{"data":{"slug":"pku-alignment-align-anything","name":"align-anything","tagline":"Training All-modality Model with Feedback","github_url":"https://github.com/PKU-Alignment/align-anything","owner":"PKU-Alignment","repo":"align-anything","owner_avatar_url":"https://avatars.githubusercontent.com/u/129283536?v=4","primary_language":"Python","stars":4666,"forks":505,"topics":["chameleon","dpo","large-language-models","multimodal","rlhf","vision-language-model"],"archived":false,"github_pushed_at":"2025-11-27T06:50:36+00:00","maintenance_label":"Slowing","stars_delta_30d":4,"url":"https://www.graphcanon.com/tools/pku-alignment-align-anything","markdown_url":"https://www.graphcanon.com/tools/pku-alignment-align-anything.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pku-alignment-align-anything","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pku-alignment-align-anything","description":"Align Anything: Training All-modality Model with Feedback","homepage_url":null,"license":"Apache-2.0","open_issues":32,"watchers":266,"ai_summary":"Developed for training large, all-modality models using feedback mechanisms including Reinforcement Learning from Human Feedback (RLHF) and Data Programming Optimization (DPO). Supports a wide array of data types and modalities for alignment purposes.","readme_excerpt":"# License\n\nalign-anything is released under Apache License 2.0.","github_created_at":"2024-07-14T11:05:19+00:00","created_at":"2026-07-07T17:35:06.512252+00:00","updated_at":"2026-08-17T12:01:30.990884+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":"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":"chameleon","name":"chameleon"},{"slug":"dpo","name":"dpo"},{"slug":"large-language-models","name":"large language models"},{"slug":"multimodal","name":"multimodal"},{"slug":"rlhf","name":"rlhf"},{"slug":"vision-language-model","name":"vision-language-model"}],"trust":{"provenance":{"is_fork":false,"github_id":828505099,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T12:01:30.138Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":263,"last_release_at":null,"stars_delta_30d":4,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:04:53.871Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T12:01:30.607Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-17T12:01:30.607Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-17T12:01:30.607Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-17T12:01:30.607Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-17T12:01:30.607Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python execution environment"]},"constraints":null,"when_to_use":["- When you are developing a model that requires feedback from human evaluators and needs to handle different types of data (multimodal).","- If your project involves visual-textual or language-only large models requiring Reinforcement Learning from Human Feedback (RLHF) and Data Programming Optimization (DPO)."],"when_not_to_use":["- When the model training does not benefit from advanced feedback mechanisms like RLHF or DPO.","- For projects that do not require support for multiple data modalities."],"source":"enrich:decision_facts","observed_at":"2026-07-12T17:56:34.114Z"},"constraint_facets":null,"decision_summary":[{"label":"Requirements","value":"Python execution environment"},{"label":"Adopt for","value":"Align Anything focuses on training large models with multiple forms of feedback across various data modalities, leveraging RLHF and DPO."},{"label":"License detail","value":"This tool operates under Apache License 2.0, allowing free use, modification, and distribution provided copyright notices are preserved."}]}}