kming-l/LyingDocs

Documentation-code misalignment detection. A trust layer for your repository.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
doc-pathPath to documentation root directory (relative to repo root)yesdocs
code-pathPath to code repository root (relative to repo root)no.
configPath to lyingdocs.toml config file (optional)no""
backendArgus backend: local, claude_code, or codexnolocal
hermes-providerLLM provider for Hermes agent: openai or anthropic. Auto-set to 'anthropic' when backend is claude_code.no""
argus-providerLLM provider for Argus local backend: openai or anthropicno""
hermes-modelLLM model for Hermes agentno""
hermes-base-urlAPI base URL for Hermes agentno""
argus-modelLLM model for Argus agentno""
argus-base-urlAPI base URL for Argus agentno""
openai-api-keyOpenAI API key (for local/codex backends)no""
anthropic-api-keyAnthropic API key (for claude_code backend, billed per API usage)no""
claude-oauth-tokenClaude Code OAuth token (for claude_code backend, uses Pro/Max subscription quota). Generate with: claude setup-tokenno""
max-dispatchesMaximum number of Argus dispatchesno""
max-iterationsMaximum Hermes loop iterationsno""
gen-issueGenerate GitHub issue drafts from findings (true/false)nofalse
comment-on-prPost findings as a PR comment (true/false)notrue
python-versionPython version to useno3.12
namedescription
report-pathPath to the generated Misalignment Report
findings-countNumber of misalignment findings
has-findingsWhether any misalignments were found (true/false)