{"id":11693387,"name":"github.com/NVIDIA/NeMo-Curator","ecosystem":"go","description":null,"homepage":null,"licenses":"apache-2.0","normalized_licenses":["Apache-2.0"],"repository_url":"https://github.com/NVIDIA/NeMo-Curator","keywords_array":[],"namespace":null,"versions_count":13,"first_release_published_at":"2024-05-16T19:58:25.000Z","latest_release_published_at":"2026-05-12T20:10:23.000Z","latest_release_number":"v1.2.0","last_synced_at":"2026-07-26T08:01:30.717Z","created_at":"2025-05-27T08:27:15.947Z","updated_at":"2026-10-04T20:59:57.185Z","registry_url":"https://pkg.go.dev/github.com/NVIDIA/NeMo-Curator","install_command":"go get github.com/NVIDIA/NeMo-Curator","documentation_url":"https://pkg.go.dev/github.com/NVIDIA/NeMo-Curator#section-documentation","metadata":{},"repo_metadata":{"id":227968333,"uuid":"772255271","full_name":"NVIDIA-NeMo/Curator","owner":"NVIDIA-NeMo","description":"Scalable data pre processing and curation toolkit for LLMs","archived":false,"fork":false,"pushed_at":"2026-10-01T15:19:46.000Z","size":88280,"stargazers_count":1789,"open_issues_count":300,"forks_count":342,"subscribers_count":19,"default_branch":"main","last_synced_at":"2026-10-01T15:24:20.077Z","etag":null,"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"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIA-NeMo.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","claude":null,"gemini":null,"cursor":".cursor/rules/coding-standards.mdc","copilot":".github/copilot-instructions.md","dco":null,"cla":null,"disclosure":null}},"created_at":"2024-03-14T20:41:51.000Z","updated_at":"2026-10-01T15:19:49.000Z","dependencies_parsed_at":"2026-10-01T15:39:21.285Z","dependency_job_id":null,"html_url":"https://github.com/NVIDIA-NeMo/Curator","commit_stats":null,"previous_names":["nvidia/nemo-curator","nvidia-nemo/curator","nvidia-nemo/nemo-curator"],"tags_count":30,"template":false,"template_full_name":null,"purl":"pkg:github/NVIDIA-NeMo/Curator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-NeMo%2FCurator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-NeMo%2FCurator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-NeMo%2FCurator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-NeMo%2FCurator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA-NeMo","download_url":"https://codeload.github.com/NVIDIA-NeMo/Curator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-NeMo%2FCurator/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":342085742,"owners_count":37914263,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-10-01T02:00:06.691Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"},"owner_record":{"login":"NVIDIA","name":"NVIDIA Corporation","uuid":"1728152","kind":"organization","description":"","email":null,"website":"https://nvidia.com","location":"2788 San Tomas Expressway, Santa Clara, CA, 95051","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/1728152?v=4","repositories_count":342,"last_synced_at":"2026-10-04T17:48:11.632Z","metadata":{"has_sponsors_listing":false,"funding":null},"html_url":"https://github.com/NVIDIA","funding_links":[],"total_stars":null,"followers":31011,"following":0,"created_at":"2022-11-02T16:32:36.376Z","updated_at":"2026-10-04T17:48:11.656Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA/repositories"},"tags":[]},"repo_metadata_updated_at":"2026-10-04T20:59:57.184Z","dependent_packages_count":0,"downloads":null,"downloads_period":null,"dependent_repos_count":0,"rankings":{"downloads":null,"dependent_repos_count":5.807004531283771,"dependent_packages_count":5.441509219438237,"stargazers_count":null,"forks_count":null,"docker_downloads_count":null,"average":5.624256875361004},"purl":"pkg:golang/github.com/NVIDIA/NeMo-Curator","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/go/github.com/NVIDIA/NeMo-Curator","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/go/github.com/NVIDIA/NeMo-Curator","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/go/github.com/NVIDIA/NeMo-Curator/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2026-10-04T09:21:00.680Z","issues_count":96,"pull_requests_count":484,"avg_time_to_close_issue":6838256.470588235,"avg_time_to_close_pull_request":1050973.553846154,"issues_closed_count":34,"pull_requests_closed_count":260,"pull_request_authors_count":54,"issue_authors_count":36,"avg_comments_per_issue":1.2604166666666667,"avg_comments_per_pull_request":2.4524793388429753,"merged_pull_requests_count":206,"bot_issues_count":1,"bot_pull_requests_count":23,"past_year_issues_count":48,"past_year_pull_requests_count":242,"past_year_avg_time_to_close_issue":2824002.111111111,"past_year_avg_time_to_close_pull_request":1348628.1403508773,"past_year_issues_closed_count":18,"past_year_pull_requests_closed_count":114,"past_year_pull_request_authors_count":35,"past_year_issue_authors_count":22,"past_year_avg_comments_per_issue":1.4791666666666667,"past_year_avg_comments_per_pull_request":3.5950413223140494,"past_year_bot_issues_count":1,"past_year_bot_pull_requests_count":22,"past_year_merged_pull_requests_count":89,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA-NeMo%2FCurator/issues","maintainers":[{"login":"praateekmahajan","count":4,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/praateekmahajan"},{"login":"chtruong814","count":3,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/chtruong814"},{"login":"nithinraok","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/nithinraok"},{"login":"cdedreuille","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/cdedreuille"},{"login":"Jintao-Huang","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Jintao-Huang"}],"active_maintainers":[{"login":"nithinraok","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/nithinraok"}]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2FNVIDIA%2FNeMo-Curator/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2FNVIDIA%2FNeMo-Curator/version_numbers","latest_version_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2FNVIDIA%2FNeMo-Curator/latest_version","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2FNVIDIA%2FNeMo-Curator/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2FNVIDIA%2FNeMo-Curator/related_packages","codemeta_url":"https://packages.ecosyste.ms/api/v1/registries/proxy.golang.org/packages/github.com%2FNVIDIA%2FNeMo-Curator/codemeta","maintainers":[]}