Skip to main content

OCR Reader Pack

★Trusted◇Sandbox optionalv1.0.0MITUnverified

by AgentNode · published 6 months ago · toolpack

Extract text from images and scanned documents using OCR.

Optical character recognition for images, screenshots, and scanned PDFs. Supports 100+ languages via Tesseract and EasyOCR.

langchaincrewaigeneric

Quick Start

bash
agentnode install ocr-reader-pack

Runs in a subprocess with filtered environment by default. Declared permissions are policy-checked, not sandboxed.

Usage

From package
python
from ocr_reader_pack.tool import run

result = run(
    action="ocr_read",
    image_path="/tmp/invoice-scan-march.png",
    language="eng",
    output_format="text"
)

print("Extracted text:")
print(result["text"])
print(f"\nConfidence: {result['confidence']:.1%}")
print(f"Words detected: {result['word_count']}")
print(f"Language: {result['detected_language']}")

Runs locally on your machine. No execution data is sent to AgentNode. Permissions are checked before execution. Learn how this works

Verification

low confidence30/100Unverified
smokeSmoke test failed
0/25
testsTests failed
0/15
importAll tools imported successfully
+15/15
installInstalled in 1.8s
+15/15
contractContract not validated
0/10
determinismNo determinism data
0/5
reliabilityNo stability data
0/10

Package installs and imports correctly.

✔install1.8s
✔import60ms
✖smoke148ms
✖tests1.2s

This package scored below the verification threshold. Some checks may have failed or produced inconclusive results.

Verified in cases_real mode

Python 3.12.3ffmpegpopplertesseractuv

Last verified 11d ago· Runner v2.0.0

Use this when you need to...

  • ›Extract text from scanned invoices and receipts for bookkeeping
  • ›Digitize handwritten notes from whiteboard photos
  • ›Read text overlays and captions from screenshot images
  • ›Convert scanned legal documents into searchable plain text
  • ›Extract multilingual text from product labels and packaging photos

README

Version History

v1.0.0latestverified
3/16/2026

Capabilities

ocr_readingocr_readtool

Input Schema

{
  "type": "object",
  "required": [
    "image_path"
  ],
  "properties": {
    "language": {
      "type": "string",
      "default": "eng"
    },
    "image_path": {
      "type": "string",
      "default": "/tmp/agentnode_verify/test.png",
      "description": "Path to the image file"
    },
    "output_format": {
      "type": "string",
      "default": "text"
    }
  }
}

Permissions

◇Sandbox optionalFrom a trusted publisher — runs on the host by default. You can require isolation with sandbox.host_trust_policy.

Declared by the publisher. Checked before execution by the policy gate.

Networknone
Filesystemtemp
Code Executionnone
Data Accessinput_only
User Approvalnever

Permissions are policy-checked before execution. For trusted and curated packages that run on the host, network and filesystem access are policy-checked but not OS-sandboxed. When runtime isolation is required for untrusted/community code, AgentNode uses sandbox-or-fail-closed if the required container runtime and pinned image are available. Learn more

Privacy

All tool execution happens locally on your machine. AgentNode never receives:

  • • Tool inputs or outputs
  • • Execution logs
  • • Data your agent processes

Only install events and search queries are sent to the registry.

bash
agentnode install ocr-reader-pack

Files (3)

License

MIT

Stats

Downloads0
Installs0
Versionv1.0.0
Published3/16/2026
Channelstable
Typetoolpack
Entrypointocr_reader_pack.tool

Compatibility

Frameworks

langchaincrewaigeneric

Runtime

python

Python Version

>=3.10

Trust & Security

Publisher★Trusted
SignatureNone
ProvenanceNone
Security Issues0

Publisher

A

AgentNode

@agentnode

Report an issue with this package