maxuver

maxuver/sentinelops

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

2 stars 0 forks 2 watchers Python GNU Affero General Public License v3.0
aiops devops fastapi incident-response kubernetes llm observability platform-engineering prometheus sre
View on GitHub
6 Open Issues Need Help Last updated: Sep 14, 2026

Open Issues Need Help

View All on GitHub
Docs: a runbook example that the agent indexes into memory 8 days ago
good first issue
maxuver/sentinelops
2

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

Python
#aiops#devops#fastapi#incident-response#kubernetes#llm#observability#platform-engineering#prometheus#sre
Web UI: filter incidents by engineer verdict 8 days ago
good first issue
maxuver/sentinelops
2

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

Python
#aiops#devops#fastapi#incident-response#kubernetes#llm#observability#platform-engineering#prometheus#sre
Notifier: Discord via webhook 8 days ago
good first issue notifier
maxuver/sentinelops
2

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

Python
#aiops#devops#fastapi#incident-response#kubernetes#llm#observability#platform-engineering#prometheus#sre
Collector: Kubernetes node conditions in the reflex path 8 days ago
help wanted collector
maxuver/sentinelops
2

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

Python
#aiops#devops#fastapi#incident-response#kubernetes#llm#observability#platform-engineering#prometheus#sre
Scenario: liveness probe failing because of a slow dependency, not the app 8 days ago
good first issue scenario
maxuver/sentinelops
2

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

Python
#aiops#devops#fastapi#incident-response#kubernetes#llm#observability#platform-engineering#prometheus#sre
Scenario: CrashLoop caused by a wrong image tag after a rollout 8 days ago
good first issue scenario
maxuver/sentinelops
2

AI-assisted incident triage for Kubernetes — turns raw Alertmanager alerts into pre-investigated incidents (Loki + Prometheus + K8s context → LLM root-cause hypothesis).

Python
#aiops#devops#fastapi#incident-response#kubernetes#llm#observability#platform-engineering#prometheus#sre