{"data":{"node":{"slug":"jasonwei20-eda-nlp","name":"eda_nlp","tagline":"Data augmentation for NLP","github_url":"https://github.com/jasonwei20/eda_nlp","owner":"jasonwei20","repo":"eda_nlp","owner_avatar_url":"https://avatars.githubusercontent.com/u/26695953?v=4","primary_language":"Python","stars":1652,"forks":311,"topics":["classification","cnn","data-augmentation","embeddings","nlp","position","rnn","sentence","swap","synonyms","text-classification"],"archived":false,"github_pushed_at":"2023-03-19T21:39:48+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/jasonwei20-eda-nlp","markdown_url":"https://www.graphcanon.com/tools/jasonwei20-eda-nlp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jasonwei20-eda-nlp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jasonwei20-eda-nlp"},"categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"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":"classification","name":"classification"},{"slug":"cnn","name":"cnn"},{"slug":"data-augmentation","name":"data-augmentation"},{"slug":"embeddings","name":"embeddings"},{"slug":"nlp","name":"nlp"},{"slug":"position","name":"position"},{"slug":"rnn","name":"rnn"},{"slug":"sentence","name":"sentence"}],"edges":[],"neighbours":[{"slug":"blader-humanizer","name":"humanizer","tagline":"A tool to remove signs of AI-generated text","github_url":"https://github.com/blader/humanizer","owner":"blader","repo":"humanizer","owner_avatar_url":"https://avatars.githubusercontent.com/u/1672?v=4","primary_language":"Python","stars":33808,"forks":3049,"topics":["agent-skills","ai-writing","claude-code","codex","cursor","prompt-engineering","writing-tools"],"archived":false,"github_pushed_at":"2026-07-22T06:26:25+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/blader-humanizer","markdown_url":"https://www.graphcanon.com/tools/blader-humanizer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/blader-humanizer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=blader-humanizer","shared_categories":["developer-tools"]},{"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"]},{"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":[]},{"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"]},{"slug":"elyase-awesome-gpt3","name":"awesome-gpt3","tagline":"A collection of demos and articles about the OpenAI GPT-3 API","github_url":"https://github.com/elyase/awesome-gpt3","owner":"elyase","repo":"awesome-gpt3","owner_avatar_url":"https://avatars.githubusercontent.com/u/1175888?v=4","primary_language":null,"stars":4520,"forks":345,"topics":[],"archived":true,"github_pushed_at":"2023-08-27T11:46:48+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/elyase-awesome-gpt3","markdown_url":"https://www.graphcanon.com/tools/elyase-awesome-gpt3.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/elyase-awesome-gpt3","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=elyase-awesome-gpt3","shared_categories":["model-training"]},{"slug":"nyldn-claude-octopus","name":"claude-octopus","tagline":"Surface AI blindspots before you ship","github_url":"https://github.com/nyldn/claude-octopus","owner":"nyldn","repo":"claude-octopus","owner_avatar_url":"https://avatars.githubusercontent.com/u/4805949?v=4","primary_language":"Shell","stars":3962,"forks":374,"topics":["ai-agents","ai-orchestration","claude-code","claude-code-plugin","codex","copilot","developer-tools","double-diamond","gemini","multi-ai","multi-llm","ollama"],"archived":false,"github_pushed_at":"2026-08-13T23:28:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/nyldn-claude-octopus","markdown_url":"https://www.graphcanon.com/tools/nyldn-claude-octopus.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nyldn-claude-octopus","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nyldn-claude-octopus","shared_categories":["developer-tools"]},{"slug":"conorbronsdon-avoid-ai-writing","name":"avoid-ai-writing","tagline":"Audits and rewrites content to eliminate AI writing patterns","github_url":"https://github.com/conorbronsdon/avoid-ai-writing","owner":"conorbronsdon","repo":"avoid-ai-writing","owner_avatar_url":"https://avatars.githubusercontent.com/u/120674402?v=4","primary_language":"JavaScript","stars":2655,"forks":243,"topics":["ai-writing","claude","claude-code","llm","prompt-engineering","skill","writing"],"archived":false,"github_pushed_at":"2026-07-22T17:56:19+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/conorbronsdon-avoid-ai-writing","markdown_url":"https://www.graphcanon.com/tools/conorbronsdon-avoid-ai-writing.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/conorbronsdon-avoid-ai-writing","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=conorbronsdon-avoid-ai-writing","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":[]},{"slug":"datadreamer-dev-datadreamer","name":"DataDreamer","tagline":"Prompt. Generate Synthetic Data. Train & Align Models.","github_url":"https://github.com/datadreamer-dev/DataDreamer","owner":"datadreamer-dev","repo":"DataDreamer","owner_avatar_url":"https://avatars.githubusercontent.com/u/154913957?v=4","primary_language":"Python","stars":1117,"forks":58,"topics":["alignment","deep-learning","fine-tuning","gpt","instruction-tuning","llm","llmops","llms","machine-learning","natural-language-processing","nlp","nlp-library","openai","python","pytorch","synthetic-data","synthetic-dataset-generation","transformers"],"archived":false,"github_pushed_at":"2025-02-02T21:23:50+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/datadreamer-dev-datadreamer","markdown_url":"https://www.graphcanon.com/tools/datadreamer-dev-datadreamer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datadreamer-dev-datadreamer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datadreamer-dev-datadreamer","shared_categories":["model-training"]},{"slug":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","shared_categories":["model-training"]},{"slug":"rohan-paul-llm-finetuning-large-language-models","name":"LLM-FineTuning-Large-Language-Models","tagline":"LLM FineTuning","github_url":"https://github.com/rohan-paul/LLM-FineTuning-Large-Language-Models","owner":"rohan-paul","repo":"LLM-FineTuning-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/12703975?v=4","primary_language":"Jupyter Notebook","stars":577,"forks":136,"topics":["gpt-3","gpt3-turbo","large-language-models","llama2","llm","llm-finetuning","llm-inference","llm-serving","llm-training","mistral-7b","open-source-llm","pytorch"],"archived":false,"github_pushed_at":"2025-04-01T21:05:06+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rohan-paul-llm-finetuning-large-language-models","markdown_url":"https://www.graphcanon.com/tools/rohan-paul-llm-finetuning-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rohan-paul-llm-finetuning-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rohan-paul-llm-finetuning-large-language-models","shared_categories":["model-training"]},{"slug":"curated-awesome-lists-awesome-llms-fine-tuning","name":"awesome-llms-fine-tuning","tagline":"A comprehensive collection of resources for fine-tuning Large Language Models.","github_url":"https://github.com/Curated-Awesome-Lists/awesome-llms-fine-tuning","owner":"Curated-Awesome-Lists","repo":"awesome-llms-fine-tuning","owner_avatar_url":"https://avatars.githubusercontent.com/u/142611331?v=4","primary_language":null,"stars":525,"forks":79,"topics":["ai","awesome-list","deep-learning","fine-tuning","gpt","large-language-models","llms","machine-learning","nlp","transformers"],"archived":false,"github_pushed_at":"2024-12-02T20:11:14+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning","markdown_url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/curated-awesome-lists-awesome-llms-fine-tuning","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=curated-awesome-lists-awesome-llms-fine-tuning","shared_categories":["model-training"]}]}}