[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-cc0538c6":3,"seo:featured-workflow:cc0538c6-4ddd-11f1-9bc6-00163e2b0d79:zh":83,"workflow-related-asset-cc0538c6-cc0538c6-4ddd-11f1-9bc6-00163e2b0d79":84},{"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":12,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":14,"tags":21,"has_voted":27,"visibility":17,"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":82},3250,"cc0538c6-4ddd-11f1-9bc6-00163e2b0d79","asset-cc0538c6","FLAML — Fast Lightweight AutoML by Microsoft","FLAML finds accurate machine learning models with low computational cost using a cost-frugal search strategy, supporting classification, regression, NLP, and time series tasks.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source","",0,"en",[15],{"id":16,"step_order":17,"title":18,"description":11,"prompt_template":19,"variables":11,"depends_on":20,"expected_output":11},3813,1,"FLAML AutoML","# FLAML — Fast Lightweight AutoML by Microsoft\n\n## Quick Use\n```bash\npip install \"flaml[automl]\"\npython -c \"\nfrom flaml import AutoML\nfrom sklearn.datasets import load_iris\nX, y = load_iris(return_X_y=True)\nautoml = AutoML()\nautoml.fit(X, y, task='classification', time_budget=60)\nprint(f'Best model: {automl.best_estimator}')\nprint(f'Accuracy: {automl.best_result[\"accuracy\"]:.3f}')\n\"\n```\n\n## Introduction\nFLAML (Fast and Lightweight AutoML) is a library from Microsoft Research that finds high-quality ML models at minimal cost. Its cost-frugal optimization strategy allocates more budget to promising configurations and less to unpromising ones, often matching or beating other AutoML tools in a fraction of the time.\n\n## What FLAML Does\n- Automatically selects models and tunes hyperparameters for tabular data\n- Supports classification, regression, and time-series forecasting\n- Provides a generic hyperparameter tuning API for any custom learner\n- Integrates with scikit-learn, XGBoost, LightGBM, and CatBoost\n- Optimizes within a user-specified time or iteration budget\n\n## Architecture Overview\nFLAML implements a cost-frugal search strategy called BlendSearch that combines Bayesian optimization with bandit-based pruning. It starts with cheap learners like linear models, estimates their potential, and progressively allocates budget to more expensive models like gradient boosting. The search adapts the evaluation cost dynamically based on observed performance.\n\n## Self-Hosting & Configuration\n- Install via pip with optional extras for specific learners\n- Call automl.fit() with your data, task type, and time_budget\n- Specify metric (accuracy, f1, rmse, etc.) to match your goal\n- Use estimator_list to restrict which model types are explored\n- Enable early stopping for neural network or deep learning models\n\n## Key Features\n- Cost-frugal search finds good models faster than random or grid search\n- Zero-config API that works out of the box for common tasks\n- Time-series forecasting with automated feature engineering\n- Custom learner support for integrating any estimator\n- Lightweight with minimal dependencies beyond scikit-learn\n\n## Comparison with Similar Tools\n- **Auto-sklearn** — uses Bayesian optimization with meta-learning; FLAML is faster with its cost-frugal approach\n- **TPOT** — genetic programming over pipeline structures; FLAML focuses on efficient hyperparameter search\n- **H2O AutoML** — full platform with Java backend; FLAML is pure Python and more lightweight\n- **Optuna** — general hyperparameter tuning; FLAML adds automated model selection on top\n\n## FAQ\n**Q: How does FLAML choose which model to try first?**\nA: FLAML starts with cheap learners and uses cost-aware search to decide when to move to more expensive models.\n\n**Q: Can I use FLAML for deep learning?**\nA: Yes. FLAML supports PyTorch and TensorFlow models via its custom learner interface.\n\n**Q: What is the minimum time budget?**\nA: Even 10-60 seconds can produce reasonable results on small datasets.\n\n**Q: Does FLAML support parallel trials?**\nA: Yes. Set n_concurrent_trials > 1 and optionally use Ray for distributed execution.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFLAML\n- https:\u002F\u002Fmicrosoft.github.io\u002FFLAML\u002F","0",[22],{"id":23,"name":24,"slug":25,"icon":26},12,"Configs","config","⚙️",false,"768b78a9d1dd68bb9212461d36ac3f0bc98edb1ed8b183f311a7e5784963319f","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],"flaml[automl]",[],[],{"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":17,"created_at":82,"updated_at":82},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-cc0538c6","2026-05-12 16:37:23",null,[85,138,185,238],{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"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":91,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":92,"tags":93,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":95,"asset_kind":29,"target_tools":96,"install_mode":34,"entrypoint":97,"risk_profile":98,"dependencies":100,"verification":105,"agent_metadata":108,"agent_fit":120,"trust":122,"provenance":126,"created_at":128,"updated_at":129,"__relatedScore":130,"__relatedReasons":131,"__sharedTags":136},1029,"25e2a55c-35b8-11f1-9bc6-00163e2b0d79","lit-simple-library-fast-lightweight-web-components-25e2a55c","Lit — Simple Library for Fast Lightweight Web Components","Lit is a simple library for building fast, lightweight web components. Built by Google on top of the standard Web Components APIs, it provides reactive properties, scoped styles, and a declarative templating system in about 5KB.",108,[],[94],{"id":23,"name":24,"slug":25,"icon":26},"278a6c7c3593fbefefc74f3e6d12d47323a5c1ffbf362c251fb06ab568ef65c1",[31,32,33],"SKILL.md",{"executes_code":27,"modifies_global_config":27,"requires_secrets":99,"uses_absolute_paths":27,"network_access":27},[],{"npm":101,"pip":102,"brew":103,"system":104},[],[],[],[],{"commands":106,"expected_files":107},[],[11],{"asset_kind":29,"target_tools":109,"install_mode":34,"entrypoint":97,"risk_profile":110,"dependencies":112,"content_hash":95,"verification":117},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":111,"uses_absolute_paths":27,"network_access":27},[],{"npm":113,"pip":114,"brew":115,"system":116},[],[],[],[],{"commands":118,"expected_files":119},[],[11],{"target":32,"score":60,"status":61,"policy":62,"why":121,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":95,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":123,"review_status":75,"signals":124},[],[125,77,78,79],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":127,"content_hash":95,"visibility":17,"created_at":128,"updated_at":129},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Flit-simple-library-fast-lightweight-web-components-25e2a55c","2026-04-11 23:07:25","2026-05-12 18:01:21",103.05613974691093,[132,133,134,135],"topic-match","same-kind","same-target","same-author",[25,137],"configs",{"id":139,"uuid":140,"slug":141,"title":142,"description":143,"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":144,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":145,"tags":146,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":148,"asset_kind":29,"target_tools":149,"install_mode":34,"entrypoint":150,"risk_profile":151,"dependencies":153,"verification":158,"agent_metadata":161,"agent_fit":173,"trust":175,"provenance":178,"created_at":180,"updated_at":181,"__relatedScore":182,"__relatedReasons":183,"__sharedTags":184},2207,"8e9001d7-41cf-11f1-9bc6-00163e2b0d79","uikit-lightweight-modular-front-end-framework-8e9001d7","UIkit — Lightweight Modular Front-End Framework","A lightweight and modular front-end framework for developing fast and powerful web interfaces. UIkit provides a comprehensive collection of HTML, CSS, and JS components with consistent styling.",71,[],[147],{"id":23,"name":24,"slug":25,"icon":26},"7dd62a7e56574380cfc3fc21a66f0d52b85e6073af703625fb69735a2ee775a1",[31,32,33],"UIkit Overview",{"executes_code":27,"modifies_global_config":27,"requires_secrets":152,"uses_absolute_paths":27,"network_access":27},[],{"npm":154,"pip":155,"brew":156,"system":157},[],[],[],[],{"commands":159,"expected_files":160},[],[150],{"asset_kind":29,"target_tools":162,"install_mode":34,"entrypoint":150,"risk_profile":163,"dependencies":165,"content_hash":148,"verification":170},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":164,"uses_absolute_paths":27,"network_access":27},[],{"npm":166,"pip":167,"brew":168,"system":169},[],[],[],[],{"commands":171,"expected_files":172},[],[150],{"target":32,"score":60,"status":61,"policy":62,"why":174,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":148,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":176,"review_status":75,"signals":177},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":179,"content_hash":148,"visibility":17,"created_at":180,"updated_at":181},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fuikit-lightweight-modular-front-end-framework-8e9001d7","2026-04-27 08:25:13","2026-05-12 10:27:32",91.7859987446469,[132,133,134,135],[25,137],{"id":186,"uuid":187,"slug":188,"title":189,"description":190,"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":191,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":192,"tags":193,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":195,"asset_kind":29,"target_tools":196,"install_mode":34,"entrypoint":197,"risk_profile":198,"dependencies":200,"verification":205,"agent_metadata":208,"agent_fit":220,"trust":227,"provenance":231,"created_at":233,"updated_at":234,"__relatedScore":235,"__relatedReasons":236,"__sharedTags":237},1404,"18438936-38e7-11f1-9bc6-00163e2b0d79","fluent-bit-lightweight-high-performance-log-metrics-18438936","Fluent Bit — Lightweight High-Performance Log and Metrics Processor","Fluent Bit is a fast, lightweight telemetry agent from the Fluentd family. It collects logs, metrics and traces from any source, processes them with filters, and forwards them to dozens of backends.",60,[],[194],{"id":23,"name":24,"slug":25,"icon":26},"34c50a58647400820cf6f789d22ddcafce7f5facf5a922044e933d616d66a9da",[31,32,33],"Fluent Bit",{"executes_code":27,"modifies_global_config":27,"requires_secrets":199,"uses_absolute_paths":58,"network_access":27},[],{"npm":201,"pip":202,"brew":203,"system":204},[],[],[],[],{"commands":206,"expected_files":207},[],[197],{"asset_kind":29,"target_tools":209,"install_mode":34,"entrypoint":197,"risk_profile":210,"dependencies":212,"content_hash":195,"verification":217},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":211,"uses_absolute_paths":58,"network_access":27},[],{"npm":213,"pip":214,"brew":215,"system":216},[],[],[],[],{"commands":218,"expected_files":219},[],[197],{"target":32,"score":221,"status":222,"policy":223,"why":224,"asset_kind":29,"install_mode":34},64,"needs_confirmation","confirm",[64,65,66,225,226,70],"policy confirm","risk_profile.uses_absolute_paths is true",{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":195,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":228,"review_status":75,"signals":230},[229],"uses_absolute_paths",[77,78],{"owner_uuid":9,"owner_name":10,"source_url":232,"content_hash":195,"visibility":17,"created_at":233,"updated_at":234},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Ffluent-bit-lightweight-high-performance-log-metrics-18438936","2026-04-16 00:21:02","2026-05-12 15:25:33",91.67799475251616,[132,133,134,135],[25,137],{"id":239,"uuid":240,"slug":241,"title":242,"description":243,"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":244,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":245,"tags":246,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":248,"asset_kind":29,"target_tools":249,"install_mode":34,"entrypoint":97,"risk_profile":250,"dependencies":252,"verification":257,"agent_metadata":260,"agent_fit":272,"trust":274,"provenance":277,"created_at":279,"updated_at":280,"__relatedScore":281,"__relatedReasons":282,"__sharedTags":283},2930,"9bbd460e-4c49-11f1-9bc6-00163e2b0d79","asset-9bbd460e","AutoKeras — AutoML for Deep Learning with Keras","AutoKeras automatically searches for optimal neural network architectures and hyperparameters for image classification, text classification, regression, and structured data tasks using the Keras API.",23,[],[247],{"id":23,"name":24,"slug":25,"icon":26},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":251,"uses_absolute_paths":27,"network_access":27},[],{"npm":253,"pip":254,"brew":255,"system":256},[],[],[],[],{"commands":258,"expected_files":259},[],[],{"asset_kind":29,"target_tools":261,"install_mode":34,"entrypoint":97,"risk_profile":262,"dependencies":264,"content_hash":248,"verification":269,"inferred":58},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":263,"uses_absolute_paths":27,"network_access":27},[],{"npm":265,"pip":266,"brew":267,"system":268},[],[],[],[],{"commands":270,"expected_files":271},[],[],{"target":32,"score":60,"status":61,"policy":62,"why":273,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":248,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":275,"review_status":75,"signals":276},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":278,"content_hash":248,"visibility":17,"created_at":279,"updated_at":280},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-9bbd460e","2026-05-10 16:24:05","2026-05-12 18:43:33",88.07031686256741,[132,133,134,135],[25,137]]