Skip to main content

Integrations

Integrations allow agents to interact with external tools and services, extending their capabilities beyond chat.

Available Integrations

IntegrationAgentsUse Case
GitHubOpenClaw (planned)PR reviews, issues
JiraOpenClaw (planned)Issue tracking
GitLabNot plannedAlternative to GitHub
ConfluenceNot plannedDocumentation
LinearNot plannedIssue tracking
NotionNot plannedKnowledge base

Integration vs Provider vs Channel

ComponentPurposeExample
ProviderAI model backendOpenAI GPT-4
ChannelHow users talk to agentDiscord, CLI
IntegrationWhat the agent can doRead GitHub issues

How Integrations Work

Integrations typically:

  1. Read data: Fetch information from external services
  2. Take actions: Create/update items in external services
  3. Receive events: Webhooks for real-time updates
  4. Use credentials: API keys or OAuth tokens

Configuration

Integrations will be configured during agent onboarding or separately:

# Future command (not yet available)
clm agent configure <agent-name> --integrations

Security

  • API tokens stored securely
  • Scoped permissions (least privilege)
  • Audit logging for actions
  • Per-integration credential isolation

Requesting New Integrations

To request a new integration:

  1. Check if it exists in 📋 Not Planned section
  2. Open an issue describing:
    • The service (e.g., PagerDuty, Zendesk)
    • Use case
    • Required actions (read, write, both)
  3. Consider contributing a PR

See individual integration pages for detailed setup instructions.