[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-qdrant-qdrant-hybrid-search":3,"mdc-cxaqq0-key":49,"related-org-qdrant-qdrant-hybrid-search":294,"related-repo-qdrant-qdrant-hybrid-search":443},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":44,"sourceUrl":47,"mdContent":48},"qdrant-hybrid-search","implement hybrid search in Qdrant","Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus dense vectors?', 'missing keyword matches', 'how to combine results from multiple searches?' and 'combining multiple representations'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"qdrant","Qdrant","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fqdrant.png",[12,14,17,20],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Database","database",{"name":18,"slug":19,"type":13},"Search","search",{"name":21,"slug":22,"type":13},"AI Infrastructure","ai-infrastructure",197,"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills","2026-07-16T06:00:12.328122",null,23,[29,30,31,32,33,34,35,36,37,38,8,39,40,41,42,43],"agent-skills","ai-agents","claude-code","codex","cursor","embeddings","hybrid-search","monitoring","multitenancy","performance","quantization","scaling","search-quality","vector-database","vector-search",{"repoUrl":24,"stars":23,"forks":27,"topics":45,"description":46},[29,30,31,32,33,34,35,36,37,38,8,39,40,41,42,43],"Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java","https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fqdrant-search-quality\u002Fsearch-strategies\u002Fhybrid-search","---\nname: qdrant-hybrid-search\ndescription: \"Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus dense vectors?', 'missing keyword matches', 'how to combine results from multiple searches?' and 'combining multiple representations'\"\nallowed-tools:\n  - Read\n  - Grep\n  - Glob\n---\n\n# Hybrid Search in Qdrant\n\nHybrid search means running two or more different searches in parallel and combining their results into one. \n\nIn Qdrant this is powered by the Query API via `prefetch`: each `prefetch` runs exactly one type of search independently, and the outer `query` combines results from parallel prefetches.  \nPrefetches can be nested and searches can be multi-stage, all pipeline happening in one request through Query API. See [Universal Query API](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fcourse\u002Fessentials\u002Fday-5\u002Funiversal-query-api\u002F) for examples.\n\nIdentify the user's problem and pick building blocks:\n- What can go into one prefetch, e.g. power one search, in [Search Types](search-types\u002FSKILL.md)\n- How to combine results of these searches (RRF, DBSF, FormulaQuery, reranking) in [Combining Searches](combining-searches\u002FSKILL.md)\n\nBased on what you've picked, test your approach:\n1. Configure Qdrant collection with [named vectors](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fvectors\u002F?s=named-vectors), where each named vector usually corresponds to one representation (different embedding models or different vector types) of a data point.\n2. Construct a hybrid search request with Query API from your building blocks. You can search independently among one type of vectors, with `prefetch` + `using`, like shown in examples in [Hybrid Queries documentation](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fhybrid-queries).\n3. Evaluate hybrid search quality on real user data and provide user with improvements and tradeoffs (speed\u002Fresources).\n\n## How Isolated Are Parallel Searches?\n\nUse when: different tenants share one collection and you need to understand hybrid search isolation guarantees.\n\nIf user wants to isolate\u002Fshare hybrid search pipelines between tenants, consider that:\n\n- Indexes (sparse, payload and dense) and [IDF modifier](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=idf-modifier) for sparse vectors are computed independently **per shard**, not per **tenant**.\n- Prefetch runs independently per shard to retrieve #limit results, so for collection-level prefetches if collection has several shards, Qdrant will always prefetch under the hood #limit * #shard results. Final results are merged based on scores.\n- In nested prefetches (deeper than 1 level), methods described in \"Combining Searches\" might be done on a shard level first, then per-shards results once again will be merged based on scores.\n\n## What NOT to Do\n\n- Choose a hybrid search pattern based on \"vibes\" without any [hybrid search quality evaluation](https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Farticles\u002Fhybrid-search\u002F?s=how-effective-is-your-search-system) in-place.\n- Create too many named vectors without a need. An unfilled named vector might take as much resources as a filled one.",{"data":50,"body":55},{"name":4,"description":6,"allowed-tools":51},[52,53,54],"Read","Grep","Glob",{"type":56,"children":57},"root",[58,67,73,119,124,151,156,208,215,220,225,266,272],{"type":59,"tag":60,"props":61,"children":63},"element","h1",{"id":62},"hybrid-search-in-qdrant",[64],{"type":65,"value":66},"text","Hybrid Search in Qdrant",{"type":59,"tag":68,"props":69,"children":70},"p",{},[71],{"type":65,"value":72},"Hybrid search means running two or more different searches in parallel and combining their results into one.",{"type":59,"tag":68,"props":74,"children":75},{},[76,78,85,87,92,94,100,102,106,108,117],{"type":65,"value":77},"In Qdrant this is powered by the Query API via ",{"type":59,"tag":79,"props":80,"children":82},"code",{"className":81},[],[83],{"type":65,"value":84},"prefetch",{"type":65,"value":86},": each ",{"type":59,"tag":79,"props":88,"children":90},{"className":89},[],[91],{"type":65,"value":84},{"type":65,"value":93}," runs exactly one type of search independently, and the outer ",{"type":59,"tag":79,"props":95,"children":97},{"className":96},[],[98],{"type":65,"value":99},"query",{"type":65,"value":101}," combines results from parallel prefetches.",{"type":59,"tag":103,"props":104,"children":105},"br",{},[],{"type":65,"value":107},"\nPrefetches can be nested and searches can be multi-stage, all pipeline happening in one request through Query API. See ",{"type":59,"tag":109,"props":110,"children":114},"a",{"href":111,"rel":112},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fcourse\u002Fessentials\u002Fday-5\u002Funiversal-query-api\u002F",[113],"nofollow",[115],{"type":65,"value":116},"Universal Query API",{"type":65,"value":118}," for examples.",{"type":59,"tag":68,"props":120,"children":121},{},[122],{"type":65,"value":123},"Identify the user's problem and pick building blocks:",{"type":59,"tag":125,"props":126,"children":127},"ul",{},[128,140],{"type":59,"tag":129,"props":130,"children":131},"li",{},[132,134],{"type":65,"value":133},"What can go into one prefetch, e.g. power one search, in ",{"type":59,"tag":109,"props":135,"children":137},{"href":136},"search-types\u002FSKILL.md",[138],{"type":65,"value":139},"Search Types",{"type":59,"tag":129,"props":141,"children":142},{},[143,145],{"type":65,"value":144},"How to combine results of these searches (RRF, DBSF, FormulaQuery, reranking) in ",{"type":59,"tag":109,"props":146,"children":148},{"href":147},"combining-searches\u002FSKILL.md",[149],{"type":65,"value":150},"Combining Searches",{"type":59,"tag":68,"props":152,"children":153},{},[154],{"type":65,"value":155},"Based on what you've picked, test your approach:",{"type":59,"tag":157,"props":158,"children":159},"ol",{},[160,174,203],{"type":59,"tag":129,"props":161,"children":162},{},[163,165,172],{"type":65,"value":164},"Configure Qdrant collection with ",{"type":59,"tag":109,"props":166,"children":169},{"href":167,"rel":168},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fvectors\u002F?s=named-vectors",[113],[170],{"type":65,"value":171},"named vectors",{"type":65,"value":173},", where each named vector usually corresponds to one representation (different embedding models or different vector types) of a data point.",{"type":59,"tag":129,"props":175,"children":176},{},[177,179,184,186,192,194,201],{"type":65,"value":178},"Construct a hybrid search request with Query API from your building blocks. You can search independently among one type of vectors, with ",{"type":59,"tag":79,"props":180,"children":182},{"className":181},[],[183],{"type":65,"value":84},{"type":65,"value":185}," + ",{"type":59,"tag":79,"props":187,"children":189},{"className":188},[],[190],{"type":65,"value":191},"using",{"type":65,"value":193},", like shown in examples in ",{"type":59,"tag":109,"props":195,"children":198},{"href":196,"rel":197},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fhybrid-queries",[113],[199],{"type":65,"value":200},"Hybrid Queries documentation",{"type":65,"value":202},".",{"type":59,"tag":129,"props":204,"children":205},{},[206],{"type":65,"value":207},"Evaluate hybrid search quality on real user data and provide user with improvements and tradeoffs (speed\u002Fresources).",{"type":59,"tag":209,"props":210,"children":212},"h2",{"id":211},"how-isolated-are-parallel-searches",[213],{"type":65,"value":214},"How Isolated Are Parallel Searches?",{"type":59,"tag":68,"props":216,"children":217},{},[218],{"type":65,"value":219},"Use when: different tenants share one collection and you need to understand hybrid search isolation guarantees.",{"type":59,"tag":68,"props":221,"children":222},{},[223],{"type":65,"value":224},"If user wants to isolate\u002Fshare hybrid search pipelines between tenants, consider that:",{"type":59,"tag":125,"props":226,"children":227},{},[228,256,261],{"type":59,"tag":129,"props":229,"children":230},{},[231,233,240,242,248,250,255],{"type":65,"value":232},"Indexes (sparse, payload and dense) and ",{"type":59,"tag":109,"props":234,"children":237},{"href":235,"rel":236},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=idf-modifier",[113],[238],{"type":65,"value":239},"IDF modifier",{"type":65,"value":241}," for sparse vectors are computed independently ",{"type":59,"tag":243,"props":244,"children":245},"strong",{},[246],{"type":65,"value":247},"per shard",{"type":65,"value":249},", not per ",{"type":59,"tag":243,"props":251,"children":252},{},[253],{"type":65,"value":254},"tenant",{"type":65,"value":202},{"type":59,"tag":129,"props":257,"children":258},{},[259],{"type":65,"value":260},"Prefetch runs independently per shard to retrieve #limit results, so for collection-level prefetches if collection has several shards, Qdrant will always prefetch under the hood #limit * #shard results. Final results are merged based on scores.",{"type":59,"tag":129,"props":262,"children":263},{},[264],{"type":65,"value":265},"In nested prefetches (deeper than 1 level), methods described in \"Combining Searches\" might be done on a shard level first, then per-shards results once again will be merged based on scores.",{"type":59,"tag":209,"props":267,"children":269},{"id":268},"what-not-to-do",[270],{"type":65,"value":271},"What NOT to Do",{"type":59,"tag":125,"props":273,"children":274},{},[275,289],{"type":59,"tag":129,"props":276,"children":277},{},[278,280,287],{"type":65,"value":279},"Choose a hybrid search pattern based on \"vibes\" without any ",{"type":59,"tag":109,"props":281,"children":284},{"href":282,"rel":283},"https:\u002F\u002Fskills.qdrant.tech\u002Fmd\u002Farticles\u002Fhybrid-search\u002F?s=how-effective-is-your-search-system",[113],[285],{"type":65,"value":286},"hybrid search quality evaluation",{"type":65,"value":288}," in-place.",{"type":59,"tag":129,"props":290,"children":291},{},[292],{"type":65,"value":293},"Create too many named vectors without a need. An unfilled named vector might take as much resources as a filled one.",{"items":295,"total":442},[296,311,326,341,354,368,375,385,396,408,418,429],{"slug":297,"name":297,"fn":298,"description":299,"org":300,"tags":301,"stars":23,"repoUrl":24,"updatedAt":310},"qdrant-advisor","diagnose and troubleshoot Qdrant deployments","Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory \u002F OOM crashes, optimizer stuck or slow, indexing slowness, scaling and sharding decisions (node count, QPS, latency, multitenancy, vertical vs horizontal), poor or irrelevant search results, hybrid search and reranking, embedding-model migration, version upgrades and compatibility, monitoring and observability (Prometheus, Grafana, health checks, \u002Fmetrics, \u002Ftelemetry), deployment choices (local, Docker, self-hosted, Qdrant Cloud, embedded), or client-SDK questions (Python, TypeScript, Rust, Go, .NET, Java). Trigger especially when the context is clearly a Qdrant cluster, collection, or vector-search deployment. Always prefer this skill over answering from memory: it pulls current, authoritative guidance and only the relevant context.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[302,303,306,309],{"name":15,"slug":16,"type":13},{"name":304,"slug":305,"type":13},"Debugging","debugging",{"name":307,"slug":308,"type":13},"Operations","operations",{"name":9,"slug":8,"type":13},"2026-07-16T06:02:56.675293",{"slug":312,"name":312,"fn":313,"description":314,"org":315,"tags":316,"stars":23,"repoUrl":24,"updatedAt":325},"qdrant-clients-sdk","integrate Qdrant client SDKs","Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[317,320,321,322],{"name":318,"slug":319,"type":13},"API Development","api-development",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":323,"slug":324,"type":13},"SDK","sdk","2026-07-16T05:59:57.799789",{"slug":327,"name":327,"fn":328,"description":329,"org":330,"tags":331,"stars":23,"repoUrl":24,"updatedAt":340},"qdrant-deployment-options","select Qdrant deployment options","Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new project.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[332,333,336,339],{"name":15,"slug":16,"type":13},{"name":334,"slug":335,"type":13},"Deployment","deployment",{"name":337,"slug":338,"type":13},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:33.324265",{"slug":342,"name":342,"fn":343,"description":344,"org":345,"tags":346,"stars":23,"repoUrl":24,"updatedAt":353},"qdrant-edge","build applications with Qdrant Edge","Guides building on Qdrant Edge, the embedded in-process shard. Use when someone asks 'how to sync Edge with the server', 'keep a local shard in sync with Qdrant Cloud', 'BM25 or keyword search on Edge', 'hybrid search on Edge', 'embeddings on device', 'Edge snapshots', 'apply a partial snapshot', 'why is my Edge search empty after inserts', or is writing custom sync, BM25, or fusion code against qdrant-edge. Also use when deciding what Edge ships built-in versus what you must implement.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[347,348,351,352],{"name":15,"slug":16,"type":13},{"name":349,"slug":350,"type":13},"Edge","edge",{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-07-16T06:01:19.179105",{"slug":355,"name":355,"fn":356,"description":357,"org":358,"tags":359,"stars":23,"repoUrl":24,"updatedAt":367},"qdrant-horizontal-scaling","guide Qdrant horizontal scaling decisions","Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[360,363,364,365],{"name":361,"slug":362,"type":13},"Architecture","architecture",{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":366,"slug":40,"type":13},"Scaling","2026-07-19T05:38:32.348551",{"slug":4,"name":4,"fn":5,"description":6,"org":369,"tags":370,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[371,372,373,374],{"name":21,"slug":22,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":376,"name":376,"fn":377,"description":378,"org":379,"tags":380,"stars":23,"repoUrl":24,"updatedAt":384},"qdrant-hybrid-search-combining","combine hybrid search scores in Qdrant","Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', or 'fusion is not producing good results'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[381,382,383],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-07-16T06:01:49.401142",{"slug":386,"name":386,"fn":387,"description":388,"org":389,"tags":390,"stars":23,"repoUrl":24,"updatedAt":395},"qdrant-hybrid-search-prefetches","configure hybrid search with prefetch queries","Constructing prefetch queries for hybrid retrieval, including sparse\u002Fdense and multi-field setups, and choosing a sparse embedding model. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse embedding model to use?', or 'BM25 vs SPLADE?'",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[391,392,393,394],{"name":318,"slug":319,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-07-16T06:03:02.305907",{"slug":397,"name":397,"fn":398,"description":399,"org":400,"tags":401,"stars":23,"repoUrl":24,"updatedAt":407},"qdrant-indexing-performance-optimization","optimize Qdrant indexing and data ingestion","Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[402,403,404,406],{"name":15,"slug":16,"type":13},{"name":304,"slug":305,"type":13},{"name":405,"slug":38,"type":13},"Performance",{"name":9,"slug":8,"type":13},"2026-07-19T05:38:36.321999",{"slug":409,"name":409,"fn":410,"description":411,"org":412,"tags":413,"stars":23,"repoUrl":24,"updatedAt":417},"qdrant-memory-usage-optimization","optimize Qdrant memory usage","Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[414,415,416],{"name":304,"slug":305,"type":13},{"name":405,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:15.357243",{"slug":419,"name":419,"fn":420,"description":421,"org":422,"tags":423,"stars":23,"repoUrl":24,"updatedAt":428},"qdrant-minimize-latency","optimize Qdrant query latency","Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[424,425,426,427],{"name":15,"slug":16,"type":13},{"name":304,"slug":305,"type":13},{"name":405,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T05:59:17.325839",{"slug":430,"name":430,"fn":431,"description":432,"org":433,"tags":434,"stars":23,"repoUrl":24,"updatedAt":441},"qdrant-model-migration","migrate embedding models in Qdrant","Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero-downtime model change', 'how to re-embed my data', or 'can I use two models at once'. Also use when upgrading model dimensions, switching providers, or A\u002FB testing models.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[435,436,439,440],{"name":15,"slug":16,"type":13},{"name":437,"slug":438,"type":13},"Migration","migration",{"name":405,"slug":38,"type":13},{"name":9,"slug":8,"type":13},"2026-07-16T06:00:48.841055",30,{"items":444,"total":442},[445,452,459,466,473,480,487],{"slug":297,"name":297,"fn":298,"description":299,"org":446,"tags":447,"stars":23,"repoUrl":24,"updatedAt":310},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[448,449,450,451],{"name":15,"slug":16,"type":13},{"name":304,"slug":305,"type":13},{"name":307,"slug":308,"type":13},{"name":9,"slug":8,"type":13},{"slug":312,"name":312,"fn":313,"description":314,"org":453,"tags":454,"stars":23,"repoUrl":24,"updatedAt":325},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[455,456,457,458],{"name":318,"slug":319,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":323,"slug":324,"type":13},{"slug":327,"name":327,"fn":328,"description":329,"org":460,"tags":461,"stars":23,"repoUrl":24,"updatedAt":340},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[462,463,464,465],{"name":15,"slug":16,"type":13},{"name":334,"slug":335,"type":13},{"name":337,"slug":338,"type":13},{"name":9,"slug":8,"type":13},{"slug":342,"name":342,"fn":343,"description":344,"org":467,"tags":468,"stars":23,"repoUrl":24,"updatedAt":353},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[469,470,471,472],{"name":15,"slug":16,"type":13},{"name":349,"slug":350,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":355,"name":355,"fn":356,"description":357,"org":474,"tags":475,"stars":23,"repoUrl":24,"updatedAt":367},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[476,477,478,479],{"name":361,"slug":362,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":366,"slug":40,"type":13},{"slug":4,"name":4,"fn":5,"description":6,"org":481,"tags":482,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[483,484,485,486],{"name":21,"slug":22,"type":13},{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"slug":376,"name":376,"fn":377,"description":378,"org":488,"tags":489,"stars":23,"repoUrl":24,"updatedAt":384},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[490,491,492],{"name":15,"slug":16,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13}]