RunbookAI vs StackStorm

RunbookAI is a self-hosted, MIT-licensed incident-response tool for investigating production problems. Its workflow collects incident context, ranks hypotheses, checks them against infrastructure, identifies a root cause, and recommends remediation. Users can ask natural-language questions across AWS, Kubernetes, and CloudWatch, then execute step-by-step runbooks. Queries are read-only by default; every mutating action needs explicit human approval. Investigations record hypotheses, evidence, proposed actions, approval decisions, and execution results in a local audit trail. RunbookAI indexes knowledge from local files, Confluence, and Google Drive. Documented integrations include AWS, Kubernetes, PagerDuty, OpsGenie, Slack, and Claude Code. A self-hosted shared knowledge server exposes runbooks, postmortems, and known issues through REST and an MCP endpoint for Claude Code. CLI mode is available, with no hosted service or control plane. The maker says it runs inside your infrastructure, sends no telemetry, and sends model requests directly to the configured provider without proxying or storing prompts. Requirements include Bun 1.0+ or Node.js 20+ and an Anthropic API key for Claude.

StackStorm is a free, open-source platform for integrating services and automating responses to events. Rules connect triggers to actions or workflows, and workflows can combine actions into multi-step automations. Sensors and actions link external systems; listed examples include webhooks, SSH, REST calls, OpenStack, Docker, Puppet, Sensu, and JIRA. StackStorm Exchange offers ready-made integration packs, and users can create and share packs of their own. Action records include triggering context and results, while audit logs can connect to Logstash, Splunk, statsd, and syslog. Administrators can use role-based access control to limit users’ access and operations. The platform includes a Web UI, CLI client, REST API, and Python client bindings. It is self-hosted and distributed as Linux RPMs and Debs or Docker images; deployment documentation also covers Vagrant/OVA, Ansible, Puppet, and Kubernetes. Supported systems are 64-bit Ubuntu and RHEL, Rocky Linux, or CentOS. Other Linux distributions, Windows, and Apple OSX are not officially supported. Listed uses include remediation, continuous deployment, ChatOps, and automated security response.