FAQ

What is HealOps?

HealOps is an open-source framework for building AI SRE agents that investigate production incidents using your existing observability stack, cloud context, and runbooks.

How do I get started quickly?

Install HealOps, run onboarding, then investigate a sample alert:
healops onboard

healops investigate -i
tests/e2e/kubernetes/fixtures/datadog_k8s_alert.json

Which deployment path is recommended?

Deploy HealOps 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.

Can I self-host HealOps?

Yes. You can self-host HealOps 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).

Which model providers are supported?

HealOps 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.

Does HealOps work with our existing tools?

Usually yes. HealOps 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.

What happens when I run HealOps with no command?

Running healops 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.

How is security and telemetry handled?

HealOps is designed for security-sensitive environments and uses structured, auditable workflows. Anonymous telemetry can be disabled with HEALOPS_NO_TELEMETRY=1. For vulnerability reports, email support@healops.ai.

Overview

First steps