[!NOTE]
open-ocr-cli is the current executable and npm package; the earlier
gemini-ocr executable and config paths still work. This repository also
hosts the original Gemini web app — provider-neutral
support applies to the CLI.

Quick start

Requires Node.js 20.19+, 22.13+, or 24+ and one provider key
(--dry-run needs none).

npm install --global open-ocr-cli

export GEMINI_API_KEY="your-key"
open-ocr-cli extract invoice.pdf

Switch providers with a flag:

open-ocr-cli extract invoice.pdf --provider kimi          # MOONSHOT_API_KEY
open-ocr-cli extract invoice.pdf --provider openrouter \
  --model moonshotai/kimi-k3                              # OPENROUTER_API_KEY

Keys are read only from the environment or a project .env — never from a flag
or config file. With no arguments the CLI prints help and never prompts, so
scripts and CI stay deterministic; interactive, init, and doctor cover the
guided paths.

Also available as a Docker image
(ghcr.io/cyanxxy/open-ocr-cli), a GitHub Action
(cyanxxy/open-ocr-cli@v2), and a Homebrew formula.

Extraction modes

Schemas are validated locally — both the schema and the model's returned value —
before anything is written. Invalid JSON or a schema mismatch is never persisted
as a success.

Agentic mode uses a two-loop design: an outer document loop evaluates confidence
and coverage, while an inner loop lets the model call one tool (structure
analysis, batch field extraction, region re-OCR), inspect the result, and decide
what to do next. The document is sent once.

Commands

# Recursive, resumable batch
open-ocr-cli extract ./documents --output ./results --concurrency 4 --resume

# Structured invoice artifacts (markdown + JSON + CSV)
open-ocr-cli extract ./invoices --preset invoice --format all --output ./invoice-results

# Validate the full plan without credentials, API calls, or writes
open-ocr-cli extract ./documents --dry-run

Extracted content and JSONL events go to stdout; progress and diagnostics go
to stderr — every command composes safely in a pipeline.

Flags, configuration keys, batch semantics, cost controls, and exit codes:
packages/cli/README.md

Agents and MCP

Three entry points wrap the same job engine.

Machine protocol — run executes a versioned request (v2 current, v1 still
supported) validated against published Draft 2020-12 JSON Schemas, returning a
typed result object or an ordered JSONL event stream with stable sequence
numbers and typed error codes carrying recovery hints:

open-ocr-cli capabilities --json
open-ocr-cli run --request request.json --response-format jsonl

MCP server — open-ocr-cli mcp starts a stdio server exposing
ocr_extract, ocr_run_agentic, and ocr_web, plus an
open-ocr://capabilities resource:

{
  "mcpServers": {
    "open-ocr": {
      "command": "open-ocr-cli",
      "args": ["mcp"]
    }
  }
}

Agent skill — a validated skill for Claude Code, Codex, and compatible
agents ships at
integrations/open-ocr/skills/open-ocr/SKILL.md
and in the npm package under skills/open-ocr/.

All three are reference-first: large bodies land in .open-ocr-results/<runId>
artifacts instead of flooding an agent's context, cancellation is honored, and
under mcp stdout carries only transport messages.

Providers

Named profiles supply endpoints, credential variable names, and multimodal wire
formats; openrouter and openai-compatible take arbitrary upstream model IDs.
Any provider can also run through Cloudflare AI Gateway with --gateway cloudflare, including BYOK.

Model catalogs, reasoning levels, cost estimates, and gateway configuration are
documented in the CLI reference.

Limits and guarantees

Every discovered input gets a succeeded, partial, failed, or skipped result —
no silent loss. Batches are fingerprinted and resumable, output is lock-guarded
and no-clobber, and truncated, blocked, or schema-invalid model responses fail
closed rather than being written as success.

There is no backend and no telemetry: documents go to the selected provider or
gateway and nowhere else. Web OCR rejects credentials in URLs, localhost,
private ranges, and tunnel hosts, and pins DNS across redirects. Report
vulnerabilities privately via SECURITY.md.

Web application

The repository also contains the original Gemini-powered React app with the same
five workflows and light/dark/AMOLED themes:

npm ci && npm run dev   # http://localhost:5173 — add your key under Settings

[!IMPORTANT]
The browser stores the API key in localStorage with light obfuscation, not
strong encryption. Anyone with access to that browser profile can recover it.
Prefer a backend proxy for organization-owned credentials.

Repository layout

One repository, three entry points over a shared extraction engine:

open-ocr-cli mcp is not a separate package — it is a third front end inside
the CLI, alongside extract (human-facing) and run (versioned protocol), all
routed through the same job service.

The CLI is typechecked without DOM libraries on purpose, so a browser API cannot
reach it through the shared engine.

Contributing

Setup, PR gates, and release steps are in CONTRIBUTING.md.
Behavior changes need tests or evaluation evidence; the evaluation suite is
documented in evals/README.md.