jalapenolabs/Self Repair

Automatically diagnose and repair CI failures using LLM agents

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
errorError message to diagnose. If omitted, the action automatically fetches failed step logs from the current workflow run via the GitHub API. no""
engineLLM engine (claude or codex)claude
modelModel identifier to pass to the engine (e.g. claude-sonnet-4-6). Falls back to engine default.no""
repoGitHub repository (owner/repo)${{ github.repository }}
claude-api-tokenAnthropic API key (required when engine is claude)no
openai-api-tokenOpenAI API key (required when engine is codex)no
github-tokenGitHub token for creating issues and PRs${{ github.token }}
max-turnsMaximum conversation turns per engine invocation50
verboseEnable verbose logging of prompts and engine outputfalse
versionVersion of self-repair to use (e.g. "0.2.0", "latest")latest

no outputs