cyanxxy/Open OCR CLI

Extract text or structured data from images and PDFs in GitHub Actions.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
inputsNewline-separated files, directories, or globs to extract.yes
providergemini, kimi, muse, openrouter, or openai-compatible.gemini
modelOptional provider model ID.no
api-key-envOptional environment-variable name containing the provider credential.no
base-urlOptional base URL for preview or OpenAI-compatible providers.no
gatewaydirect or cloudflare.direct
cloudflare-account-idOptional Cloudflare account ID; defaults to CLOUDFLARE_ACCOUNT_ID.no
cloudflare-gateway-idOptional AI Gateway ID; defaults to CLOUDFLARE_AI_GATEWAY_ID.no
cloudflare-providerOptional Cloudflare custom-provider slug for Kimi, Muse, or compatible APIs.no
cloudflare-token-envEnvironment-variable name containing the token for an authenticated AI Gateway.CLOUDFLARE_AI_GATEWAY_TOKEN
cloudflare-byokUse a provider credential stored by Cloudflare AI Gateway.false
cloudflare-byok-aliasOptional Cloudflare stored-key alias.no
modesimple, template, or agentic.simple
presetOptional structured extraction preset.no
formatmarkdown, json, csv, or all.markdown
outputOutput file or directory.gemini-ocr-output
versionopen-ocr-cli npm version to execute.latest
dry-runValidate inputs and planned outputs without credentials, requests, or writes.false

no outputs