--- title: "FAQ" description: "Frequently asked questions about OpenSRE" --- OpenSRE is an open-source framework for building AI SRE agents that investigate production incidents using your existing observability stack, cloud context, and runbooks. Install OpenSRE, run onboarding, then investigate a sample alert:
opensre onboard
opensre investigate -i tests/e2e/kubernetes/fixtures/datadog_k8s_alert.json
Deploy OpenSRE as a standard Python/FastAPI app with the repo Dockerfile or your host's native Python workflow. Set LLM_PROVIDER, add the matching provider API key, and configure storage or integration env vars as needed. Yes. You can self-host OpenSRE on your own infrastructure as a normal web runtime. Before deploying, set{" "} LLM_PROVIDER and the matching provider key (for example{" "} ANTHROPIC_API_KEY when LLM_PROVIDER=anthropic). OpenSRE supports multiple providers, including Anthropic, OpenAI, OpenRouter, and Gemini via LLM_PROVIDER plus the matching API key. Additional providers and overrides are documented in .env.example. Usually yes. OpenSRE integrates with 60+ systems across observability, cloud, incident management, data platforms, and collaboration tools. See the Integrations section in docs for connector-specific setup steps. Running opensre starts an interactive incident-response shell where you can describe issues in plain language, stream investigations live, and ask grounded follow-up questions in the same session. OpenSRE is designed for security-sensitive environments and uses structured, auditable workflows. Anonymous telemetry can be disabled with OPENSRE_NO_TELEMETRY=1. For vulnerability reports, email support@opensre.com.