natmart/AgentQA

Autonomous QA Engineer - AI-powered test generation, execution, and self-healing

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Maintainedlast commit Jan 28, 2026
License
MIT

Pinned Snippet

workflow.ymlSHA-pinned
uses: natmart/agentqa@fecec0edd3db5babba0f6e4dcc895cfe74fd365e # no releases — HEAD as of 2026-07-11

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
pathPath to scan for untested codeno./src
frameworkTest framework (jest, vitest, pytest)novitest
openai-api-keyOpenAI API key for AI test generationyes
github-tokenGitHub token for posting PR commentsno${{ github.token }}
max-retriesMaximum healing retries per test (1-5)no3
dry-runRun without writing files (preview mode)nofalse
auto-commitAutomatically commit generated testsnotrue
coverage-thresholdFail if coverage drops below this percentageno""
limitMaximum number of files to processno""
modelOpenAI model to use (gpt-4, gpt-4o, gpt-3.5-turbo)nogpt-4o
verboseEnable verbose loggingnofalse
post-commentPost results as PR commentnotrue
namedescription
coverage-beforeCoverage percentage before test generation
coverage-afterCoverage percentage after test generation
coverage-diffCoverage difference (positive = improvement)
tests-generatedNumber of tests generated
tests-healedNumber of tests that required healing
healing-success-ratePercentage of failed tests successfully healed
summarySummary of AgentQA run in markdown format