AI Agent Platformfor SRE
Deep investigation engine that learns from every incident. Thinks like your best SRE — read-only, open source.
How It Works
Investigate, learn, repeat
A continuous loop that gets smarter with every incident
Describe
Tell Siclaw what's wrong — any channel
Investigate
4-phase engine: hypothesize, validate in parallel, conclude
Learn
Every investigation feeds memory — next time is smarter
Report
Structured root cause with evidence and confidence scores
Describe
Tell Siclaw what's wrong — any channel
Investigate
4-phase engine: hypothesize, validate in parallel, conclude
Report
Structured root cause with evidence and confidence scores
Learn
Every investigation feeds memory — next time is smarter
Capabilities
Built for production
Security First
Read-only investigation by default, with controlled execution when needed.
Alert-Driven Channels
Connect Siclaw to team channels and trigger investigations from alerts or operator input.
Skill System
AI generates diagnostic scripts with review workflow. Fork and share across teams.
Cron Patrols
Schedule health checks in natural language. "Check GPU every 6h" just works.
Team Workspaces
Shared investigations, team skills, and a web experience for collaboration.
Integrations
Connects to your stack
Built-in channels and Kubernetes. Extend to anything via Model Context Protocol.
Get Started