini CLI is Google's AI assistant. You can authenticate using your Google account, an API key, or Vertex AI.

Install and Configure

Open a terminal (Terminal on macOS/Linux, PowerShell on Windows) and run the following commands.

Install Gemini CLI:

npm install -g @google/gemini-cli

Find the installation path:

::: code-group

which gemini
# Example output: /usr/local/bin/gemini

where.exe gemini
# Example output: C:\Users\Username\AppData\Roaming\npm\gemini.cmd

:::

Open Settings → Agent Client. The default command (gemini) works in many cases. If the agent is not found automatically, set the Gemini CLI path to the path found above, or click Auto-detect.
Ensure Arguments contains --experimental-acp (this is set by default).

Authentication

Choose one of the following methods:

If you have a Google account and prefer not to use an API key, you can log in directly.

::: warning Account login is being discontinued for Pro / Ultra / free tiers on June 18, 2026. See Gemini CLI Discontinuation & Migration. :::

Run Gemini CLI in your terminal and choose "Login with Google":

gemini

Follow the browser authentication flow.
In Settings → Agent Client, leave the API key field empty.

::: tip If you have a Gemini Code Assist License from your organization, add GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID in the Environment variables field. :::

Option B: Gemini API Key

If you prefer to use an API key for authentication:

Get your API key from Google AI Studio
Open Settings → Agent Client → Built-in agents → Gemini CLI → API key
Click the Link... button next to the API key field
In the Select secret dialog:
- To use an existing secret: select it from the list and click Save
- To create a new one: click Add secret..., enter an ID (lowercase letters, numbers, and dashes only — e.g., gemini-api-key), paste your API key, then click Save

Once linked, the field shows the masked secret value with a Change button to swap secrets.

::: tip Managing secrets API keys are stored in Obsidian's Keychain (Settings → Keychain). You can rename, edit, or delete secrets there at any time. The same secret can be shared across plugins by referencing the same ID. :::

::: info Upgrading from a previous version If you previously stored your Gemini API key in this plugin (v0.10.x or earlier), it is automatically migrated to Obsidian's Keychain as gemini-api-key the first time you load the upgraded plugin. A one-time notification confirms the migration.

If gemini-api-key is already in use by another plugin with a different value, your key is preserved under agent-client-gemini-api-key instead. You can rename it from Settings → Keychain if you prefer. :::

::: tip If the key isn't picked up If authentication still fails, set the key on the Gemini CLI side instead: run gemini in your terminal, type /auth, choose Use Gemini API Key, and paste your key (it's stored in your system keychain). Then leave the API key field empty in Agent Client. :::

Option C: Vertex AI

If you are using Vertex AI for enterprise workloads:

In Settings → Agent Client → Built-in agents → Gemini CLI → Environment variables, add:

GOOGLE_API_KEY=YOUR_API_KEY
GOOGLE_GENAI_USE_VERTEXAI=true

Leave the API key field empty (use Environment variables instead).

::: tip If it isn't picked up If authentication still fails, configure Vertex AI on the Gemini CLI side instead: run gemini in your terminal, type /auth, and choose Vertex AI. :::

Verify Setup

Click the robot icon in the ribbon or use the command palette: "Open chat view"
Switch to Gemini CLI from the agent dropdown in the chat header
Try sending a message to verify the connection

Having issues? See Troubleshooting.

4.4 KiB Raw Blame History