# Adrian

## Docs

- [Hosted and self-hosted](https://docs.adrian.secureagentics.ai/hosted-vs-open-source.md): Two ways to run Adrian's backend: hosted by Secure Agentics, or self-hosted from the open-source release.
- [How it works](https://docs.adrian.secureagentics.ai/how-it-works.md): Adrian's architecture, event flow, and operating modes.
- [Integrations](https://docs.adrian.secureagentics.ai/integrations.md): Adrian connects to your agent framework and to the alerting channels you already use.
- [Introduction](https://docs.adrian.secureagentics.ai/introduction.md): Adrian is a real-time security monitoring and control engine for AI agents that analyses agent activity logs (tool calls, actions, outputs) and reasoning traces to detect malicious, misaligned, or out-of-remit behaviour and optionally intervene in-flight.
- [Quickstart](https://docs.adrian.secureagentics.ai/quickstart.md): Wrap a LangChain agent with Adrian and see your first event in the dashboard.
- [Backend](https://docs.adrian.secureagentics.ai/reference/backend.md): Reference for the self-hosted Adrian backend: bring-up, configuration, and endpoints.
- [Claude Code Plugin](https://docs.adrian.secureagentics.ai/reference/claude-code.md): Reference for the Adrian Claude Code plugin: install, configuration, commands, enforcement modes, and what it captures.
- [Python SDK](https://docs.adrian.secureagentics.ai/reference/sdk.md): Reference for the Adrian Python SDK: installation, configuration, callbacks, and the events it emits.
- [Severity codes](https://docs.adrian.secureagentics.ai/reference/severity-codes.md): Adrian's four severity levels and the kinds of behaviour each one captures.
- [TypeScript SDK](https://docs.adrian.secureagentics.ai/reference/typescript-sdk.md): Reference for the Adrian TypeScript SDK and its OpenAI integration: install, wrapping your client, configuration, and what it captures.
- [Reliability](https://docs.adrian.secureagentics.ai/reliability.md): If Adrian fails, what happens to your agent?
- [Security and Privacy](https://docs.adrian.secureagentics.ai/security-and-privacy.md): How Adrian handles data and defends against prompt injection.
- [Videos](https://docs.adrian.secureagentics.ai/videos.md): Watch Adrian in action.