{"data":{"node":{"slug":"unstructured-io-unstructured","name":"unstructured","tagline":"Convert documents to structured data effortlessly","github_url":"https://github.com/Unstructured-IO/unstructured","owner":"Unstructured-IO","repo":"unstructured","owner_avatar_url":"https://avatars.githubusercontent.com/u/108372208?v=4","primary_language":"HTML","stars":15238,"forks":1284,"topics":["data-pipelines","deep-learning","document-image-analysis","document-image-processing","document-parser","document-parsing","docx","donut","information-retrieval","langchain","llm","machine-learning","ml","natural-language-processing","nlp","ocr","pdf","pdf-to-json","pdf-to-text","preprocessing"],"archived":false,"github_pushed_at":"2026-07-31T20:54:17+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/unstructured-io-unstructured","markdown_url":"https://www.graphcanon.com/tools/unstructured-io-unstructured.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/unstructured-io-unstructured","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=unstructured-io-unstructured"},"categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"data-pipelines","name":"data-pipelines"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"document-parser","name":"document-parser"},{"slug":"document-processing","name":"document-processing"},{"slug":"information-retrieval","name":"information-retrieval"},{"slug":"langchain","name":"langchain"},{"slug":"llm","name":"llm"},{"slug":"natural-language-processing","name":"natural-language-processing"}],"edges":[{"type":"related","direction":"out","explanation":null,"successor_context":null,"tool":{"slug":"run-llama-llama-index","name":"llama_index","tagline":"Leading document agent and OCR platform","github_url":"https://github.com/run-llama/llama_index","owner":"run-llama","repo":"llama_index","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"Python","stars":51442,"forks":7885,"topics":["agents","application","data","fine-tuning","framework","llamaindex","llm","multi-agents","rag","vector-database"],"archived":false,"github_pushed_at":"2026-08-06T21:24:16+00:00","maintenance_label":"Very active","stars_delta_30d":719,"url":"https://www.graphcanon.com/tools/run-llama-llama-index","markdown_url":"https://www.graphcanon.com/tools/run-llama-llama-index.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-llama-index","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-llama-index"}},{"type":"related","direction":"out","explanation":null,"successor_context":null,"tool":{"slug":"paddlepaddle-paddleocr","name":"PaddleOCR","tagline":"A powerful, lightweight OCR toolkit to convert images and PDFs into structured data","github_url":"https://github.com/PaddlePaddle/PaddleOCR","owner":"PaddlePaddle","repo":"PaddleOCR","owner_avatar_url":"https://avatars.githubusercontent.com/u/23534030?v=4","primary_language":"Python","stars":87808,"forks":11187,"topics":["ai4science","chineseocr","document-parsing","document-translation","kie","ocr","paddleocr-vl","pdf-extractor-rag","pdf-parser","pdf2markdown","pp-ocr","pp-structure","rag"],"archived":false,"github_pushed_at":"2026-07-22T11:59:34+00:00","maintenance_label":"Active","stars_delta_30d":2062,"url":"https://www.graphcanon.com/tools/paddlepaddle-paddleocr","markdown_url":"https://www.graphcanon.com/tools/paddlepaddle-paddleocr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/paddlepaddle-paddleocr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=paddlepaddle-paddleocr"}},{"type":"alternative","direction":"out","explanation":"Both opendataloader-pdf and unstructured deal with parsing PDFs, but they likely have different approaches or capabilities.","successor_context":null,"tool":{"slug":"opendataloader-project-opendataloader-pdf","name":"opendataloader-pdf","tagline":"PDF Parser for AI-ready data","github_url":"https://github.com/opendataloader-project/opendataloader-pdf","owner":"opendataloader-project","repo":"opendataloader-pdf","owner_avatar_url":"https://avatars.githubusercontent.com/u/211280852?v=4","primary_language":"Java","stars":28528,"forks":2724,"topics":["a11y","accessibility","ai","bounding-box","document-parsing","eaa","html","json","markdown","ocr","ocr-recognition","pdf","pdf-accessibility","pdf-converter","pdf-extraction","pdf-parser","pdf-ua","rag","tables","tagged-pdf"],"archived":false,"github_pushed_at":"2026-08-18T04:01:45+00:00","maintenance_label":"Very active","stars_delta_30d":1078,"url":"https://www.graphcanon.com/tools/opendataloader-project-opendataloader-pdf","markdown_url":"https://www.graphcanon.com/tools/opendataloader-project-opendataloader-pdf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opendataloader-project-opendataloader-pdf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opendataloader-project-opendataloader-pdf"}},{"type":"alternative","direction":"out","explanation":"The focus of both langextract and unstructured is extracting structured data from unstructured text; however, they might differ in the methods used or features offered.","successor_context":null,"tool":{"slug":"google-langextract","name":"langextract","tagline":"A Python library for extracting structured information from unstructured text using LLMs.","github_url":"https://github.com/google/langextract","owner":"google","repo":"langextract","owner_avatar_url":"https://avatars.githubusercontent.com/u/1342004?v=4","primary_language":"Python","stars":38400,"forks":2693,"topics":["gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","llm","nlp","python","structured-data"],"archived":false,"github_pushed_at":"2026-08-11T15:31:39+00:00","maintenance_label":"Very active","stars_delta_30d":1241,"url":"https://www.graphcanon.com/tools/google-langextract","markdown_url":"https://www.graphcanon.com/tools/google-langextract.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/google-langextract","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=google-langextract"}},{"type":"depends_on","direction":"out","explanation":null,"successor_context":null,"tool":{"slug":"ray-project-ray","name":"ray","tagline":"Ray is an AI compute engine with a core distributed runtime and AI Libraries for accelerating ML workloads.","github_url":"https://github.com/ray-project/ray","owner":"ray-project","repo":"ray","owner_avatar_url":"https://avatars.githubusercontent.com/u/22125274?v=4","primary_language":"Python","stars":43526,"forks":7929,"topics":["data-science","deep-learning","deployment","distributed","hyperparameter-optimization","hyperparameter-search","large-language-models","llm","llm-inference","llm-serving","machine-learning","optimization","parallel","python","pytorch","ray","reinforcement-learning","rllib","serving","tensorflow"],"archived":false,"github_pushed_at":"2026-08-16T00:26:16+00:00","maintenance_label":"Very active","stars_delta_30d":270,"url":"https://www.graphcanon.com/tools/ray-project-ray","markdown_url":"https://www.graphcanon.com/tools/ray-project-ray.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ray-project-ray","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ray-project-ray"}},{"type":"alternative","direction":"in","explanation":"Both OpenDataLoader PDF and unstructured parse various document types into structured data, focusing on accessibility and ease of use for AI applications.","successor_context":null,"tool":{"slug":"opendataloader-project-opendataloader-pdf","name":"opendataloader-pdf","tagline":"PDF Parser for AI-ready data","github_url":"https://github.com/opendataloader-project/opendataloader-pdf","owner":"opendataloader-project","repo":"opendataloader-pdf","owner_avatar_url":"https://avatars.githubusercontent.com/u/211280852?v=4","primary_language":"Java","stars":28528,"forks":2724,"topics":["a11y","accessibility","ai","bounding-box","document-parsing","eaa","html","json","markdown","ocr","ocr-recognition","pdf","pdf-accessibility","pdf-converter","pdf-extraction","pdf-parser","pdf-ua","rag","tables","tagged-pdf"],"archived":false,"github_pushed_at":"2026-08-18T04:01:45+00:00","maintenance_label":"Very active","stars_delta_30d":1078,"url":"https://www.graphcanon.com/tools/opendataloader-project-opendataloader-pdf","markdown_url":"https://www.graphcanon.com/tools/opendataloader-project-opendataloader-pdf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opendataloader-project-opendataloader-pdf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opendataloader-project-opendataloader-pdf"}},{"type":"alternative","direction":"in","explanation":"Both LangExtract and unstructured aim to convert unstructured text into structured data using AI techniques.","successor_context":null,"tool":{"slug":"google-langextract","name":"langextract","tagline":"A Python library for extracting structured information from unstructured text using LLMs.","github_url":"https://github.com/google/langextract","owner":"google","repo":"langextract","owner_avatar_url":"https://avatars.githubusercontent.com/u/1342004?v=4","primary_language":"Python","stars":38400,"forks":2693,"topics":["gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","llm","nlp","python","structured-data"],"archived":false,"github_pushed_at":"2026-08-11T15:31:39+00:00","maintenance_label":"Very active","stars_delta_30d":1241,"url":"https://www.graphcanon.com/tools/google-langextract","markdown_url":"https://www.graphcanon.com/tools/google-langextract.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/google-langextract","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=google-langextract"}},{"type":"integrates_with","direction":"in","explanation":"Graphify seeks to turn various files into a queryable form and may integrate with Unstructured’s capability of converting documents into structured formats for easier querying and processing within the knowledge graph.","successor_context":null,"tool":{"slug":"graphify-labs-graphify","name":"graphify","tagline":"Turn any code or documentation into a queryable knowledge graph","github_url":"https://github.com/Graphify-Labs/graphify","owner":"Graphify-Labs","repo":"graphify","owner_avatar_url":"https://avatars.githubusercontent.com/u/297659074?v=4","primary_language":"Python","stars":107507,"forks":10441,"topics":["ai-agents","antigravity","ast","claude-code","code-analysis","code-search","codex","cursor","developer-tools","gemini","graphrag","knowledge-graph","leiden","llm","mcp","openclaw","rag","skills","tree-sitter"],"archived":false,"github_pushed_at":"2026-08-17T18:42:58+00:00","maintenance_label":"Very active","stars_delta_30d":16918,"url":"https://www.graphcanon.com/tools/graphify-labs-graphify","markdown_url":"https://www.graphcanon.com/tools/graphify-labs-graphify.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/graphify-labs-graphify","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=graphify-labs-graphify"}},{"type":"alternative","direction":"in","explanation":"Unstructured and OfficeCLI both convert unstructured content (documents) into structured data, albeit for different formats (e.g., PDF to structured vs. various office documents).","successor_context":null,"tool":{"slug":"iofficeai-officecli","name":"OfficeCLI","tagline":"First and best Office suite for AI agents to automate Word, Excel, and PowerPoint files.","github_url":"https://github.com/iOfficeAI/OfficeCLI","owner":"iOfficeAI","repo":"OfficeCLI","owner_avatar_url":"https://avatars.githubusercontent.com/u/145246968?v=4","primary_language":"C#","stars":28777,"forks":1953,"topics":["agent","ai","claude-code","cli","codex","docx","excel","office","openclaw","pptx","presentation","skills","word","xlsx"],"archived":false,"github_pushed_at":"2026-08-13T10:28:53+00:00","maintenance_label":"Very active","stars_delta_30d":9205,"url":"https://www.graphcanon.com/tools/iofficeai-officecli","markdown_url":"https://www.graphcanon.com/tools/iofficeai-officecli.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/iofficeai-officecli","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=iofficeai-officecli"}},{"type":"alternative","direction":"in","explanation":"Both xberg and unstructured aim to convert documents into structured data, making them alternatives.","successor_context":null,"tool":{"slug":"xberg-io-xberg","name":"xberg","tagline":"A polyglot document intelligence framework with a Rust core","github_url":"https://github.com/xberg-io/xberg","owner":"xberg-io","repo":"xberg","owner_avatar_url":"https://avatars.githubusercontent.com/u/241328462?v=4","primary_language":"Rust","stars":9128,"forks":562,"topics":["bun","csharp","document-intelligence","elixir","ffi","golang","java","metadata-extraction","node","pdf-extraction","pdfium","php","python","rag","ruby","rust","table-extraction","tesseract","text-extraction","wasm"],"archived":false,"github_pushed_at":"2026-08-16T16:00:11+00:00","maintenance_label":"Very active","stars_delta_30d":460,"url":"https://www.graphcanon.com/tools/xberg-io-xberg","markdown_url":"https://www.graphcanon.com/tools/xberg-io-xberg.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/xberg-io-xberg","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=xberg-io-xberg"}},{"type":"depends_on","direction":"in","explanation":"Data-Juicer processes data which could include the output from unstructured documents processed by unstructured.","successor_context":null,"tool":{"slug":"datajuicer-data-juicer","name":"data-juicer","tagline":"Data processing for and with foundation models","github_url":"https://github.com/datajuicer/data-juicer","owner":"datajuicer","repo":"data-juicer","owner_avatar_url":"https://avatars.githubusercontent.com/u/223222708?v=4","primary_language":"Python","stars":6897,"forks":404,"topics":["data","data-analysis","data-pipeline","data-processing","data-science","data-visualization","foundation-models","instruction-tuning","large-language-models","llm","llms","multi-modal","pre-training","synthetic-data"],"archived":false,"github_pushed_at":"2026-08-13T09:19:31+00:00","maintenance_label":"Very active","stars_delta_30d":166,"url":"https://www.graphcanon.com/tools/datajuicer-data-juicer","markdown_url":"https://www.graphcanon.com/tools/datajuicer-data-juicer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datajuicer-data-juicer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datajuicer-data-juicer"}},{"type":"integrates_with","direction":"in","explanation":"llama_cloud_services deals with document parsing, while unstructured is focused on converting documents to structured data, a process they could be integrated for enhancing cloud-based document management.","successor_context":null,"tool":{"slug":"run-llama-llama-cloud-services","name":"llama_cloud_services","tagline":"Knowledge Agents and Management in the Cloud","github_url":"https://github.com/run-llama/llama_cloud_services","owner":"run-llama","repo":"llama_cloud_services","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"TypeScript","stars":4258,"forks":467,"topics":["document","document-parser","document-parsing","docx-to-markdown","parsing","pdf","pdf-document-processor","pdf-to-excel","pdf-to-json","pdf-to-markdown","pdf-to-text","ppt-to-json","ppt-to-markdown","pptx","structured-data","tables"],"archived":false,"github_pushed_at":"2026-05-18T19:09:10+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/run-llama-llama-cloud-services","markdown_url":"https://www.graphcanon.com/tools/run-llama-llama-cloud-services.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-llama-cloud-services","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-llama-cloud-services"}},{"type":"integrates_with","direction":"in","explanation":"Unstructured transforms documents into structured data, which can then be fed into EmbedAnything to generate embeddings and perform indexing or search operations.","successor_context":null,"tool":{"slug":"starlightsearch-embedanything","name":"EmbedAnything","tagline":"Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust","github_url":"https://github.com/StarlightSearch/EmbedAnything","owner":"StarlightSearch","repo":"EmbedAnything","owner_avatar_url":"https://avatars.githubusercontent.com/u/165606246?v=4","primary_language":"Rust","stars":1304,"forks":143,"topics":["ai","cloud","generative-ai","hacktoberfest","high-performance","indexing","inference","information-retrieval","large-language-models","local","machine-learning","onnxruntime","pipeline","production-ready","python","rag","rust","search","server","vector-database"],"archived":false,"github_pushed_at":"2026-08-12T08:56:59+00:00","maintenance_label":"Active","stars_delta_30d":18,"url":"https://www.graphcanon.com/tools/starlightsearch-embedanything","markdown_url":"https://www.graphcanon.com/tools/starlightsearch-embedanything.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/starlightsearch-embedanything","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=starlightsearch-embedanything"}}],"neighbours":[{"slug":"graphify-labs-graphify","name":"graphify","tagline":"Turn any code or documentation into a queryable knowledge graph","github_url":"https://github.com/Graphify-Labs/graphify","owner":"Graphify-Labs","repo":"graphify","owner_avatar_url":"https://avatars.githubusercontent.com/u/297659074?v=4","primary_language":"Python","stars":107507,"forks":10441,"topics":["ai-agents","antigravity","ast","claude-code","code-analysis","code-search","codex","cursor","developer-tools","gemini","graphrag","knowledge-graph","leiden","llm","mcp","openclaw","rag","skills","tree-sitter"],"archived":false,"github_pushed_at":"2026-08-17T18:42:58+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/graphify-labs-graphify","markdown_url":"https://www.graphcanon.com/tools/graphify-labs-graphify.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/graphify-labs-graphify","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=graphify-labs-graphify","shared_categories":["data-retrieval"]},{"slug":"pathwaycom-llm-app","name":"llm-app","tagline":"Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data.","github_url":"https://github.com/pathwaycom/llm-app","owner":"pathwaycom","repo":"llm-app","owner_avatar_url":"https://avatars.githubusercontent.com/u/25750857?v=4","primary_language":"Jupyter Notebook","stars":59037,"forks":1466,"topics":["chatbot","hugging-face","llm","llm-local","llm-prompting","llm-security","llmops","machine-learning","open-ai","pathway","rag","real-time","retrieval-augmented-generation","vector-database","vector-index"],"archived":false,"github_pushed_at":"2026-07-05T17:59:07+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/pathwaycom-llm-app","markdown_url":"https://www.graphcanon.com/tools/pathwaycom-llm-app.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pathwaycom-llm-app","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pathwaycom-llm-app","shared_categories":["data-retrieval"]},{"slug":"opendataloader-project-opendataloader-pdf","name":"opendataloader-pdf","tagline":"PDF Parser for AI-ready data","github_url":"https://github.com/opendataloader-project/opendataloader-pdf","owner":"opendataloader-project","repo":"opendataloader-pdf","owner_avatar_url":"https://avatars.githubusercontent.com/u/211280852?v=4","primary_language":"Java","stars":28528,"forks":2724,"topics":["a11y","accessibility","ai","bounding-box","document-parsing","eaa","html","json","markdown","ocr","ocr-recognition","pdf","pdf-accessibility","pdf-converter","pdf-extraction","pdf-parser","pdf-ua","rag","tables","tagged-pdf"],"archived":false,"github_pushed_at":"2026-08-18T04:01:45+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/opendataloader-project-opendataloader-pdf","markdown_url":"https://www.graphcanon.com/tools/opendataloader-project-opendataloader-pdf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opendataloader-project-opendataloader-pdf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opendataloader-project-opendataloader-pdf","shared_categories":["model-training","data-retrieval"]},{"slug":"promtengineer-localgpt","name":"localGPT","tagline":"Chat with your documents locally using GPT models","github_url":"https://github.com/PromtEngineer/localGPT","owner":"PromtEngineer","repo":"localGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/134474669?v=4","primary_language":"Python","stars":22209,"forks":2467,"topics":[],"archived":false,"github_pushed_at":"2026-07-18T07:15:01+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/promtengineer-localgpt","markdown_url":"https://www.graphcanon.com/tools/promtengineer-localgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/promtengineer-localgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=promtengineer-localgpt","shared_categories":["data-retrieval"]},{"slug":"tencent-weknora","name":"WeKnora","tagline":"Open-source LLM knowledge platform for creating a queryable RAG, autonomous reasoning agent, and self-maintaining Wiki.","github_url":"https://github.com/Tencent/WeKnora","owner":"Tencent","repo":"WeKnora","owner_avatar_url":"https://avatars.githubusercontent.com/u/18461506?v=4","primary_language":"Go","stars":19992,"forks":2877,"topics":["agent","agentic","ai","chatbot","embeddings","evaluation","generative-ai","golang","knowledge-base","llm","multi-tenant","multimodel","ollama","openai","question-answering","rag","reranking","semantic-search","vector-search","wiki"],"archived":false,"github_pushed_at":"2026-08-16T05:31:52+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/tencent-weknora","markdown_url":"https://www.graphcanon.com/tools/tencent-weknora.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tencent-weknora","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tencent-weknora","shared_categories":[]},{"slug":"yusufkaraaslan-skill-seekers","name":"Skill_Seekers","tagline":"Automation tool for converting documentation and code into Claude AI skills","github_url":"https://github.com/yusufkaraaslan/Skill_Seekers","owner":"yusufkaraaslan","repo":"Skill_Seekers","owner_avatar_url":"https://avatars.githubusercontent.com/u/11597362?v=4","primary_language":"Python","stars":14565,"forks":1477,"topics":["ai-tools","ast-parser","automation","claude-ai","claude-skills","code-analysis","conflict-detection","documentation","documentation-generator","github","github-scraper","mcp","mcp-server","multi-source","ocr","pdf","python","web-scraping"],"archived":false,"github_pushed_at":"2026-07-20T13:09:44+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/yusufkaraaslan-skill-seekers","markdown_url":"https://www.graphcanon.com/tools/yusufkaraaslan-skill-seekers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/yusufkaraaslan-skill-seekers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=yusufkaraaslan-skill-seekers","shared_categories":["model-training"]},{"slug":"data-privacy-stack-presidio","name":"presidio","tagline":"A framework for detecting and anonymizing sensitive data","github_url":"https://github.com/data-privacy-stack/presidio","owner":"data-privacy-stack","repo":"presidio","owner_avatar_url":"https://avatars.githubusercontent.com/u/275623515?v=4","primary_language":"Python","stars":10395,"forks":1237,"topics":["anonymization","data-anonymization","data-masking","data-obfuscation","data-privacy","data-redaction","de-identification","guardrails","image-redactor","named-entity-recognition","nlp","personally-identifiable-information","phi","pii","pii-detection","privacy","python","sensitive-data","spacy","transformers"],"archived":false,"github_pushed_at":"2026-08-08T21:25:09+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/data-privacy-stack-presidio","markdown_url":"https://www.graphcanon.com/tools/data-privacy-stack-presidio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/data-privacy-stack-presidio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=data-privacy-stack-presidio","shared_categories":["data-retrieval"]},{"slug":"zipstack-unstract","name":"unstract","tagline":"LLM-Driven Extraction of Unstructured Data for API Deployments and ETL Pipeline Workflows","github_url":"https://github.com/Zipstack/unstract","owner":"Zipstack","repo":"unstract","owner_avatar_url":"https://avatars.githubusercontent.com/u/89070934?v=4","primary_language":"Python","stars":6932,"forks":663,"topics":["ai-agents","data-engineering","document-ai","generative-ai","idp","json-extraction","llm","mcp-server","ocr","pdf-extraction","prompt-engineering","structured-output"],"archived":false,"github_pushed_at":"2026-07-27T22:23:41+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/zipstack-unstract","markdown_url":"https://www.graphcanon.com/tools/zipstack-unstract.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zipstack-unstract","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zipstack-unstract","shared_categories":["data-retrieval"]},{"slug":"datajuicer-data-juicer","name":"data-juicer","tagline":"Data processing for and with foundation models","github_url":"https://github.com/datajuicer/data-juicer","owner":"datajuicer","repo":"data-juicer","owner_avatar_url":"https://avatars.githubusercontent.com/u/223222708?v=4","primary_language":"Python","stars":6897,"forks":404,"topics":["data","data-analysis","data-pipeline","data-processing","data-science","data-visualization","foundation-models","instruction-tuning","large-language-models","llm","llms","multi-modal","pre-training","synthetic-data"],"archived":false,"github_pushed_at":"2026-08-13T09:19:31+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/datajuicer-data-juicer","markdown_url":"https://www.graphcanon.com/tools/datajuicer-data-juicer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datajuicer-data-juicer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datajuicer-data-juicer","shared_categories":["model-training","data-retrieval"]},{"slug":"clusterzx-paperless-ai","name":"paperless-ai","tagline":"Automated document analyzer for Paperless-ngx using OpenAI API and compatible services to tag documents","github_url":"https://github.com/clusterzx/paperless-ai","owner":"clusterzx","repo":"paperless-ai","owner_avatar_url":"https://avatars.githubusercontent.com/u/32274973?v=4","primary_language":"JavaScript","stars":5882,"forks":322,"topics":["ai","automation","gemma","llama","mistral","ollama","paperless","paperless-ngx","phi"],"archived":false,"github_pushed_at":"2026-08-02T04:51:37+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/clusterzx-paperless-ai","markdown_url":"https://www.graphcanon.com/tools/clusterzx-paperless-ai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/clusterzx-paperless-ai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=clusterzx-paperless-ai","shared_categories":["model-training"]},{"slug":"ucbepic-docetl","name":"docetl","tagline":"A system for agentic LLM-powered data processing and ETL","github_url":"https://github.com/ucbepic/docetl","owner":"ucbepic","repo":"docetl","owner_avatar_url":"https://avatars.githubusercontent.com/u/88680502?v=4","primary_language":"Python","stars":3961,"forks":421,"topics":["agents","data","data-pipelines","document-analysis","document-processing","elt","etl","llm","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow"],"archived":false,"github_pushed_at":"2026-08-09T23:31:04+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/ucbepic-docetl","markdown_url":"https://www.graphcanon.com/tools/ucbepic-docetl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ucbepic-docetl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ucbepic-docetl","shared_categories":["data-retrieval"]},{"slug":"huggingface-datatrove","name":"datatrove","tagline":"Platform-agnostic customizable pipeline processing blocks for data processing and transformation.","github_url":"https://github.com/huggingface/datatrove","owner":"huggingface","repo":"datatrove","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":3250,"forks":288,"topics":[],"archived":false,"github_pushed_at":"2026-08-06T15:27:26+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-datatrove","markdown_url":"https://www.graphcanon.com/tools/huggingface-datatrove.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-datatrove","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-datatrove","shared_categories":["model-training","data-retrieval"]}]}}