{"data":{"node":{"slug":"ahammadmejbah-awesome-datasets-hub","name":"Awesome-Datasets-Hub","tagline":"Curated collection of datasets for Large Language Models (LLMs)","github_url":"https://github.com/ahammadmejbah/Awesome-Datasets-Hub","owner":"ahammadmejbah","repo":"Awesome-Datasets-Hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/56669333?v=4","primary_language":null,"stars":146,"forks":40,"topics":["benchmark","benchmarking","deep-learning","deep-neural-networks","deeplearning","genetic-algorithm","llm","llm-evaluation","llm-inference","machine-learning","machine-learning-algorithms","machinelearning","neural-network"],"archived":false,"github_pushed_at":"2026-06-20T07:06:51+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/ahammadmejbah-awesome-datasets-hub","markdown_url":"https://www.graphcanon.com/tools/ahammadmejbah-awesome-datasets-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ahammadmejbah-awesome-datasets-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ahammadmejbah-awesome-datasets-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":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"benchmark","name":"benchmark"},{"slug":"code-generation","name":"code generation"},{"slug":"instruction-tuning","name":"instruction-tuning"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"medical-ai","name":"medical-ai"},{"slug":"multimodal-learning","name":"multimodal-learning"},{"slug":"nlp","name":"nlp"},{"slug":"reasoning","name":"reasoning"}],"edges":[],"neighbours":[{"slug":"patchy631-ai-engineering-hub","name":"ai-engineering-hub","tagline":"Tutorials on LLMs, RAGs, and real-world AI agent applications","github_url":"https://github.com/patchy631/ai-engineering-hub","owner":"patchy631","repo":"ai-engineering-hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/38653995?v=4","primary_language":"Jupyter Notebook","stars":37020,"forks":6107,"topics":["agents","ai","llms","machine-learning","mcp","rag"],"archived":false,"github_pushed_at":"2026-07-27T18:43:06+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/patchy631-ai-engineering-hub","markdown_url":"https://www.graphcanon.com/tools/patchy631-ai-engineering-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/patchy631-ai-engineering-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=patchy631-ai-engineering-hub","shared_categories":[]},{"slug":"aishwaryanr-awesome-generative-ai-guide","name":"awesome-generative-ai-guide","tagline":"A curated list for generative AI research and learning resources","github_url":"https://github.com/aishwaryanr/awesome-generative-ai-guide","owner":"aishwaryanr","repo":"awesome-generative-ai-guide","owner_avatar_url":"https://avatars.githubusercontent.com/u/12550285?v=4","primary_language":"HTML","stars":28771,"forks":5873,"topics":["awesome","awesome-list","generative-ai","interview-questions","large-language-models","llms","notebook-jupyter","vision-and-language"],"archived":false,"github_pushed_at":"2026-08-12T20:24:24+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/aishwaryanr-awesome-generative-ai-guide","markdown_url":"https://www.graphcanon.com/tools/aishwaryanr-awesome-generative-ai-guide.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/aishwaryanr-awesome-generative-ai-guide","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=aishwaryanr-awesome-generative-ai-guide","shared_categories":[]},{"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":"arindam200-awesome-ai-apps","name":"awesome-ai-apps","tagline":"A curated list of AI applications showcasing RAG, agents, and workflows.","github_url":"https://github.com/Arindam200/awesome-ai-apps","owner":"Arindam200","repo":"awesome-ai-apps","owner_avatar_url":"https://avatars.githubusercontent.com/u/109217591?v=4","primary_language":"Python","stars":13494,"forks":1760,"topics":["agents","ai","hacktoberfest","llm","mcp"],"archived":false,"github_pushed_at":"2026-08-19T05:04:11+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/arindam200-awesome-ai-apps","markdown_url":"https://www.graphcanon.com/tools/arindam200-awesome-ai-apps.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/arindam200-awesome-ai-apps","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=arindam200-awesome-ai-apps","shared_categories":[]},{"slug":"eugeneyan-open-llms","name":"open-llms","tagline":"A list of open LLMs available for commercial use.","github_url":"https://github.com/eugeneyan/open-llms","owner":"eugeneyan","repo":"open-llms","owner_avatar_url":"https://avatars.githubusercontent.com/u/6831355?v=4","primary_language":null,"stars":12849,"forks":985,"topics":["commercial","large-language-models","llm","llms"],"archived":false,"github_pushed_at":"2025-02-13T06:37:12+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/eugeneyan-open-llms","markdown_url":"https://www.graphcanon.com/tools/eugeneyan-open-llms.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eugeneyan-open-llms","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eugeneyan-open-llms","shared_categories":[]},{"slug":"rucaibox-llmsurvey","name":"LLMSurvey","tagline":"A comprehensive collection of papers and resources related to Large Language Models.","github_url":"https://github.com/RUCAIBox/LLMSurvey","owner":"RUCAIBox","repo":"LLMSurvey","owner_avatar_url":"https://avatars.githubusercontent.com/u/54706620?v=4","primary_language":"Python","stars":12205,"forks":931,"topics":["chain-of-thought","chatgpt","in-context-learning","instruction-tuning","large-language-models","llm","llms","natural-language-processing","pre-trained-language-models","pre-training","rlhf"],"archived":false,"github_pushed_at":"2025-03-11T09:51:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey","markdown_url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rucaibox-llmsurvey","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rucaibox-llmsurvey","shared_categories":["evaluation-observability"]},{"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":["evaluation-observability"]},{"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":["data-retrieval"]},{"slug":"luban-agi-awesome-aigc-tutorials","name":"Awesome-AIGC-Tutorials","tagline":"Curated tutorials and resources for Large Language Models, AI Painting, and more","github_url":"https://github.com/luban-agi/Awesome-AIGC-Tutorials","owner":"luban-agi","repo":"Awesome-AIGC-Tutorials","owner_avatar_url":"https://avatars.githubusercontent.com/u/142385464?v=4","primary_language":null,"stars":4522,"forks":303,"topics":["ai","aigc","awesome","chatgpt","courses-resource","deep-learning","llm","midjourney","multimodal","nlp","prompt-engineering","stable-diffusion","tutorials"],"archived":false,"github_pushed_at":"2024-03-31T09:18:04+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/luban-agi-awesome-aigc-tutorials","markdown_url":"https://www.graphcanon.com/tools/luban-agi-awesome-aigc-tutorials.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/luban-agi-awesome-aigc-tutorials","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=luban-agi-awesome-aigc-tutorials","shared_categories":[]},{"slug":"huaizhengzhang-ai-infra-from-zero-to-hero","name":"AI-Infra-from-Zero-to-Hero","tagline":"Awesome System for Machine Learning and LLM Infra","github_url":"https://github.com/HuaizhengZhang/AI-Infra-from-Zero-to-Hero","owner":"HuaizhengZhang","repo":"AI-Infra-from-Zero-to-Hero","owner_avatar_url":"https://avatars.githubusercontent.com/u/5894780?v=4","primary_language":null,"stars":4285,"forks":409,"topics":["ai-infra","genai","large-language-models","llmsys","mlsys","model-serving","model-training"],"archived":false,"github_pushed_at":"2025-07-25T02:24:35+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero","markdown_url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huaizhengzhang-ai-infra-from-zero-to-hero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huaizhengzhang-ai-infra-from-zero-to-hero","shared_categories":[]},{"slug":"amberljc-llmsys-paperlist","name":"LLMSys-PaperList","tagline":"Curated list of academic papers related to Large Language Model systems","github_url":"https://github.com/AmberLJC/LLMSys-PaperList","owner":"AmberLJC","repo":"LLMSys-PaperList","owner_avatar_url":"https://avatars.githubusercontent.com/u/42296458?v=4","primary_language":"Python","stars":2220,"forks":120,"topics":[],"archived":false,"github_pushed_at":"2026-07-25T02:03:12+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/amberljc-llmsys-paperlist","markdown_url":"https://www.graphcanon.com/tools/amberljc-llmsys-paperlist.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/amberljc-llmsys-paperlist","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=amberljc-llmsys-paperlist","shared_categories":[]},{"slug":"huggingface-aisheets","name":"aisheets","tagline":"Build, enrich, and transform datasets using AI models with no code","github_url":"https://github.com/huggingface/aisheets","owner":"huggingface","repo":"aisheets","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"TypeScript","stars":1638,"forks":140,"topics":["ai","llm-evaluation","llms","nocode","oss","synthetic-data"],"archived":false,"github_pushed_at":"2026-05-26T10:33:23+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/huggingface-aisheets","markdown_url":"https://www.graphcanon.com/tools/huggingface-aisheets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-aisheets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-aisheets","shared_categories":["evaluation-observability","data-retrieval"]}]}}