{"data":{"slug":"nvidia-nemo-curator","name":"Curator","tagline":"Scalable data pre processing and curation toolkit for LLMs","github_url":"https://github.com/NVIDIA-NeMo/Curator","owner":"NVIDIA-NeMo","repo":"Curator","owner_avatar_url":"https://avatars.githubusercontent.com/u/213689629?v=4","primary_language":"Python","stars":1656,"forks":298,"topics":["data","data-curation","data-prep","data-preparation","data-processing","data-processing-pipelines","data-quality","datacuration","datarecipes","deduplication","fast-data-processing","fine-tuning","large-language-models","large-scale-data-processing","llm","llm-data-quality","llmapps","python","semantic-deduplication"],"archived":false,"github_pushed_at":"2026-07-11T01:00:59+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/nvidia-nemo-curator","markdown_url":"https://www.graphcanon.com/tools/nvidia-nemo-curator.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-nemo-curator","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-nemo-curator","description":"Scalable data pre processing and curation toolkit for LLMs","homepage_url":null,"license":"Apache-2.0","open_issues":279,"watchers":19,"ai_summary":null,"readme_excerpt":null,"github_created_at":"2024-03-14T20:41:51+00:00","created_at":"2026-07-11T11:39:02.079984+00:00","updated_at":"2026-07-11T11:39:04.194005+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"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":"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"}],"tags":[{"slug":"data-prep","name":"data-prep"},{"slug":"data-processing-pipelines","name":"data-processing-pipelines"},{"slug":"data","name":"data"},{"slug":"data-processing","name":"data-processing"},{"slug":"data-curation","name":"data-curation"},{"slug":"data-preparation","name":"data-preparation"},{"slug":"datacuration","name":"datacuration"},{"slug":"data-quality","name":"data-quality"}],"trust":{"provenance":{"is_fork":false,"github_id":772255271,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T11:39:02.681Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":null,"days_since_push":0,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:39:03.219Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T11:39:02.982Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T11:39:02.982Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-11T11:39:02.982Z"}}}}