{"data":{"slug":"nebuly-ai-optimate","name":"optimate","tagline":"A collection of libraries to optimize AI model performances","github_url":"https://github.com/nebuly-ai/optimate","owner":"nebuly-ai","repo":"optimate","owner_avatar_url":"https://avatars.githubusercontent.com/u/83510798?v=4","primary_language":"Python","stars":8329,"forks":617,"topics":["ai","analytics","artificial-intelligence","deeplearning","large-language-models","llm"],"archived":false,"github_pushed_at":"2024-07-22T02:07:03+00:00","maintenance_label":"Dormant","stars_delta_30d":-3,"url":"https://www.graphcanon.com/tools/nebuly-ai-optimate","markdown_url":"https://www.graphcanon.com/tools/nebuly-ai-optimate.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nebuly-ai-optimate","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nebuly-ai-optimate","description":"A collection of libraries to optimise AI model performances","homepage_url":"https://www.nebuly.com/","license":"Apache-2.0","open_issues":110,"watchers":88,"ai_summary":"OptiMate is a legacy repository containing open-source tools for optimizing AI models with a focus on reducing inference, infrastructure, hardware, and data costs. The project includes Speedster, Nos, and ChatLLaMA.","readme_excerpt":"# OptiMate\n\n**[Legacy]**\n\nThis repository is now in a legacy phase and is no longer actively maintained. Although the source code is still available in the Git history, there will be no additional updates or official support.\n\n**[About Nebuly]**\n\nOur team is fully committed on creating the best user-experience platform for LLMs so that companies can understand user behavior at scale when interacting with their LLM-based products. \n- To learn more on how to get started, visit our [official documentation](https://docs.nebuly.com/welcome/overview)\n- If you need enterprise support, please contact us [here](https://www.nebuly.com/nebuly-book-a-demo)\n\n**[About optimate]**\n\nWe have open-sourced a couple of internal projects to the community, but we are not currently maintaining them. Optimate is a collection of libraries designed to help you optimize your AI models. It is an open-source project developed by Nebuly AI but is **not actively maintained**.\n\nThe tools available to assist you in your optimization are:\n\n✅ [Speedster](https://github.com/nebuly-ai/optimate/tree/main/optimization/speedster): reduce inference costs by leveraging SOTA optimization techniques that best couple your AI models with the underlying hardware (GPUs and CPUs)\n\n✅ [Nos](https://github.com/nebuly-ai/nos): reduce infrastructure costs by leveraging real-time dynamic partitioning and elastic quotas to maximize the utilization of your Kubernetes GPU cluster\n\n✅ [ChatLLaMA](https://github.com/nebuly-ai/optimate/tree/main/optimization/chatllama): reduce hardware and data costs by leveraging fine-tuning optimization techniques and RLHF alignment","github_created_at":"2022-02-12T17:17:14+00:00","created_at":"2026-07-07T17:34:18.291327+00:00","updated_at":"2026-08-17T06:02:12.883392+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"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":"ai","name":"ai"},{"slug":"analytics","name":"analytics"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"deeplearning","name":"deeplearning"},{"slug":"large-language-models","name":"large language models"},{"slug":"llm","name":"llm"}],"trust":{"provenance":{"is_fork":false,"github_id":458588993,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T06:02:12.072Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":756,"last_release_at":"2023-03-27T13:47:20Z","stars_delta_30d":-3,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:02:56.523Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T06:02:12.540Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-17T06:02:12.540Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-17T06:02:12.540Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need optimization techniques for enhancing inference costs by leveraging state-of-the-art approaches that couple your AI models with hardware like GPUs and CPUs through tools such as Speedスター","For companies still using Kubernetes GPU clusters, if reducing infrastructure costs via real-time dynamic partitioning is essential, Nos could still provide value despite its legacy status"],"when_not_to_use":["Do not use OptiMate if you need ongoing support or active development. The project has moved into a legacy phase and receives no further updates","Avoid using OptiMate for future AI deployment if you are aiming to integrate state-of-the-art real-time observability features as it's no longer actively maintained nor receiving new improvements"],"source":"enrich:decision_facts","observed_at":"2026-07-09T08:03:21.109Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"OptiMate is a collection of open-source libraries in Python designed to optimize the performance and resource utilization of AI models, though it now operates in a legacy phase meaning no further updates or official code"}]}}