- A code repository, where Switch Trust scans your source for agents. This covers GitHub and GitLab.
- A cloud platform, where Switch Trust scans your account for deployed AI resources. This covers AWS and GCP.
- A telemetry feed, where your agents send Switch Trust their sessions, turns, and cost over OpenTelemetry, with no SDK to install.
- The Claude Code plugin, which reports each person’s Claude Code sessions and cost.
- Switch Rooms, where Switch Trust checks room messages against a guardrail policy.
How the page works
Each data source is a card that shows whether it is Connected or Disconnected. Select a card to open it, connect it, and see what it has scanned. Once open, a source has a Setup tab for connecting it and a Scans tab that lists what it has scanned and when. OpenTelemetry, the Claude Code plugin, and Switch Rooms have no scans to list, so their cards show no status and they have setup steps only. To open them, you need the Editor role or higher.To confirm that scans are actually arriving, open the source and check its Scans tab.
Connected on the card is a summary, not a live health check. A code repository reads
Connected once it has reported at least one scan, and a cloud platform reads Connected
once you have saved its credentials.
Choose a data source
GitHub
Scan a GitHub repository for agents from a GitHub Action in your workflow
GitLab
Scan a GitLab repository for agents from a GitLab CI/CD component
AWS
Scan your AWS account for Bedrock, Lex, and SageMaker resources
GCP
Scan your Google Cloud project for Vertex AI resources
OpenTelemetry
Send agent sessions, turns, and cost from LangChain or Claude Code over OpenTelemetry
Claude Code plugin
Report each person’s Claude Code sessions and cost with the Switch Trust plugin
Switch Rooms
Check Switch Rooms messages against a guardrail policy

