How should Fake_vs_Real_OCR be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

Fake_vs_Real_OCR answer-first brief

Fake news detection system combining Azure OCR with a multi-agent CrewAI fact-checking pipeline and Serper web search, served via Streamlit. 📰 Fake vs Real OCR - AI-Powered Fake News Detection $1 $1 $1 $1 $1 **Fake vs Real OCR** is an AI-powered fake news detection system that combines OCR (Optical Character Recognition) with multi-agent AI verification using CrewAI. Users upload news images or enter text claims, and the system extracts text via Azure Document Intelligence, then runs a four-agent verification crew with real-time web search to produce a d Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

Fake_vs_Real_OCR is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB REPOS, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGITHUB REPOSSafety: 66/100

Fake_vs_Real_OCR

OpenClawself-declared

Public facts

Change events

Artifacts

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Marwanabdellah

Artifacts

Benchmarks

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

View Source

Setup snapshot

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Marwanabdellah

profilemedium

Observed Oct 9, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium

Observed Oct 9, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB REPOS

Extracted files

Examples

Snippets

Languages

python

Executable Examples

mermaid

graph TD
    A[News Claim Text / Uploaded Image] --> B[Azure Document Intelligence OCR]
    B --> C[Collector Agent - Serper Web Search]
    C --> D[Fact Checker Agent]
    D --> E[Classifier Agent]
    E --> F[Validation Agent]
    F --> G[Verification Report + Evidence + Confidence]

bash

git clone https://github.com/MarwanAbdellah/Fake_vs_Real_OCR.git
cd Fake_vs_Real_OCR

bash

pip install uv
uv sync

bash

cp .env.example .env

env

MODEL=azure/gpt-4.1
AZURE_API_BASE=https://your-resource.openai.azure.com
AZURE_OPENAI_API_KEY=your-azure-openai-api-key
SERPER_API_KEY=your-serper-api-key
AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT=https://your-resource.cognitiveservices.azure.com/
AZURE_DOCUMENT_INTELLIGENCE_KEY=your-document-intelligence-key

bash

# Streamlit web interface
streamlit run app.py

# CLI (crewai)
crewai run

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

Full README

📰 Fake vs Real OCR - AI-Powered Fake News Detection

Fake vs Real OCR is an AI-powered fake news detection system that combines OCR (Optical Character Recognition) with multi-agent AI verification using CrewAI. Users upload news images or enter text claims, and the system extracts text via Azure Document Intelligence, then runs a four-agent verification crew with real-time web search to produce a detailed fact-checking report.

✨ Key Features

🎯 1. OCR Text Extraction

Extracts text from uploaded news images (PNG / JPG / JPEG) using Azure Document Intelligence (prebuilt-read).
OCR text becomes the primary, locked claim source for verification.

⚡ 2. Multi-Agent Verification Crew

Collector Agent: gathers information and evidence via web search.
Fact Checker Agent: verifies claims against reliable sources.
Classifier Agent: analyzes and categorizes the information.
Validation Agent: final validation and report generation (news_verification_report.md).

🔍 3. Real-Time Web Search Integration

Live web search using the Serper API (SerperDevTool) to collect up-to-date evidence.

📊 4. Streamlit Interface & Detailed Reports

User-friendly Streamlit web app with typewriter result display and live pipeline status.
CLI entry point (crewai run) for headless verification with optional image input.

🏗️ System Architecture

graph TD
    A[News Claim Text / Uploaded Image] --> B[Azure Document Intelligence OCR]
    B --> C[Collector Agent - Serper Web Search]
    C --> D[Fact Checker Agent]
    D --> E[Classifier Agent]
    E --> F[Validation Agent]
    F --> G[Verification Report + Evidence + Confidence]

🛠️ Technology Stack

Backend / Core

Language: Python 3.10 – 3.13
Agent Framework: CrewAI 0.157 (sequential process)
LLM: Azure OpenAI GPT-4.1 (MODEL=azure/gpt-4.1)

Data & Processing

OCR: Azure Document Intelligence (prebuilt-read)
Web Search: Serper API (SerperDevTool)
Images: Pillow

Frontend / Interface

Web UI: Streamlit (primary), Gradio (in dependencies)
Package Management: uv / pip (hatchling build)

🚀 Getting Started

Prerequisites

Python 3.10 or higher (less than 3.14)
Azure account with:
- Azure OpenAI Service resource
- Azure Document Intelligence resource
Serper API key (for web search functionality)

1. Repository Setup

git clone https://github.com/MarwanAbdellah/Fake_vs_Real_OCR.git
cd Fake_vs_Real_OCR

2. Install Dependencies

pip install uv
uv sync

3. Configure Environment

Copy the example environment file and add your API keys:

cp .env.example .env

MODEL=azure/gpt-4.1
AZURE_API_BASE=https://your-resource.openai.azure.com
AZURE_OPENAI_API_KEY=your-azure-openai-api-key
SERPER_API_KEY=your-serper-api-key
AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT=https://your-resource.cognitiveservices.azure.com/
AZURE_DOCUMENT_INTELLIGENCE_KEY=your-document-intelligence-key

4. Run

# Streamlit web interface
streamlit run app.py

# CLI (crewai)
crewai run

🧪 Testing & Verification

There are no unit tests in this repository. Verify the system by:

Launching streamlit run app.py and uploading a news image or entering a text claim.
Confirming OCR text is extracted from uploaded images and shown in the UI.
Checking that the crew writes its final output to news_verification_report.md.

📁 Project Structure

Fake_vs_Real_OCR/
├── app.py                          # Streamlit web application
├── ocr_helper.py                   # Azure Document Intelligence OCR helper
├── .env.example                    # Environment variable template
├── pyproject.toml                  # Project configuration and dependencies
├── news_verification_report.md     # Generated verification report output
├── src/web_searching_crew/
│   ├── crew.py                     # CrewAI agent definitions
│   ├── main.py                     # CLI entry point
│   ├── config/
│   │   ├── agents.yaml             # Agent configurations
│   │   └── tasks.yaml              # Task definitions
│   └── tools/
│       └── custom_tool.py          # Custom tools
└── knowledge/
    └── user_preference.txt         # User preferences

👤 Author

Marwan Abdellah

GitHub: @MarwanAbdellah
LinkedIn: Marwan Abdellah

📄 License

Distributed under the MIT License. See LICENSE for more information.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB REPOS

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/snapshot"

curl -s "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/contract"

curl -s "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

Github ReposUpdated 0h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T19:24:43.259Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Marwanabdellah",
    "href": "https://github.com/MarwanAbdellah/Fake_vs_Real_OCR",
    "sourceUrl": "https://github.com/MarwanAbdellah/Fake_vs_Real_OCR",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T03:20:45.821Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T03:20:45.821Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-marwanabdellah-fake-vs-real-ocr/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]