[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-da7cf503":3,"seo:featured-workflow:da7cf503-4ddd-11f1-9bc6-00163e2b0d79:es":84,"workflow-related-asset-da7cf503-da7cf503-4ddd-11f1-9bc6-00163e2b0d79":85},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":13,"parent_id":12,"parent_uuid":11,"lang_type":14,"steps":15,"tags":21,"has_voted":27,"visibility":13,"share_token":11,"is_featured":12,"content_hash":28,"asset_kind":29,"target_tools":30,"install_mode":34,"entrypoint":18,"risk_profile":35,"dependencies":37,"verification":43,"agent_metadata":46,"agent_fit":59,"trust":71,"provenance":80,"created_at":82,"updated_at":83},3251,"da7cf503-4ddd-11f1-9bc6-00163e2b0d79","asset-da7cf503","Nevergrad — Gradient-Free Optimization by Meta","Nevergrad is a gradient-free optimization platform from Meta Research providing a unified interface to derivative-free optimizers for hyperparameter tuning, reinforcement learning, and scientific computing.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot","",0,1,"en",[16],{"id":17,"step_order":13,"title":18,"description":11,"prompt_template":19,"variables":11,"depends_on":20,"expected_output":11},3814,"Nevergrad Optimization","# Nevergrad — Gradient-Free Optimization by Meta\n\n## Quick Use\n```bash\npip install nevergrad\npython -c \"\nimport nevergrad as ng\ndef sphere(x):\n    return sum(xi**2 for xi in x)\noptimizer = ng.optimizers.NGOpt(parametrization=ng.p.Array(shape=(3,)), budget=100)\nrecommendation = optimizer.minimize(sphere)\nprint(recommendation.value)\n\"\n```\n\n## Introduction\nNevergrad is a Python library from Meta AI Research that provides gradient-free optimization algorithms under a common interface. It is designed for problems where gradients are unavailable or unreliable, such as hyperparameter tuning, reinforcement learning reward shaping, and simulation-based optimization.\n\n## What Nevergrad Does\n- Optimizes black-box functions without requiring gradients\n- Provides 30+ optimization algorithms under a unified API\n- Supports continuous, discrete, and mixed search spaces\n- Offers built-in benchmarks for comparing optimizer performance\n- Handles noisy objective functions with appropriate averaging\n\n## Architecture Overview\nNevergrad defines a Parametrization system that describes the search space (scalars, arrays, choices, log-scales). An Optimizer wraps a specific algorithm (CMA-ES, differential evolution, PSO, etc.) and generates candidates via ask\u002Ftell. The ask method proposes parameter values; tell reports back the loss. This separation allows asynchronous and parallel evaluation.\n\n## Self-Hosting & Configuration\n- Install via pip with no heavy dependencies\n- Define search spaces using ng.p.Scalar, ng.p.Array, or ng.p.Choice\n- Select an optimizer or use NGOpt for automatic algorithm selection\n- Set budget to control the total number of objective evaluations\n- Use num_workers > 1 to evaluate candidates in parallel batches\n\n## Key Features\n- NGOpt meta-optimizer automatically picks the best algorithm for your problem\n- Expressive parametrization supporting constraints and transformations\n- Ask\u002Ftell interface enables asynchronous and distributed evaluation\n- Built-in benchmarking suite for rigorous optimizer comparison\n- Supports multi-objective optimization via Pareto front tracking\n\n## Comparison with Similar Tools\n- **Optuna** — Bayesian optimization with pruning for ML; Nevergrad covers broader optimization use cases beyond ML\n- **Hyperopt** — TPE-based search for hyperparameters; Nevergrad offers more diverse algorithms\n- **scipy.optimize** — classical numerical optimization; Nevergrad handles noisy, non-differentiable objectives\n- **Ray Tune** — orchestrates trials at scale; Nevergrad focuses on the optimization algorithms themselves\n\n## FAQ\n**Q: What is NGOpt?**\nA: NGOpt is a meta-optimizer that selects the best algorithm based on your problem characteristics (budget, dimensionality, noise level).\n\n**Q: Can Nevergrad optimize discrete variables?**\nA: Yes. Use ng.p.Choice for categorical variables and ng.p.TransitionChoice for ordered discrete parameters.\n\n**Q: How do I run evaluations in parallel?**\nA: Set num_workers and call ask() multiple times before calling tell() with results as they arrive.\n\n**Q: Does Nevergrad support constraints?**\nA: Yes. Apply register_cheap_constraint to penalize infeasible regions of the search space.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fnevergrad\n- https:\u002F\u002Ffacebookresearch.github.io\u002Fnevergrad\u002F","0",[22],{"id":23,"name":24,"slug":25,"icon":26},11,"Scripts","script","📜",false,"779f55d897fb9dd8d0874a249079bc1b2d0725c586d38ebaa8fac07bd4b83409","skill",[31,32,33],"claude_code","codex","gemini_cli","single",{"executes_code":27,"modifies_global_config":27,"requires_secrets":36,"uses_absolute_paths":27,"network_access":27},[],{"npm":38,"pip":39,"brew":41,"system":42},[],[40],"nevergrad",[],[],{"commands":44,"expected_files":45},[],[18],{"asset_kind":29,"target_tools":47,"install_mode":34,"entrypoint":18,"risk_profile":48,"dependencies":50,"content_hash":28,"verification":55,"inferred":58},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":49,"uses_absolute_paths":27,"network_access":27},[],{"npm":51,"pip":52,"brew":53,"system":54},[],[40],[],[],{"commands":56,"expected_files":57},[],[18],true,{"target":32,"score":60,"status":61,"policy":62,"why":63,"asset_kind":29,"install_mode":34},98,"native","allow",[64,65,66,67,68,69,70],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":28,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":74,"review_status":75,"signals":76},"established","hash_only",[],"unreviewed",[77,78,79],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":81,"content_hash":28,"visibility":13,"created_at":82,"updated_at":83},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-da7cf503","2026-05-12 16:37:47","2026-05-12 17:42:52",null,[86,139,186,233],{"id":87,"uuid":88,"slug":89,"title":90,"description":91,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":92,"parent_id":12,"parent_uuid":11,"lang_type":14,"steps":93,"tags":94,"has_voted":27,"visibility":13,"share_token":11,"is_featured":12,"content_hash":96,"asset_kind":29,"target_tools":97,"install_mode":34,"entrypoint":98,"risk_profile":99,"dependencies":101,"verification":106,"agent_metadata":109,"agent_fit":121,"trust":123,"provenance":127,"created_at":129,"updated_at":130,"__relatedScore":131,"__relatedReasons":132,"__sharedTags":137},1994,"c9a9b225-3ecd-11f1-9bc6-00163e2b0d79","lmms-free-cross-platform-digital-audio-workstation-c9a9b225","LMMS — Free Cross-Platform Digital Audio Workstation","LMMS (Linux MultiMedia Studio) is a free, open-source digital audio workstation for music production. It includes synthesizers, sample playback, beat sequencing, and an effects chain, providing a complete environment for creating music without any cost.",105,[],[95],{"id":23,"name":24,"slug":25,"icon":26},"d5d64c9355a222a9ff6c2b5cc564c8bfcd532c75f32862e0a4aee739e3e8f986",[31,32,33],"LMMS Overview",{"executes_code":27,"modifies_global_config":27,"requires_secrets":100,"uses_absolute_paths":27,"network_access":27},[],{"npm":102,"pip":103,"brew":104,"system":105},[],[],[],[],{"commands":107,"expected_files":108},[],[98],{"asset_kind":29,"target_tools":110,"install_mode":34,"entrypoint":98,"risk_profile":111,"dependencies":113,"content_hash":96,"verification":118},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":112,"uses_absolute_paths":27,"network_access":27},[],{"npm":114,"pip":115,"brew":116,"system":117},[],[],[],[],{"commands":119,"expected_files":120},[],[98],{"target":32,"score":60,"status":61,"policy":62,"why":122,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":96,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":124,"review_status":75,"signals":125},[],[126,77,78,79],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":128,"content_hash":96,"visibility":13,"created_at":129,"updated_at":130},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Flmms-free-cross-platform-digital-audio-workstation-c9a9b225","2026-04-23 12:34:59","2026-05-12 18:44:00",89.03795879789716,[133,134,135,136],"topic-match","same-kind","same-target","same-author",[25,138],"scripts",{"id":140,"uuid":141,"slug":142,"title":143,"description":144,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":145,"parent_id":12,"parent_uuid":11,"lang_type":14,"steps":146,"tags":147,"has_voted":27,"visibility":13,"share_token":11,"is_featured":12,"content_hash":149,"asset_kind":29,"target_tools":150,"install_mode":34,"entrypoint":151,"risk_profile":152,"dependencies":154,"verification":159,"agent_metadata":162,"agent_fit":174,"trust":176,"provenance":179,"created_at":181,"updated_at":182,"__relatedScore":183,"__relatedReasons":184,"__sharedTags":185},1910,"d13939ab-3d9c-11f1-9bc6-00163e2b0d79","xgboost-scalable-gradient-boosting-machine-learning-d13939ab","XGBoost — Scalable Gradient Boosting for Machine Learning","XGBoost is an optimized distributed gradient boosting library for supervised learning tasks. It provides highly efficient implementations of gradient boosted trees for classification, regression, and ranking across CPU and GPU with bindings for Python, R, Java, and more.",68,[],[148],{"id":23,"name":24,"slug":25,"icon":26},"73277125d55eafa42266d1234fc23eb0a4de2bd76d0dbfdaec679d68e5b0ea66",[31,32,33],"XGBoost ML",{"executes_code":27,"modifies_global_config":27,"requires_secrets":153,"uses_absolute_paths":27,"network_access":27},[],{"npm":155,"pip":156,"brew":157,"system":158},[],[],[],[],{"commands":160,"expected_files":161},[],[151],{"asset_kind":29,"target_tools":163,"install_mode":34,"entrypoint":151,"risk_profile":164,"dependencies":166,"content_hash":149,"verification":171},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":165,"uses_absolute_paths":27,"network_access":27},[],{"npm":167,"pip":168,"brew":169,"system":170},[],[],[],[],{"commands":172,"expected_files":173},[],[151],{"target":32,"score":60,"status":61,"policy":62,"why":175,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":149,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":177,"review_status":75,"signals":178},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":180,"content_hash":149,"visibility":13,"created_at":181,"updated_at":182},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fxgboost-scalable-gradient-boosting-machine-learning-d13939ab","2026-04-22 00:11:55","2026-05-12 13:29:53",85.75827363610588,[133,134,135,136],[25,138],{"id":187,"uuid":188,"slug":189,"title":190,"description":191,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":192,"parent_id":12,"parent_uuid":11,"lang_type":14,"steps":193,"tags":194,"has_voted":27,"visibility":13,"share_token":11,"is_featured":12,"content_hash":196,"asset_kind":29,"target_tools":197,"install_mode":34,"entrypoint":198,"risk_profile":199,"dependencies":201,"verification":206,"agent_metadata":209,"agent_fit":221,"trust":223,"provenance":226,"created_at":228,"updated_at":229,"__relatedScore":230,"__relatedReasons":231,"__sharedTags":232},3073,"dd235d25-4d54-11f1-9bc6-00163e2b0d79","asset-dd235d25","draw.io — Free Open-Source Diagramming Tool for Any Platform","draw.io is a free, browser-based diagramming application that supports flowcharts, UML, network diagrams, and more. Works offline as a desktop app on Windows, macOS, and Linux with no account required.",27,[],[195],{"id":23,"name":24,"slug":25,"icon":26},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[31,32,33],"SKILL.md",{"executes_code":27,"modifies_global_config":27,"requires_secrets":200,"uses_absolute_paths":27,"network_access":27},[],{"npm":202,"pip":203,"brew":204,"system":205},[],[],[],[],{"commands":207,"expected_files":208},[],[],{"asset_kind":29,"target_tools":210,"install_mode":34,"entrypoint":198,"risk_profile":211,"dependencies":213,"content_hash":196,"verification":218,"inferred":58},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":212,"uses_absolute_paths":27,"network_access":27},[],{"npm":214,"pip":215,"brew":216,"system":217},[],[],[],[],{"commands":219,"expected_files":220},[],[],{"target":32,"score":60,"status":61,"policy":62,"why":222,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":196,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":224,"review_status":75,"signals":225},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":227,"content_hash":196,"visibility":13,"created_at":228,"updated_at":229},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-dd235d25","2026-05-12 00:17:10","2026-05-12 18:45:25",85.17073704701333,[133,134,135,136],[25,138],{"id":234,"uuid":235,"slug":236,"title":237,"description":238,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":239,"parent_id":12,"parent_uuid":11,"lang_type":14,"steps":240,"tags":241,"has_voted":27,"visibility":13,"share_token":11,"is_featured":12,"content_hash":243,"asset_kind":29,"target_tools":244,"install_mode":34,"entrypoint":245,"risk_profile":246,"dependencies":248,"verification":253,"agent_metadata":256,"agent_fit":268,"trust":270,"provenance":273,"created_at":275,"updated_at":276,"__relatedScore":277,"__relatedReasons":278,"__sharedTags":279},2236,"abc06a3b-4236-11f1-9bc6-00163e2b0d79","akaunting-free-self-hosted-accounting-software-abc06a3b","Akaunting — Free Self-Hosted Accounting Software","A free, open-source online accounting application built on Laravel for small businesses and freelancers to manage invoices, expenses, and financial reports.",130,[],[242],{"id":23,"name":24,"slug":25,"icon":26},"a558f02c69a2e9a935eebf974abcb45db64d869beb8777982d75c7e1a7cb180b",[31,32,33],"Akaunting",{"executes_code":27,"modifies_global_config":27,"requires_secrets":247,"uses_absolute_paths":27,"network_access":27},[],{"npm":249,"pip":250,"brew":251,"system":252},[],[],[],[],{"commands":254,"expected_files":255},[],[245],{"asset_kind":29,"target_tools":257,"install_mode":34,"entrypoint":245,"risk_profile":258,"dependencies":260,"content_hash":243,"verification":265},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":259,"uses_absolute_paths":27,"network_access":27},[],{"npm":261,"pip":262,"brew":263,"system":264},[],[],[],[],{"commands":266,"expected_files":267},[],[245],{"target":32,"score":60,"status":61,"policy":62,"why":269,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":243,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":271,"review_status":75,"signals":272},[],[126,77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":274,"content_hash":243,"visibility":13,"created_at":275,"updated_at":276},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fakaunting-free-self-hosted-accounting-software-abc06a3b","2026-04-27 20:43:20","2026-05-12 18:50:53",83.17590694348365,[133,134,135,136],[25,138]]