Infrastructure●●●Banger
RunbookAI – Hypothesis-driven incident investigation agent(open source)
Hypothesis-pruning incident agent with approval gates beats chaos engineering explorers.
Solve My ProblemWizardry
EmTekker
203mo ago
Back to browse
GitHub Repository
Claude Code SRE Handbook
11 starsPython
K8s watcher that investigates incidents and opens PRs (it can't merge)
by har-ki·Jun 16, 2026·2 points·0 comments
AI Analysis
●MidNiche GemShip It
Reference implementation for AI SRE workflows, but it's a blog example not a deployable tool.
Strengths
- •Broken K8s manifest scenarios provide concrete test cases for AI SRE workflows.
- •Benchmark runner outputs JSONL data for measuring AI incident response performance.
- •OTEL + ClickHouse demo setup is genuinely useful for observability testing.
Weaknesses
- •Watcher is reference code for a blog post, not a packaged tool you can install.
- •No clear deployment path — requires significant adaptation to use in production.
Category
Target Audience
SREs and platform engineers exploring AI-assisted incident response
Similar Projects
Developer Tools●Mid
Spinal – Prod aware code review and validation
Another code review tool claiming to catch slop, competing with CodeRabbit and Cursor.
Bold Bet
mahendraroopa
101mo ago
AI/ML●Mid
Devin AI can automatically triage issues
Auto-triage is a classic sales demo feature wrapped in a proprietary black box.
Slick
limelight
401mo ago
Infrastructure●●Solid
RunbookAI – Stop scrolling dashboards at 3 a.m., let AI investigate
The project converts on-call triage into a hypothesis-driven agent that forms and prunes hypotheses, fetches evidence from CloudWatch/Kubernetes and your runbooks, and surfaces an investigation plus approval-gated remediation steps. I like the npx demo, read-only-by-default K8s stance, and built-in audit trail; the obvious caveat is its dependence on proprietary LLM keys and the ops work needed before trusting any mutating actions in production.
Solve My ProblemNiche GemWizardry
EmTekker
104mo ago
Developer Tools●●●Banger
Tmppr – local PR review for AI coding agents
Local-first agent coordination with PR workflows keeps code on 127.0.0.1.
Zero to OneBig BrainSolve My Problem
douglaswlance
205d ago
Developer Tools●●Solid
Nightwatch, The open-source, read-only AI SRE
Read-only AI agent architecture prevents production accidents during incident response.
Big BrainShip It
egorferber
331015d ago