supermemory/apps/docs/org-settings.mdx

---
title: "Organization Settings"
description: "Configure organization-wide settings and content filtering for Supermemory"
icon: "settings"
---

Organization settings control how Supermemory processes content across your entire organization. These settings apply to all memories and connectors, helping you:

- Filter content before indexing
- Configure custom OAuth applications for connectors
- Set organization-wide processing rules
- Control what gets indexed and what gets excluded

<Note>
Settings are organization-wide and apply to all users and memories within your organization.
</Note>

## Why Settings Matter

The settings endpoint is crucial for teaching Supermemory about your specific use case. It helps Supermemory understand:

- **What you are**: Your organization's specific use case and purpose
- **What to expect**: The types of content and information flowing through your system
- **How to interpret**: Context for understanding queries in your specific use case
- **What to prioritize**: Which content matters most for your users

### Example: Brand Guidelines Use Case

Without proper settings, when a user searches "what are our values?", Supermemory might return random documents mentioning "values". But with proper configuration:

```typescript
await client.settings.update({
  shouldLLMFilter: true,
  filterPrompt: `You are managing brand guidelines for Brand.ai.
    You will receive all outbound content from our organization.
    
    When users search, they're looking for:
    - "What are our values?" → Return official brand values document
    - "What's our tone of voice?" → Return brand voice guidelines
    - "How do we describe our mission?" → Return approved mission statements
    
    Focus on the latest approved brand materials, not drafts or outdated versions.`
});
```

Now Supermemory understands that:
- Searches about "values" refer to brand values, not financial values
- "Tone" means brand voice, not audio settings
- Priority should be given to official, approved content

This context dramatically improves search relevance and ensures users get the right information for their specific use case.

## API Endpoints

### Get Current Settings

Retrieve your organization's current settings configuration.

<CodeGroup>

```typescript TypeScript
const settings = await client.settings.get();
console.log('Current settings:', settings);
```

```python Python
settings = client.settings.get()
print(f'Current settings: {settings}')
```

```bash cURL
curl -X GET "https://api.supermemory.ai/v3/settings" \
  -H "Authorization: Bearer $SUPERMEMORY_API_KEY"
```

</CodeGroup>

### Update Settings

Update your organization's settings. You only need to include the fields you want to change.

<CodeGroup>

```typescript TypeScript
const updatedSettings = await client.settings.update({
  shouldLLMFilter: true,
  filterPrompt: "Only index technical documentation and code",
  includeItems: ["*.md", "*.ts", "*.py"],
  excludeItems: ["node_modules", ".git", "*.test.*"]
});

console.log('Updated fields:', updatedSettings.updated);
```

```python Python
updated_settings = client.settings.update(
    should_llm_filter=True,
    filter_prompt="Only index technical documentation and code",
    include_items=["*.md", "*.ts", "*.py"],
    exclude_items=["node_modules", ".git", "*.test.*"]
)

print(f'Updated fields: {updated_settings.updated}')
```

```bash cURL
curl -X PATCH "https://api.supermemory.ai/v3/settings" \
  -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "shouldLLMFilter": true,
    "filterPrompt": "Only index technical documentation and code",
    "includeItems": ["*.md", "*.ts", "*.py"],
    "excludeItems": ["node_modules", ".git", "*.test.*"]
  }'
```

</CodeGroup>

## Content Filtering Settings

Control what content gets indexed into Supermemory.

### Basic Filtering

Use include/exclude patterns to filter content:

```typescript
await client.settings.update({
  includeItems: [
    "*.md",           // All markdown files
    "*.mdx",          // MDX documentation
    "docs/**",        // Everything in docs folder
    "src/**/*.ts"     // TypeScript files in src
  ],
  excludeItems: [
    "node_modules",   // Dependencies
    ".git",           // Version control
    "*.test.*",       // Test files
    "build/**",       // Build outputs
    "*.tmp"           // Temporary files
  ]
});
```

### Intelligent LLM Filtering

Enable AI-powered content filtering for semantic understanding:

```typescript
await client.settings.update({
  shouldLLMFilter: true,
  filterPrompt: `You are filtering content for a technical documentation system.
    
    Include:
    - API documentation
    - Code examples and tutorials
    - Technical guides and references
    - Architecture documentation
    
    Exclude:
    - Marketing materials
    - Internal meeting notes
    - Personal information
    - Outdated or deprecated content
    
    Focus on content that helps developers understand and use our APIs.`
});
```

## Connector OAuth Settings

Configure custom OAuth applications for connector integrations.

### Google Drive Custom OAuth

```typescript
await client.settings.update({
  googleDriveCustomKeyEnabled: true,
  googleDriveClientId: "your-client-id.apps.googleusercontent.com",
  googleDriveClientSecret: "your-client-secret"
});
```

### Notion Custom OAuth

```typescript
await client.settings.update({
  notionCustomKeyEnabled: true,
  notionClientId: "your-notion-oauth-client-id",
  notionClientSecret: "your-notion-oauth-client-secret"
});
```

### OneDrive Custom OAuth

```typescript
await client.settings.update({
  onedriveCustomKeyEnabled: true,
  onedriveClientId: "your-azure-app-id",
  onedriveClientSecret: "your-azure-app-secret"
});
```

## Best Practices

### 1. Set Before Bulk Import
Configure settings before importing large amounts of content. Changes don't retroactively affect existing memories.

### 2. Be Specific in Filter Prompts
Provide clear context about your organization and expected search patterns:

```typescript
// Good - Specific and contextual
filterPrompt: `Technical documentation for developers.
  Include: API references, code examples, error solutions.
  Exclude: marketing content, personal data, test files.
  Users search for: implementation details, troubleshooting, best practices.`

// Bad - Too vague
filterPrompt: "Only important content"
```

### 3. Test OAuth Credentials
Always test custom OAuth credentials in development before production:

```typescript
// Test connection after updating OAuth settings
const testConnection = await client.connections.create('google-drive', {
  redirectUrl: 'https://yourapp.com/callback',
  containerTags: ['test-connection']
});
```

### 4. Monitor Filter Effectiveness
Check what's being indexed to ensure filters work as expected:

```typescript
const memories = await client.memories.list({
  containerTags: ['your-tags'],
  limit: 10
});

// Review what's actually being indexed
memories.memories.forEach(memory => {
  console.log(`Indexed: ${memory.title} - ${memory.type}`);
});
```

## Important Notes

<Warning>
**Settings Limitations:**
- Changes are organization-wide, not per-user
- Settings don't retroactively process existing memories
- OAuth credentials must be properly configured in respective platforms
- Filter patterns are applied during content ingestion
</Warning>

## Related Documentation

- [Connectors Overview](/connectors/overview) - Setting up external integrations
- [Google Drive Setup](/connectors/google-drive) - Configure Google Drive OAuth
- [Notion Setup](/connectors/notion) - Configure Notion OAuth
- [OneDrive Setup](/connectors/onedrive) - Configure OneDrive OAuth