{"data":{"node":{"slug":"mhbashari-awesome-persian-nlp-ir","name":"awesome-persian-nlp-ir","tagline":"Curated List of Persian NLP and IR Tools","github_url":"https://github.com/mhbashari/awesome-persian-nlp-ir","owner":"mhbashari","repo":"awesome-persian-nlp-ir","owner_avatar_url":"https://avatars.githubusercontent.com/u/4939481?v=4","primary_language":null,"stars":768,"forks":117,"topics":["corpus","dependency-parser","embeddings","information-retrieval","language-detection","morphological-analysis","named-entity-recognition","natural-language-processing","normalizer","part-of-speech-tagger","persian-language","persian-nlp","persian-stemmer","shallow-parser","spell-check","stemmer"],"archived":false,"github_pushed_at":"2023-11-07T11:51:46+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/mhbashari-awesome-persian-nlp-ir","markdown_url":"https://www.graphcanon.com/tools/mhbashari-awesome-persian-nlp-ir.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mhbashari-awesome-persian-nlp-ir","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mhbashari-awesome-persian-nlp-ir"},"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":"corpus","name":"corpus"},{"slug":"dependency-parser","name":"dependency-parser"},{"slug":"embeddings","name":"embeddings"},{"slug":"information-retrieval","name":"information-retrieval"},{"slug":"language-detection","name":"language-detection"},{"slug":"morphological-analysis","name":"morphological-analysis"},{"slug":"named-entity-recognition","name":"named-entity-recognition"},{"slug":"natural-language-processing","name":"natural-language-processing"}],"edges":[],"neighbours":[{"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":"neuml-txtai","name":"txtai","tagline":"All-in-one AI framework for semantic search, LLM orchestration and language model workflows","github_url":"https://github.com/neuml/txtai","owner":"neuml","repo":"txtai","owner_avatar_url":"https://avatars.githubusercontent.com/u/59890304?v=4","primary_language":"Python","stars":12890,"forks":873,"topics":["agents","ai","ai-agents","embeddings","information-retrieval","language-model","large-language-models","llm","nlp","python","rag","retrieval-augmented-generation","search","search-engine","semantic-search","sentence-embeddings","transformers","txtai","vector-database","vector-search"],"archived":false,"github_pushed_at":"2026-08-12T13:42:39+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/neuml-txtai","markdown_url":"https://www.graphcanon.com/tools/neuml-txtai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/neuml-txtai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=neuml-txtai","shared_categories":["data-retrieval"]},{"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":"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":"tensorchord-awesome-llmops","name":"Awesome-LLMOps","tagline":"An awesome & curated list of best LLMOps tools for developers","github_url":"https://github.com/tensorchord/Awesome-LLMOps","owner":"tensorchord","repo":"Awesome-LLMOps","owner_avatar_url":"https://avatars.githubusercontent.com/u/100543303?v=4","primary_language":"Shell","stars":5915,"forks":993,"topics":["ai-development-tools","awesome-list","llmops","mlops"],"archived":false,"github_pushed_at":"2026-05-21T09:12:50+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/tensorchord-awesome-llmops","markdown_url":"https://www.graphcanon.com/tools/tensorchord-awesome-llmops.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorchord-awesome-llmops","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorchord-awesome-llmops","shared_categories":["model-training","data-retrieval"]},{"slug":"mahseema-awesome-ai-tools","name":"awesome-ai-tools","tagline":"A curated list of Artificial Intelligence Top Tools","github_url":"https://github.com/mahseema/awesome-ai-tools","owner":"mahseema","repo":"awesome-ai-tools","owner_avatar_url":"https://avatars.githubusercontent.com/u/143227828?v=4","primary_language":null,"stars":5912,"forks":2011,"topics":["ai","ai-agent","ai-agents","ai-assistant","ai-tools","ai-tools-list","ai-top-tools","awesome","awesome-ai","awesome-ai-tools","awesome-list","bestofai","futuretools","machine-learning","ml","mlops","theresanaiforthat","top-ai-tools","vibe-coding","workflow"],"archived":false,"github_pushed_at":"2025-12-31T14:46:19+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/mahseema-awesome-ai-tools","markdown_url":"https://www.graphcanon.com/tools/mahseema-awesome-ai-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mahseema-awesome-ai-tools","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mahseema-awesome-ai-tools","shared_categories":["model-training","data-retrieval"]},{"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":["model-training"]},{"slug":"huangowen-awesome-llm-compression","name":"Awesome-LLM-Compression","tagline":"Awesome LLM compression research papers and tools to accelerate LLM training and inference.","github_url":"https://github.com/HuangOwen/Awesome-LLM-Compression","owner":"HuangOwen","repo":"Awesome-LLM-Compression","owner_avatar_url":"https://avatars.githubusercontent.com/u/24937399?v=4","primary_language":null,"stars":1859,"forks":129,"topics":[],"archived":false,"github_pushed_at":"2026-06-30T15:26:46+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/huangowen-awesome-llm-compression","markdown_url":"https://www.graphcanon.com/tools/huangowen-awesome-llm-compression.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huangowen-awesome-llm-compression","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huangowen-awesome-llm-compression","shared_categories":[]},{"slug":"run-llama-semtools","name":"semtools","tagline":"Semantic search and document parsing tools for the command line","github_url":"https://github.com/run-llama/semtools","owner":"run-llama","repo":"semtools","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"Rust","stars":1855,"forks":142,"topics":["cli","embeddings","parser","rust","search","semantic","semantic-search","static-embedding"],"archived":false,"github_pushed_at":"2026-03-11T14:30:50+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/run-llama-semtools","markdown_url":"https://www.graphcanon.com/tools/run-llama-semtools.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-semtools","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-semtools","shared_categories":["data-retrieval"]},{"slug":"llm-jp-awesome-japanese-llm","name":"awesome-japanese-llm","tagline":"Overview of Japanese LLMs","github_url":"https://github.com/llm-jp/awesome-japanese-llm","owner":"llm-jp","repo":"awesome-japanese-llm","owner_avatar_url":"https://avatars.githubusercontent.com/u/134031702?v=4","primary_language":"TypeScript","stars":1424,"forks":45,"topics":["foundation-models","generative-ai","generative-model","generative-models","japanese","japanese-language","japanese-language-model","japanese-llm","language-model","language-models","large-language-model","large-language-models","llm","llm-japanese","llms","multimodal","vision-and-language","vision-language","vision-language-model"],"archived":false,"github_pushed_at":"2026-08-05T12:39:04+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/llm-jp-awesome-japanese-llm","markdown_url":"https://www.graphcanon.com/tools/llm-jp-awesome-japanese-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/llm-jp-awesome-japanese-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=llm-jp-awesome-japanese-llm","shared_categories":["model-training"]},{"slug":"roshan-research-hazm","name":"hazm","tagline":"Persian NLP Toolkit for dependency parsing, embeddings, lemmatization, normalization, POS tagging, and tokenization","github_url":"https://github.com/roshan-research/hazm","owner":"roshan-research","repo":"hazm","owner_avatar_url":"https://avatars.githubusercontent.com/u/1282599?v=4","primary_language":"Python","stars":1417,"forks":208,"topics":["dependency-parser","embeddings","farsi","lemmatization","natural-language-processing","nlp","normalization","persian","persian-nlp","pos-tagging","python","text-processing","tokenizer"],"archived":false,"github_pushed_at":"2026-04-01T18:55:05+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/roshan-research-hazm","markdown_url":"https://www.graphcanon.com/tools/roshan-research-hazm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/roshan-research-hazm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=roshan-research-hazm","shared_categories":["model-training","data-retrieval"]},{"slug":"natasha-natasha","name":"natasha","tagline":"Solves basic Russian NLP tasks via API for lower level Natasha projects","github_url":"https://github.com/natasha/natasha","owner":"natasha","repo":"natasha","owner_avatar_url":"https://avatars.githubusercontent.com/u/12713890?v=4","primary_language":"Python","stars":1348,"forks":120,"topics":["embeddings","morphology","ner","nlp","python","russian","sentence-segmentation","syntax","tokenizer","visualization"],"archived":false,"github_pushed_at":"2026-04-13T19:39:01+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/natasha-natasha","markdown_url":"https://www.graphcanon.com/tools/natasha-natasha.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/natasha-natasha","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=natasha-natasha","shared_categories":["model-training","data-retrieval"]}]}}