{"data":{"node":{"slug":"run-llama-llama-hub","name":"llama-hub","tagline":"A library of data loaders for LLMs made by the community","github_url":"https://github.com/run-llama/llama-hub","owner":"run-llama","repo":"llama-hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"Jupyter Notebook","stars":3469,"forks":721,"topics":[],"archived":true,"github_pushed_at":"2024-03-01T15:17:16+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/run-llama-llama-hub","markdown_url":"https://www.graphcanon.com/tools/run-llama-llama-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-llama-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-llama-hub"},"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":"community-driven","name":"community-driven"},{"slug":"jupyter-notebook","name":"jupyter-notebook"},{"slug":"langchain","name":"langchain"},{"slug":"llamaindex","name":"llamaindex"},{"slug":"python","name":"python"}],"edges":[],"neighbours":[{"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":"scrapegraphai-scrapegraph-ai","name":"Scrapegraph-ai","tagline":"Python scraper based on AI","github_url":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","owner":"ScrapeGraphAI","repo":"Scrapegraph-ai","owner_avatar_url":"https://avatars.githubusercontent.com/u/171017415?v=4","primary_language":"Python","stars":29618,"forks":2925,"topics":["ai-crawler","ai-scraping","ai-search","crawler","data-extraction","firecrawl-alternative","large-language-model","llm","markdown","rag","scraping","scraping-python","web-crawler","web-crawlers","web-data","web-data-extraction","web-scraper","web-scraping","web-search","webscraping"],"archived":false,"github_pushed_at":"2026-07-20T14:22:20+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/scrapegraphai-scrapegraph-ai","markdown_url":"https://www.graphcanon.com/tools/scrapegraphai-scrapegraph-ai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/scrapegraphai-scrapegraph-ai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=scrapegraphai-scrapegraph-ai","shared_categories":["data-retrieval"]},{"slug":"nirdiamant-rag-techniques","name":"RAG_Techniques","tagline":"Showcases advanced techniques for Retrieval-Augmented Generation (RAG) systems with detailed notebook tutorials.","github_url":"https://github.com/NirDiamant/RAG_Techniques","owner":"NirDiamant","repo":"RAG_Techniques","owner_avatar_url":"https://avatars.githubusercontent.com/u/28316913?v=4","primary_language":"Jupyter Notebook","stars":29076,"forks":3540,"topics":["agentic-rag","ai","embeddings","generative-ai","gpt","langchain","llama-index","llm","llms","machine-learning","nlp","openai","python","rag","retrieval-augmented-generation","semantic-search","tutorials","vector-database"],"archived":false,"github_pushed_at":"2026-08-15T00:52:05+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/nirdiamant-rag-techniques","markdown_url":"https://www.graphcanon.com/tools/nirdiamant-rag-techniques.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nirdiamant-rag-techniques","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nirdiamant-rag-techniques","shared_categories":["model-training","data-retrieval"]},{"slug":"huggingface-datasets","name":"datasets","tagline":"Largest hub of ready-to-use datasets for AI models","github_url":"https://github.com/huggingface/datasets","owner":"huggingface","repo":"datasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":21791,"forks":3322,"topics":["ai","artificial-intelligence","computer-vision","dataset-hub","datasets","deep-learning","huggingface","llm","machine-learning","natural-language-processing","nlp","numpy","pandas","pytorch","speech","tensorflow"],"archived":false,"github_pushed_at":"2026-07-30T11:23:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-datasets","markdown_url":"https://www.graphcanon.com/tools/huggingface-datasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-datasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-datasets","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":"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":"wangrongsheng-awesome-llm-resources","name":"awesome-LLM-resources","tagline":"Summary of the world's best LLM resources.","github_url":"https://github.com/WangRongsheng/awesome-LLM-resources","owner":"WangRongsheng","repo":"awesome-LLM-resources","owner_avatar_url":"https://avatars.githubusercontent.com/u/55651568?v=4","primary_language":null,"stars":8845,"forks":950,"topics":["awesome-list","book","course","large-language-models","llama","llm","mistral","openai","qwen","rag","retrieval-augmented-generation","webui"],"archived":false,"github_pushed_at":"2026-08-14T15:54:28+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources","markdown_url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wangrongsheng-awesome-llm-resources","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wangrongsheng-awesome-llm-resources","shared_categories":["model-training"]},{"slug":"zilliztech-deep-searcher","name":"deep-searcher","tagline":"Open Source Deep Research Alternative to Reason and Search on Private Data.","github_url":"https://github.com/zilliztech/deep-searcher","owner":"zilliztech","repo":"deep-searcher","owner_avatar_url":"https://avatars.githubusercontent.com/u/18416694?v=4","primary_language":"Python","stars":8060,"forks":775,"topics":["agent","agentic-rag","claude","deep-research","deepseek","deepseek-r1","grok","grok3","llama4","llm","milvus","openai","qwen3","rag","reasoning-models","vector-database","zilliz"],"archived":false,"github_pushed_at":"2025-11-19T06:04:16+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/zilliztech-deep-searcher","markdown_url":"https://www.graphcanon.com/tools/zilliztech-deep-searcher.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zilliztech-deep-searcher","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zilliztech-deep-searcher","shared_categories":[]},{"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"]},{"slug":"agentset-ai-agentset","name":"agentset","tagline":"The open-source RAG platform with built-in citations and support for deep research","github_url":"https://github.com/agentset-ai/agentset","owner":"agentset-ai","repo":"agentset","owner_avatar_url":"https://avatars.githubusercontent.com/u/200139246?v=4","primary_language":"TypeScript","stars":2066,"forks":185,"topics":["agentic-rag","ai","ai-agents","ai-sdk","chatbots","embeddings","genai","llms","memory","memory-management","rag","vercel-ai-sdk"],"archived":false,"github_pushed_at":"2026-07-16T13:11:34+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/agentset-ai-agentset","markdown_url":"https://www.graphcanon.com/tools/agentset-ai-agentset.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agentset-ai-agentset","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agentset-ai-agentset","shared_categories":["data-retrieval"]},{"slug":"akshata29-entaoai","name":"entaoai","tagline":"Accelerator for uploading enterprise data and using OpenAI services to interact with it.","github_url":"https://github.com/akshata29/entaoai","owner":"akshata29","repo":"entaoai","owner_avatar_url":"https://avatars.githubusercontent.com/u/18509807?v=4","primary_language":"TypeScript","stars":866,"forks":245,"topics":["azure","azure-functions","azure-openai","azure-webapp","azureopenai","chatgpt","cognitive-search","gpt-3","gpt-35-turbo","langchain","openai","pinecone","redis-search","vector-store"],"archived":false,"github_pushed_at":"2025-01-02T16:23:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/akshata29-entaoai","markdown_url":"https://www.graphcanon.com/tools/akshata29-entaoai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/akshata29-entaoai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=akshata29-entaoai","shared_categories":["data-retrieval"]},{"slug":"yvann-ba-robby-chatbot","name":"Robby-chatbot","tagline":"AI chatbot 🤖 for chat with CSV, PDF, TXT files 📄 and YTB videos 🎥","github_url":"https://github.com/yvann-ba/Robby-chatbot","owner":"yvann-ba","repo":"Robby-chatbot","owner_avatar_url":"https://avatars.githubusercontent.com/u/97234242?v=4","primary_language":"Python","stars":813,"forks":284,"topics":["ai","chatbot","gpt-4","langchain","nlp","openai","streamlit"],"archived":false,"github_pushed_at":"2026-02-21T09:38:01+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/yvann-ba-robby-chatbot","markdown_url":"https://www.graphcanon.com/tools/yvann-ba-robby-chatbot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/yvann-ba-robby-chatbot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=yvann-ba-robby-chatbot","shared_categories":["data-retrieval"]}]}}