{"data":{"slug":"lightly-ai-lightly","name":"lightly","tagline":"A python library for self-supervised learning on images.","github_url":"https://github.com/lightly-ai/lightly","owner":"lightly-ai","repo":"lightly","owner_avatar_url":"https://avatars.githubusercontent.com/u/50146475?v=4","primary_language":"Python","stars":3812,"forks":367,"topics":["computer-vision","contrastive-learning","contributions-welcome","deep-learning","embeddings","hacktoberfest","machine-learning","pytorch","self-supervised-learning"],"archived":false,"github_pushed_at":"2026-09-18T21:02:58+00:00","maintenance_label":"Very active","stars_delta_30d":28,"url":"https://www.graphcanon.com/tools/lightly-ai-lightly","markdown_url":"https://www.graphcanon.com/tools/lightly-ai-lightly.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lightly-ai-lightly","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lightly-ai-lightly","description":"A python library for self-supervised learning on images.","homepage_url":"https://docs.lightly.ai/self-supervised-learning/","license":"MIT","open_issues":107,"watchers":29,"ai_summary":"Provides tools and utilities to perform self-supervised learning, particularly aimed at image data which is critical for enhancing model performance in computer vision tasks without requiring labeled datasets.","readme_excerpt":"## Quick Start\n\nLightly requires **Python 3.8+**. We recommend installing Lightly in a **Linux** or **OSX** environment. Python 3.13 is not yet supported, as PyTorch itself lacks Python 3.13 compatibility.\n\n---\n\n### Installation\n\nYou can install Lightly and its dependencies from PyPI with:\n\n```\npip3 install lightly\n```\n\nWe strongly recommend installing Lightly in a dedicated virtualenv to avoid conflicts with your system packages.","github_created_at":"2020-10-13T13:02:56+00:00","created_at":"2026-07-11T11:28:55.869233+00:00","updated_at":"2026-09-20T06:10:31.304266+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"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":"computer-vision","name":"computer-vision"},{"slug":"contrastive-learning","name":"contrastive-learning"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"embeddings","name":"embeddings"},{"slug":"self-supervised-learning","name":"self-supervised-learning"}],"trust":{"provenance":{"is_fork":false,"github_id":303705119,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:10:28.622Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":1,"last_release_at":"2026-07-27T17:39:36Z","stars_delta_30d":28,"open_issues_delta_30d":14},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:28:57.175Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:10:29.822Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T06:10:29.822Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T06:10:29.822Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T06:10:29.822Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need to enhance model performance with unlabeled image data.","Your project benefits from modern contrastive-learning techniques."],"when_not_to_use":["Labeled datasets are abundant and of high quality for your use case.","Project requirements strictly limit the use of Python-based libraries."],"source":"enrich:decision_facts","observed_at":"2026-07-12T12:52:56.461Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Lightly specializes in self-supervised learning for image data to improve computer vision models without labeled datasets."}]}}