{"data":{"node":{"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":1424,"forks":205,"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","stars_delta_30d":12,"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"},"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":"dependency-parser","name":"dependency-parser"},{"slug":"embeddings","name":"embeddings"},{"slug":"lemmatization","name":"lemmatization"},{"slug":"natural-language-processing","name":"natural language processing"},{"slug":"nlp","name":"nlp"},{"slug":"normalization","name":"normalization"},{"slug":"persian-nlp","name":"persian-nlp"},{"slug":"pos-tagging","name":"pos-tagging"}],"edges":[],"neighbours":[{"slug":"p-e-w-heretic","name":"heretic","tagline":"Fully automatic censorship removal for language models","github_url":"https://github.com/p-e-w/heretic","owner":"p-e-w","repo":"heretic","owner_avatar_url":"https://avatars.githubusercontent.com/u/2702526?v=4","primary_language":"Python","stars":31738,"forks":3547,"topics":["abliteration","llm","transformer"],"archived":false,"github_pushed_at":"2026-09-05T16:11:52+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/p-e-w-heretic","markdown_url":"https://www.graphcanon.com/tools/p-e-w-heretic.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/p-e-w-heretic","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=p-e-w-heretic","shared_categories":[]},{"slug":"microsoft-semantic-kernel","name":"semantic-kernel","tagline":"Integrate cutting-edge LLM technology quickly and easily into your apps","github_url":"https://github.com/microsoft/semantic-kernel","owner":"microsoft","repo":"semantic-kernel","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"C#","stars":28575,"forks":4774,"topics":["ai","artificial-intelligence","llm","openai","sdk"],"archived":false,"github_pushed_at":"2026-09-18T01:35:01+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/microsoft-semantic-kernel","markdown_url":"https://www.graphcanon.com/tools/microsoft-semantic-kernel.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-semantic-kernel","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-semantic-kernel","shared_categories":[]},{"slug":"huggingface-tokenizers","name":"tokenizers","tagline":"Fast State-of-the-Art Tokenizers optimized for Research and Production","github_url":"https://github.com/huggingface/tokenizers","owner":"huggingface","repo":"tokenizers","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Rust","stars":11047,"forks":1201,"topics":["bert","gpt","language-model","natural-language-processing","natural-language-understanding","nlp","transformers"],"archived":false,"github_pushed_at":"2026-09-18T08:07:38+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-tokenizers","markdown_url":"https://www.graphcanon.com/tools/huggingface-tokenizers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-tokenizers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-tokenizers","shared_categories":["model-training"]},{"slug":"espnet-espnet","name":"espnet","tagline":"End-to-End Speech Processing Toolkit","github_url":"https://github.com/espnet/espnet","owner":"espnet","repo":"espnet","owner_avatar_url":"https://avatars.githubusercontent.com/u/34493687?v=4","primary_language":"Python","stars":9963,"forks":2435,"topics":["chainer","deep-learning","end-to-end","kaldi","machine-translation","pytorch","singing-voice-synthesis","speaker-diarization","speech-enhancement","speech-recognition","speech-separation","speech-synthesis","speech-translation","spoken-language-understanding","text-to-speech","voice-conversion"],"archived":false,"github_pushed_at":"2026-09-20T05:11:59+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/espnet-espnet","markdown_url":"https://www.graphcanon.com/tools/espnet-espnet.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/espnet-espnet","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=espnet-espnet","shared_categories":["model-training"]},{"slug":"madcowd-ell","name":"ell","tagline":"A language model programming library","github_url":"https://github.com/MadcowD/ell","owner":"MadcowD","repo":"ell","owner_avatar_url":"https://avatars.githubusercontent.com/u/719535?v=4","primary_language":"Python","stars":5857,"forks":341,"topics":["ai","prompt-engineering"],"archived":false,"github_pushed_at":"2025-06-05T21:41:57+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/madcowd-ell","markdown_url":"https://www.graphcanon.com/tools/madcowd-ell.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/madcowd-ell","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=madcowd-ell","shared_categories":[]},{"slug":"qdrant-fastembed","name":"fastembed","tagline":"Fast, Accurate, Lightweight Python library for creating state-of-the-art embeddings","github_url":"https://github.com/qdrant/fastembed","owner":"qdrant","repo":"fastembed","owner_avatar_url":"https://avatars.githubusercontent.com/u/73504361?v=4","primary_language":"Python","stars":3211,"forks":249,"topics":["embeddings","openai","rag","retrieval","retrieval-augmented-generation","vector-search"],"archived":false,"github_pushed_at":"2026-09-16T10:46:46+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/qdrant-fastembed","markdown_url":"https://www.graphcanon.com/tools/qdrant-fastembed.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/qdrant-fastembed","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=qdrant-fastembed","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":1442,"forks":47,"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":"2026-10-03T05:16:34+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":"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":1349,"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"]},{"slug":"bheinzerling-bpemb","name":"bpemb","tagline":"Pre-trained subword embeddings in 275 languages using Byte-Pair Encoding","github_url":"https://github.com/bheinzerling/bpemb","owner":"bheinzerling","repo":"bpemb","owner_avatar_url":"https://avatars.githubusercontent.com/u/4348795?v=4","primary_language":"Python","stars":1224,"forks":100,"topics":["embeddings","multilingual","natural-language-processing","nlp","subword-embeddings"],"archived":false,"github_pushed_at":"2024-10-01T02:49:47+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/bheinzerling-bpemb","markdown_url":"https://www.graphcanon.com/tools/bheinzerling-bpemb.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bheinzerling-bpemb","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bheinzerling-bpemb","shared_categories":["data-retrieval"]},{"slug":"tencent-tencentpretrain","name":"TencentPretrain","tagline":"Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo","github_url":"https://github.com/Tencent/TencentPretrain","owner":"Tencent","repo":"TencentPretrain","owner_avatar_url":"https://avatars.githubusercontent.com/u/18461506?v=4","primary_language":"Python","stars":1093,"forks":148,"topics":["albert","bart","bert","chinese","classification","clue","elmo","fine-tuning","gpt","gpt-2","model-zoo","natural-language-processing","ner","pegasus","pre-training","pytorch","roberta","t5","unilm","xlm-roberta"],"archived":false,"github_pushed_at":"2024-08-04T11:53:43+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/tencent-tencentpretrain","markdown_url":"https://www.graphcanon.com/tools/tencent-tencentpretrain.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tencent-tencentpretrain","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tencent-tencentpretrain","shared_categories":["model-training"]},{"slug":"keyvank-femtogpt","name":"femtoGPT","tagline":"Pure Rust implementation of a minimal Generative Pretrained Transformer","github_url":"https://github.com/keyvank/femtoGPT","owner":"keyvank","repo":"femtoGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/4275654?v=4","primary_language":"Rust","stars":936,"forks":67,"topics":["from-scratch","gpt","gpu","hacktoberfest","llm","machine-learning","neural-network","opencl","rust"],"archived":false,"github_pushed_at":"2025-10-21T11:13:42+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/keyvank-femtogpt","markdown_url":"https://www.graphcanon.com/tools/keyvank-femtogpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/keyvank-femtogpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=keyvank-femtogpt","shared_categories":["model-training"]},{"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":769,"forks":118,"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","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","shared_categories":["model-training","data-retrieval"]}]}}