{"id":"6b836b0c-6c90-41a7-8c26-254ec808bde5","entityType":"agent","slug":"crewai-shivamchauhan18-ai-document-organizer-agent","name":"AI_DOCUMENT_ORGANIZER_AGENT","canonicalUrl":"https://www.xpersona.co/agent/crewai-shivamchauhan18-ai-document-organizer-agent","canonicalPath":"/agent/crewai-shivamchauhan18-ai-document-organizer-agent","generatedAt":"2026-10-10T01:28:21.177Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T14:52:36.822Z","emptyReason":null},"description":"An AI-powered multi-agent document classification and organization system that automatically scans, classifies, validates, and organizes documents using CrewAI, Python, Flask, and a real-time web dashboard. DocFlow AI — Intelligent Multi-Agent Document Organizer **DocFlow AI** is an autonomous multi-agent document classification and organization pipeline powered by **$1**, **$1**, **$1**, and **$1**. It recursively scans any input folder, extracts text and layout information using hybrid OCR / document parser pipelines, and runs a 4-agent sequential workflow to classify, validate, update category taxonomies, and organiz","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/shivamchauhan18/AI_DOCUMENT_ORGANIZER_AGENT","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/shivamchauhan18/AI_DOCUMENT_ORGANIZER_AGENT","kind":"source"}],"safetyScore":66,"overallRank":22.2,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"An AI-powered multi-agent document classification and organization system that automatically scans, classifies, validates, and organizes documents using CrewAI,"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T14:52:36.822Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"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"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T14:52:36.822Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T14:52:36.817Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T14:52:36.822Z","lastCrawledAt":"2026-10-09T14:52:36.817Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T14:52:36.817Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T01:28:21.177Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-shivamchauhan18-ai-document-organizer-agent/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T14:52:36.822Z","emptyReason":null},"readme":"# DocFlow AI — Intelligent Multi-Agent Document Organizer\n\n**DocFlow AI** is an autonomous multi-agent document classification and organization pipeline powered by **[CrewAI](https://www.crewai.com/)**, **[Docling](https://github.com/DS4SD/docling)**, **[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)**, and **[Flask](https://flask.palletsprojects.com/)**.\n\nIt recursively scans any input folder, extracts text and layout information using hybrid OCR / document parser pipelines, and runs a 4-agent sequential workflow to classify, validate, update category taxonomies, and organize documents into categorized destination directories safely without modifying source files.\n\n---\n\n## 🌟 Key Features\n\n- **Autonomous 4-Agent Pipeline**: Specialized CrewAI agents handle document classification, independent validation, taxonomy lifecycle management, and file organization.\n- **Hybrid Document Extraction Engine**:\n  - **PaddleOCR + PyMuPDF** for OCR processing of PDF files.\n  - **Docling** for deep structure extraction across Word, Excel, PowerPoint, Text, and image documents.\n- **Dynamic Taxonomy Management**: Reuses existing categories when appropriate while creating new categories only when genuinely necessary to avoid duplicate or synonymous folders.\n- **Modern Web Dashboard & Real-Time Console**:\n  - Built-in Flask dashboard with live step-by-step agent tracking via the CrewAI Event Bus.\n  - Native GUI folder selection dialogs.\n  - Live execution streaming console and organized output file explorer.\n- **CLI & Batch Support**: Fully functional command-line interface for headless execution and automated workflows.\n- **Non-Destructive File Organization**: Safely copies documents into categorized folders with automated conflict resolution (`filename_1.ext`).\n\n---\n\n## 📂 Supported File Types\n\n| Category | File Extensions | Extraction Engine |\n|---|---|---|\n| **PDF Documents** | `.pdf` | PyMuPDF + PaddleOCR |\n| **Word Documents** | `.docx`, `.doc` | Docling / python-docx |\n| **Spreadsheets** | `.xlsx`, `.xls` | Docling / openpyxl |\n| **Presentations** | `.pptx`, `.ppt` | Docling / python-pptx |\n| **Plain Text** | `.txt` | Docling |\n| **Images** | `.png`, `.jpg`, `.jpeg` | Docling / Pillow |\n\n---\n\n## 🤖 Multi-Agent Architecture\n\n```\n                                  ┌───────────────────────────────┐\n                                  │   Input Folder (Documents)    │\n                                  └──────────────┬────────────────┘\n                                                 │\n                                                 ▼\n┌─────────────────────────────────────────────────────────────────────────────────────────────────┐\n│                                   CREWAI AGENT PIPELINE                                         │\n│                                                                                                 │\n│  [1. Classifier Agent]  ──►  [2. Validator Agent]  ──►  [3. Category Manager]  ──► [4. Organizer]│\n│  - Extracts 1st page        - Validates accuracy        - Updates taxonomy          - Copies to  │\n│  - Proposes category        - Checks duplicates         - Prevents taxonomy         destination │\n│  - Calculates confidence    - Flags new category          bloat (categories.json)     subfolder │\n└────────────────────────────────────────────────┬────────────────────────────────────────────────┘\n                                                 │\n                                                 ▼\n                                  ┌───────────────────────────────┐\n                                  │  Output / <Category> / Files  │\n                                  └───────────────────────────────┘\n```\n\n1. **Document Classification Specialist (`document_classifier`)**\n   Extracts content from the first page of the document, inspects the current category taxonomy, and proposes a representative category along with a confidence score and rationale.\n2. **Document Classification Validator (`classification_validator`)**\n   Independently audits the proposed category against document evidence and taxonomy to prevent duplicates, synonyms, or overly granular classifications.\n3. **Document Taxonomy Manager (`category_manager`)**\n   Applies approved categories. If the category is new, it persists it into `categories.json` for future document batches.\n4. **Document Organization Specialist (`document_organizer`)**\n   Creates the target category folder in the destination path and securely copies the document without modifying the original.\n\n---\n\n## 📋 Prerequisites & System Requirements\n\n- **Operating System**: Linux, macOS, or Windows (Linux recommended)\n- **Python**: `3.10` to `3.13`\n- **Ollama**: Required for running the local/cloud LLM backend (default model: `ollama/gemma4:cloud`).\n- **Zenity** *(Linux Web UI only)*: Required for the native desktop folder picker dialog.\n  ```bash\n  sudo apt install zenity\n  ```\n\n---\n\n## 🚀 Installation\n\n### 1. Clone or Open the Repository\n```bash\ncd DOC_CLASSIFIER\n```\n\n### 2. Create and Activate a Virtual Environment\n```bash\npython3 -m venv .venv\nsource .venv/bin/activate\n```\n\n### 3. Install Dependencies\n```bash\npip install -r requirements.txt\n```\n\n### 4. Configure Environment Variables\nCreate or verify your `.env` file in the root directory:\n```env\nMODEL=ollama/gemma4:cloud\nAPI_BASE=http://localhost:11434\nCREWAI_TRACING_ENABLED=true\n```\n\nEnsure Ollama is running and accessible at `http://localhost:11434`.\n\n---\n\n## 💻 How to Run\n\n### Method 1: Web UI Dashboard (Recommended)\n\nStart the Flask web application:\n```bash\npython3 app.py\n```\n\nThen open your browser at:\n```\nhttp://127.0.0.1:5000\n```\n\n1. Click **Select Folder** for **Step 01 (Source Documents)** to pick your input folder.\n2. Click **Select Folder** for **Step 02 (Destination Folder)** to choose where organized files should go.\n3. Click **Start Organization**.\n4. Monitor the real-time agent execution pipeline, live console output, and browse the resulting organized folders in the UI.\n\n---\n\n### Method 2: Command Line Interface (CLI)\n\nRun the backend pipeline directly on any folder:\n\n```bash\n# Basic run (default output directory: ./output)\npython3 backend/main.py /path/to/input-folder\n\n# Specify custom output destination\npython3 backend/main.py /path/to/input-folder -o /path/to/output-folder\n```\n\n---\n\n## 📁 Project Structure\n\n```\nDOC_CLASSIFIER/\n├── app.py                      # Flask web server & GUI orchestration\n├── requirements.txt            # Python package dependencies\n├── .env                        # Environment configuration (LLM model & API base)\n├── backend/\n│   ├── main.py                 # CLI entrypoint & CrewAI event bus orchestrator\n│   ├── crew.jsonc              # CrewAI sequential workflow configuration\n│   ├── models.py               # Pydantic schemas for structured agent outputs\n│   ├── pyproject.toml          # Project package definitions\n│   ├── agents/                 # Agent prompt definitions\n│   │   ├── category_manager.jsonc\n│   │   ├── classification_validator.jsonc\n│   │   ├── document_classifier.jsonc\n│   │   └── document_organizer.jsonc\n│   ├── tools/                  # Custom CrewAI tools\n│   │   ├── add_document_category.py\n│   │   ├── category_store.py\n│   │   ├── document_extractor.py\n│   │   ├── document_organizer.py\n│   │   ├── document_scanner.py\n│   │   └── get_document_categories.py\n│   ├── knowledge/              # Agent knowledge store\n│   │   └── user_preference.txt\n│   ├── input/                  # Sample / default input directory\n│   └── data_folder/\n│       └── categories.json     # Dynamic category taxonomy storage\n├── frontend/                   # Web Dashboard Assets\n│   ├── index.html              # Dashboard UI markup\n│   ├── style.css               # Styling & responsive layout\n│   └── app.js                  # Frontend state management & polling logic\n└── output/                     # Default organized output destination\n```\n\n---\n\n## ⚙️ Configuration & Customization\n\n- **Change LLM Model**: Update `MODEL` in `.env` (e.g. `ollama/llama3.2`, `ollama/mistral`, etc.) and ensure the corresponding agent definitions in `backend/agents/*.jsonc` point to your desired model.\n- **Initial Taxonomy**: Pre-populate initial categories by editing `backend/data_folder/categories.json`.\n- **Supported Formats**: Add or adjust recognized file extensions in `backend/tools/document_scanner.py`.\n\n---\n\n## 📄 License\n\nThis project is licensed under the MIT License.\n","readmeExcerpt":"DocFlow AI — Intelligent Multi-Agent Document Organizer **DocFlow AI** is an autonomous multi-agent document classification and organization pipeline powered by **$1**, **$1**, **$1**, and **$1**. It recursively scans any input folder, extracts text and layout information using hybrid OCR / document parser pipelines, and runs a 4-agent sequential workflow to classify, validate, update category taxonomies, and organiz","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"┌───────────────────────────────┐\n                                  │   Input Folder (Documents)    │\n                                  └──────────────┬────────────────┘\n                                                 │\n                                                 ▼\n┌─────────────────────────────────────────────────────────────────────────────────────────────────┐\n│                                   CREWAI AGENT PIPELINE                                         │\n│                                                                                                 │\n│  [1. Classifier Agent]  ──►  [2. Validator Agent]  ──►  [3. Category Manager]  ──► [4. Organizer]│\n│  - Extracts 1st page        - Validates accuracy        - Updates taxonomy          - Copies to  │\n│  - Proposes category        - Checks duplicates         - Prevents taxonomy         destination │\n│  - Calculates confidence    - Flags new category          bloat (categories.json)     subfolder │\n└────────────────────────────────────────────────┬────────────────────────────────────────────────┘\n                                                 │\n                                                 ▼\n                                  ┌───────────────────────────────┐\n                                  │  Output / <Category> / Files  │\n                                  └───────────────────────────────┘"},{"language":"bash","snippet":"sudo apt install zenity"},{"language":"bash","snippet":"cd DOC_CLASSIFIER"},{"language":"bash","snippet":"python3 -m venv .venv\nsource .venv/bin/activate"},{"language":"bash","snippet":"pip install -r requirements.txt"},{"language":"env","snippet":"MODEL=ollama/gemma4:cloud\nAPI_BASE=http://localhost:11434\nCREWAI_TRACING_ENABLED=true"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"An AI-powered multi-agent document classification and organization system that automatically scans, classifies, validates, and organizes documents using CrewAI, Python, Flask, and a real-time web dashboard. DocFlow AI — Intelligent Multi-Agent Document Organizer **DocFlow AI** is an autonomous multi-agent document classification and organization pipeline powered by **$1**, **$1**, **$1**, and **$1**. It recursively scans any input folder, extracts text and layout information using hybrid OCR / document parser pipelines, and runs a 4-agent sequential workflow to classify, validate, update category taxonomies, and organiz","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":404,"uniquenessScore":63,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T14:52:36.822Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T14:52:36.822Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T01:28:21.177Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"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!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"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","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}