Set up AI models and manage your team through the Alex Sidebar Admin Portal at https://www.alexcodes.app/admin.

You’ll need to be on a team subscription and have admin access to use these features.

​
Access Team Settings

  1. Go to Alex Sidebar Admin Portal
  2. Sign in with your admin account
  3. Navigate to your team dashboard

​
Team Management

​
Managing Team Members

From the Members tab, you can:

1

View Current Members

See all team members with their roles (Admin/Member)

2

Invite New Members

  1. Enter the email address
  2. Select their role (Member or Admin)
  3. Click “Send Invitation”
3

Remove Members

Click “Remove” next to any member to revoke their access

Team members automatically inherit all model configurations set by admins. Individual API keys are not needed when using team models.

​
Models Configuration

The Models tab lets you configure custom endpoints for all AI features in Alex Sidebar. Leave fields empty to use default models.

Remember to click the “Save Changes” button at the bottom right after configuring your models. Changes won’t take effect until saved.

​
Available Model Types

Other fields are optional. Alex Sidebar will use the default if you leave them empty.

  1. Chat Models - These are the large language models for code generation and conversation in Alex Sidebar. Examples are Claude Sonnet 4, Gemini 2.5 Pro and OpenAI o3 model.
  2. Autocomplete Model - Tab completion while you type. Fast models like Codestral work best here.
  3. Thinking Model - Models like Gemini 2.5 Pro takes more time to reason on the given prompt and context to come to an answer.
  4. Voice Model - Handles voice-to-text if you use voice input.
  5. Embedding Model - Powers codebase search and indexing.
  6. Code-Apply Model - Specialized for applying code edits.
  7. Web Model - Used when searching the web.
  8. Image Model - Analyzes screenshots and generates diagrams. Needs vision capabilities like GPT-4V or Claude.
  9. Summarizer Model - Condenses long content.

​
Adding Custom Models

For each model type, configure:

1

Set Base URL

Enter your model endpoint URL (e.g., https://internal-ai-gateway.company.com/v1)

2

Add API Key

Enter the authentication key for your endpoint

3

Specify Model Name

Enter the exact model identifier (e.g., amazon.nova-pro-v1.0)

​
Example Configurations

Base URL: https://your-litellm-proxy.com/v1
API Key: your-litellm-key
Model Name: amazon.nova-pro-v1.0

​
Multiple Chat Models

You can add multiple chat models for different use cases:

Model Variety

Add different models (Claude, GPT-4, Gemini) and let developers choose based on their needs

Environment Separation

Configure separate models for development, staging, and production environments

​
Using Team Models in Alex Sidebar

After configuring and saving your team models, they automatically appear in Alex Sidebar for all team members.

Team members can:

  • Select from configured models using the model selector (bottom left of chat)
  • See custom model names exactly as configured by admins

Changes to team models apply immediately to all members. Users may need to restart Alex Sidebar to see new models.

​
Advanced Settings

The Advanced tab contains telemetry settings:

​
Telemetry

Toggle “Enable telemetry data collection for your team” to control:

  • Analytics data collection
  • Crash logs and error reporting
  • Usage statistics

When disabled, no telemetry data is sent from any team member’s Alex Sidebar.

​
Best Practices

1

Start with Chat Models

Configure chat models first as they’re used most frequently

2

Use Consistent Naming

Name models clearly (e.g., dev-claude, prod-gpt4) so developers know which to use

3

Test Before Deploying

Verify each model works correctly before adding team members

4

Document Model Purposes

Create internal documentation explaining when to use each model

​
Cost Management

When using team models:

  • All API costs are billed to your organization’s accounts
  • Individual developers don’t need personal API keys
  • Monitor usage through your cloud provider’s dashboard
  • Set up billing alerts to track spending

​
Troubleshooting

​
Integration with LiteLLM

For teams using LiteLLM proxy:

  1. Deploy LiteLLM with your enterprise models
  2. Add your LiteLLM endpoint as Base URL
  3. All team members automatically use your proxy
  4. No individual cloud accounts needed

See the LiteLLM Setup Guide for detailed instructions.