OpenSRE
Framework and CLI for building AI agents that investigate incidents
What it is
OpenSRE is a Python framework and command-line agent for site reliability work: it connects to monitoring, logging, and chat tools such as Datadog, Grafana, and Slack, then investigates production incidents and suggests root causes. It offers an interactive shell, a headless mode for scripts and CI, and a Python API for embedding the agent in your own services. Platform and on-call engineers can run it on their own infrastructure, and the project also builds an end-to-end test environment for evaluating and training incident-response agents.