vignesh07/claude-on-call

AI-powered on-call agent that responds to production alerts with analysis and fixes

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
anthropic_api_keyAnthropic API key for Claudeyes
alert_payloadJSON alert payload from webhookyes
alert_sourceSource of alert (pagerduty, datadog, cloudwatch, sentry, opsgenie, prometheus, generic, auto)noauto
modeOperation mode: pr = attempt fix, analyze = comment only, auto = decide based on context, review = respond to PR commentsnoauto
create_issueCreate GitHub issue to track the alertnotrue
pagerduty_api_keyPagerDuty API key for updating incidents (optional)no
confidence_thresholdMinimum confidence to create PR (high, medium, low)nomedium
timeout_minutesMaximum time for Claude to work (minutes)no10
max_files_changedMaximum number of files Claude can modify in a fixno10
draft_prCreate pull requests as draftsnotrue
test_commandCommand to run tests (e.g., npm test, pytest). If set, Claude will run tests and fix failures.no
pr_numberPR number to respond to (for review mode)no
comment_bodyComment body to respond to (for review mode)no
comment_idComment ID for threading responses (for review mode)no
namedescription
action_takenWhat the agent did: pr_created, analysis_only, duplicate, error
pr_numberPull request number if created
issue_numberGitHub issue number for tracking
analysisAgent analysis summary
confidenceAgent confidence in the fix: high, medium, low
duplicate_ofIssue number if this alert was detected as a duplicate