[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-replicate-run-models":3,"mdc--agydfi-key":33,"related-repo-replicate-run-models":579,"related-org-replicate-run-models":662},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"run-models","run AI models on Replicate","Run AI models on Replicate via predictions, webhooks, and streaming.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"replicate","Replicate","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Freplicate.jpg",[12,16,19],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"Machine Learning","machine-learning",{"name":20,"slug":21,"type":15},"AI Infrastructure","ai-infrastructure",51,"https:\u002F\u002Fgithub.com\u002Freplicate\u002Fskills","2026-07-16T06:03:09.738392",null,6,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"A collection of Agent Skills for building AI-powered apps with Replicate","https:\u002F\u002Fgithub.com\u002Freplicate\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Frun-models","---\nname: run-models\ndescription: Run AI models on Replicate via predictions, webhooks, and streaming.\n---\n\n## Docs\n\n- Reference: \u003Chttps:\u002F\u002Freplicate.com\u002Fdocs\u002Fllms.txt>\n- OpenAPI schema: \u003Chttps:\u002F\u002Fapi.replicate.com\u002Fopenapi.json>\n- MCP server: \u003Chttps:\u002F\u002Fmcp.replicate.com>\n- Per-model docs: `https:\u002F\u002Freplicate.com\u002F{owner}\u002F{model}\u002Fllms.txt`\n- Set `Accept: text\u002Fmarkdown` when requesting docs pages for Markdown responses.\n\n## Workflow\n\n1. **Choose the right model** - Search with the API or ask the user.\n2. **Get model metadata** - Fetch input and output schema via API.\n3. **Create prediction** - POST to \u002Fv1\u002Fpredictions.\n4. **Poll for results** - GET prediction until status is \"succeeded\".\n5. **Return output** - Usually URLs to generated content.\n\n## Three ways to get output\n\n1. Create a prediction, store its id from the response, and poll until completion.\n2. Set a `Prefer: wait` header when creating a prediction for a blocking synchronous response. Only recommended for very fast models. Max 60 seconds.\n3. Set an HTTPS webhook URL when creating a prediction, and Replicate will POST to that URL when the prediction completes.\n\n## Guidelines\n\n- Use the `POST \u002Fv1\u002Fpredictions` endpoint, as it supports both official and community models.\n- Every model has its own OpenAPI schema. Always fetch and check model schemas to make sure you're setting valid inputs. Even popular models change their schemas.\n- Validate input parameters against schema constraints (`minimum`, `maximum`, `enum` values). Don't generate values that violate them.\n- When unsure about a parameter value, use the model's default example or omit the optional parameter.\n- Don't set optional inputs unless you have a reason to. Stick to the required inputs and let the model's defaults do the work.\n- Use HTTPS URLs for file inputs whenever possible. You can also send base64-encoded files, but they should be avoided.\n- Fire off multiple predictions concurrently. Don't wait for one to finish before starting the next.\n- Output file URLs expire after 1 hour, so back them up if you need to keep them, using a service like Cloudflare R2.\n- Webhooks are a good mechanism for receiving and storing prediction output.\n\n## Predictions\n\n- A prediction goes through these states: `starting` -> `processing` -> `succeeded` \u002F `failed` \u002F `canceled`.\n- Official models use `owner\u002Fname` format. Community models require `owner\u002Fname:version_id`.\n- The `POST \u002Fv1\u002Fpredictions` endpoint handles both.\n\n## Webhooks\n\n- Set `webhook` to an HTTPS URL when creating a prediction. Replicate POSTs the full prediction object when it completes.\n- Filter events with `webhook_events_filter`: `start`, `output`, `logs`, `completed`.\n- Validate webhook signatures using the `Webhook-ID`, `Webhook-Timestamp`, and `Webhook-Signature` headers. Get the signing secret from `GET \u002Fv1\u002Fwebhooks\u002Fdefault\u002Fsecret`.\n\n## Prediction lifetime\n\n- Set `lifetime` to auto-cancel predictions that run too long (e.g. `30s`, `5m`, `1h`). Measured from creation time.\n\n## Streaming\n\n- Language models that support streaming include a `stream` URL in the response. Use SSE to receive incremental output.\n\n## File handling\n\n- Prefer HTTPS URLs for file inputs. Output URLs from one prediction can be passed directly as file inputs to the next model.\n- Output file URLs expire after 1 hour. Download and store them immediately if you need to keep them.\n\n## Multi-model workflows\n\n- Chain models by passing output URLs as file inputs to the next model.\n- Start all independent predictions in parallel, then collect results.\n- Output URLs are valid for 1 hour, which is enough for pipeline steps.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,112,118,173,179,205,211,290,296,374,380,471,477,514,520,536,542,555,561],{"type":39,"tag":40,"props":41,"children":43},"element","h2",{"id":42},"docs",[44],{"type":45,"value":46},"text","Docs",{"type":39,"tag":48,"props":49,"children":50},"ul",{},[51,65,76,87,99],{"type":39,"tag":52,"props":53,"children":54},"li",{},[55,57],{"type":45,"value":56},"Reference: ",{"type":39,"tag":58,"props":59,"children":63},"a",{"href":60,"rel":61},"https:\u002F\u002Freplicate.com\u002Fdocs\u002Fllms.txt",[62],"nofollow",[64],{"type":45,"value":60},{"type":39,"tag":52,"props":66,"children":67},{},[68,70],{"type":45,"value":69},"OpenAPI schema: ",{"type":39,"tag":58,"props":71,"children":74},{"href":72,"rel":73},"https:\u002F\u002Fapi.replicate.com\u002Fopenapi.json",[62],[75],{"type":45,"value":72},{"type":39,"tag":52,"props":77,"children":78},{},[79,81],{"type":45,"value":80},"MCP server: ",{"type":39,"tag":58,"props":82,"children":85},{"href":83,"rel":84},"https:\u002F\u002Fmcp.replicate.com",[62],[86],{"type":45,"value":83},{"type":39,"tag":52,"props":88,"children":89},{},[90,92],{"type":45,"value":91},"Per-model docs: ",{"type":39,"tag":93,"props":94,"children":96},"code",{"className":95},[],[97],{"type":45,"value":98},"https:\u002F\u002Freplicate.com\u002F{owner}\u002F{model}\u002Fllms.txt",{"type":39,"tag":52,"props":100,"children":101},{},[102,104,110],{"type":45,"value":103},"Set ",{"type":39,"tag":93,"props":105,"children":107},{"className":106},[],[108],{"type":45,"value":109},"Accept: text\u002Fmarkdown",{"type":45,"value":111}," when requesting docs pages for Markdown responses.",{"type":39,"tag":40,"props":113,"children":115},{"id":114},"workflow",[116],{"type":45,"value":117},"Workflow",{"type":39,"tag":119,"props":120,"children":121},"ol",{},[122,133,143,153,163],{"type":39,"tag":52,"props":123,"children":124},{},[125,131],{"type":39,"tag":126,"props":127,"children":128},"strong",{},[129],{"type":45,"value":130},"Choose the right model",{"type":45,"value":132}," - Search with the API or ask the user.",{"type":39,"tag":52,"props":134,"children":135},{},[136,141],{"type":39,"tag":126,"props":137,"children":138},{},[139],{"type":45,"value":140},"Get model metadata",{"type":45,"value":142}," - Fetch input and output schema via API.",{"type":39,"tag":52,"props":144,"children":145},{},[146,151],{"type":39,"tag":126,"props":147,"children":148},{},[149],{"type":45,"value":150},"Create prediction",{"type":45,"value":152}," - POST to \u002Fv1\u002Fpredictions.",{"type":39,"tag":52,"props":154,"children":155},{},[156,161],{"type":39,"tag":126,"props":157,"children":158},{},[159],{"type":45,"value":160},"Poll for results",{"type":45,"value":162}," - GET prediction until status is \"succeeded\".",{"type":39,"tag":52,"props":164,"children":165},{},[166,171],{"type":39,"tag":126,"props":167,"children":168},{},[169],{"type":45,"value":170},"Return output",{"type":45,"value":172}," - Usually URLs to generated content.",{"type":39,"tag":40,"props":174,"children":176},{"id":175},"three-ways-to-get-output",[177],{"type":45,"value":178},"Three ways to get output",{"type":39,"tag":119,"props":180,"children":181},{},[182,187,200],{"type":39,"tag":52,"props":183,"children":184},{},[185],{"type":45,"value":186},"Create a prediction, store its id from the response, and poll until completion.",{"type":39,"tag":52,"props":188,"children":189},{},[190,192,198],{"type":45,"value":191},"Set a ",{"type":39,"tag":93,"props":193,"children":195},{"className":194},[],[196],{"type":45,"value":197},"Prefer: wait",{"type":45,"value":199}," header when creating a prediction for a blocking synchronous response. Only recommended for very fast models. Max 60 seconds.",{"type":39,"tag":52,"props":201,"children":202},{},[203],{"type":45,"value":204},"Set an HTTPS webhook URL when creating a prediction, and Replicate will POST to that URL when the prediction completes.",{"type":39,"tag":40,"props":206,"children":208},{"id":207},"guidelines",[209],{"type":45,"value":210},"Guidelines",{"type":39,"tag":48,"props":212,"children":213},{},[214,227,232,260,265,270,275,280,285],{"type":39,"tag":52,"props":215,"children":216},{},[217,219,225],{"type":45,"value":218},"Use the ",{"type":39,"tag":93,"props":220,"children":222},{"className":221},[],[223],{"type":45,"value":224},"POST \u002Fv1\u002Fpredictions",{"type":45,"value":226}," endpoint, as it supports both official and community models.",{"type":39,"tag":52,"props":228,"children":229},{},[230],{"type":45,"value":231},"Every model has its own OpenAPI schema. Always fetch and check model schemas to make sure you're setting valid inputs. Even popular models change their schemas.",{"type":39,"tag":52,"props":233,"children":234},{},[235,237,243,245,251,252,258],{"type":45,"value":236},"Validate input parameters against schema constraints (",{"type":39,"tag":93,"props":238,"children":240},{"className":239},[],[241],{"type":45,"value":242},"minimum",{"type":45,"value":244},", ",{"type":39,"tag":93,"props":246,"children":248},{"className":247},[],[249],{"type":45,"value":250},"maximum",{"type":45,"value":244},{"type":39,"tag":93,"props":253,"children":255},{"className":254},[],[256],{"type":45,"value":257},"enum",{"type":45,"value":259}," values). Don't generate values that violate them.",{"type":39,"tag":52,"props":261,"children":262},{},[263],{"type":45,"value":264},"When unsure about a parameter value, use the model's default example or omit the optional parameter.",{"type":39,"tag":52,"props":266,"children":267},{},[268],{"type":45,"value":269},"Don't set optional inputs unless you have a reason to. Stick to the required inputs and let the model's defaults do the work.",{"type":39,"tag":52,"props":271,"children":272},{},[273],{"type":45,"value":274},"Use HTTPS URLs for file inputs whenever possible. You can also send base64-encoded files, but they should be avoided.",{"type":39,"tag":52,"props":276,"children":277},{},[278],{"type":45,"value":279},"Fire off multiple predictions concurrently. Don't wait for one to finish before starting the next.",{"type":39,"tag":52,"props":281,"children":282},{},[283],{"type":45,"value":284},"Output file URLs expire after 1 hour, so back them up if you need to keep them, using a service like Cloudflare R2.",{"type":39,"tag":52,"props":286,"children":287},{},[288],{"type":45,"value":289},"Webhooks are a good mechanism for receiving and storing prediction output.",{"type":39,"tag":40,"props":291,"children":293},{"id":292},"predictions",[294],{"type":45,"value":295},"Predictions",{"type":39,"tag":48,"props":297,"children":298},{},[299,342,362],{"type":39,"tag":52,"props":300,"children":301},{},[302,304,310,312,318,319,325,327,333,334,340],{"type":45,"value":303},"A prediction goes through these states: ",{"type":39,"tag":93,"props":305,"children":307},{"className":306},[],[308],{"type":45,"value":309},"starting",{"type":45,"value":311}," -> ",{"type":39,"tag":93,"props":313,"children":315},{"className":314},[],[316],{"type":45,"value":317},"processing",{"type":45,"value":311},{"type":39,"tag":93,"props":320,"children":322},{"className":321},[],[323],{"type":45,"value":324},"succeeded",{"type":45,"value":326}," \u002F ",{"type":39,"tag":93,"props":328,"children":330},{"className":329},[],[331],{"type":45,"value":332},"failed",{"type":45,"value":326},{"type":39,"tag":93,"props":335,"children":337},{"className":336},[],[338],{"type":45,"value":339},"canceled",{"type":45,"value":341},".",{"type":39,"tag":52,"props":343,"children":344},{},[345,347,353,355,361],{"type":45,"value":346},"Official models use ",{"type":39,"tag":93,"props":348,"children":350},{"className":349},[],[351],{"type":45,"value":352},"owner\u002Fname",{"type":45,"value":354}," format. Community models require ",{"type":39,"tag":93,"props":356,"children":358},{"className":357},[],[359],{"type":45,"value":360},"owner\u002Fname:version_id",{"type":45,"value":341},{"type":39,"tag":52,"props":363,"children":364},{},[365,367,372],{"type":45,"value":366},"The ",{"type":39,"tag":93,"props":368,"children":370},{"className":369},[],[371],{"type":45,"value":224},{"type":45,"value":373}," endpoint handles both.",{"type":39,"tag":40,"props":375,"children":377},{"id":376},"webhooks",[378],{"type":45,"value":379},"Webhooks",{"type":39,"tag":48,"props":381,"children":382},{},[383,395,436],{"type":39,"tag":52,"props":384,"children":385},{},[386,387,393],{"type":45,"value":103},{"type":39,"tag":93,"props":388,"children":390},{"className":389},[],[391],{"type":45,"value":392},"webhook",{"type":45,"value":394}," to an HTTPS URL when creating a prediction. Replicate POSTs the full prediction object when it completes.",{"type":39,"tag":52,"props":396,"children":397},{},[398,400,406,408,414,415,421,422,428,429,435],{"type":45,"value":399},"Filter events with ",{"type":39,"tag":93,"props":401,"children":403},{"className":402},[],[404],{"type":45,"value":405},"webhook_events_filter",{"type":45,"value":407},": ",{"type":39,"tag":93,"props":409,"children":411},{"className":410},[],[412],{"type":45,"value":413},"start",{"type":45,"value":244},{"type":39,"tag":93,"props":416,"children":418},{"className":417},[],[419],{"type":45,"value":420},"output",{"type":45,"value":244},{"type":39,"tag":93,"props":423,"children":425},{"className":424},[],[426],{"type":45,"value":427},"logs",{"type":45,"value":244},{"type":39,"tag":93,"props":430,"children":432},{"className":431},[],[433],{"type":45,"value":434},"completed",{"type":45,"value":341},{"type":39,"tag":52,"props":437,"children":438},{},[439,441,447,448,454,456,462,464,470],{"type":45,"value":440},"Validate webhook signatures using the ",{"type":39,"tag":93,"props":442,"children":444},{"className":443},[],[445],{"type":45,"value":446},"Webhook-ID",{"type":45,"value":244},{"type":39,"tag":93,"props":449,"children":451},{"className":450},[],[452],{"type":45,"value":453},"Webhook-Timestamp",{"type":45,"value":455},", and ",{"type":39,"tag":93,"props":457,"children":459},{"className":458},[],[460],{"type":45,"value":461},"Webhook-Signature",{"type":45,"value":463}," headers. Get the signing secret from ",{"type":39,"tag":93,"props":465,"children":467},{"className":466},[],[468],{"type":45,"value":469},"GET \u002Fv1\u002Fwebhooks\u002Fdefault\u002Fsecret",{"type":45,"value":341},{"type":39,"tag":40,"props":472,"children":474},{"id":473},"prediction-lifetime",[475],{"type":45,"value":476},"Prediction lifetime",{"type":39,"tag":48,"props":478,"children":479},{},[480],{"type":39,"tag":52,"props":481,"children":482},{},[483,484,490,492,498,499,505,506,512],{"type":45,"value":103},{"type":39,"tag":93,"props":485,"children":487},{"className":486},[],[488],{"type":45,"value":489},"lifetime",{"type":45,"value":491}," to auto-cancel predictions that run too long (e.g. ",{"type":39,"tag":93,"props":493,"children":495},{"className":494},[],[496],{"type":45,"value":497},"30s",{"type":45,"value":244},{"type":39,"tag":93,"props":500,"children":502},{"className":501},[],[503],{"type":45,"value":504},"5m",{"type":45,"value":244},{"type":39,"tag":93,"props":507,"children":509},{"className":508},[],[510],{"type":45,"value":511},"1h",{"type":45,"value":513},"). Measured from creation time.",{"type":39,"tag":40,"props":515,"children":517},{"id":516},"streaming",[518],{"type":45,"value":519},"Streaming",{"type":39,"tag":48,"props":521,"children":522},{},[523],{"type":39,"tag":52,"props":524,"children":525},{},[526,528,534],{"type":45,"value":527},"Language models that support streaming include a ",{"type":39,"tag":93,"props":529,"children":531},{"className":530},[],[532],{"type":45,"value":533},"stream",{"type":45,"value":535}," URL in the response. Use SSE to receive incremental output.",{"type":39,"tag":40,"props":537,"children":539},{"id":538},"file-handling",[540],{"type":45,"value":541},"File handling",{"type":39,"tag":48,"props":543,"children":544},{},[545,550],{"type":39,"tag":52,"props":546,"children":547},{},[548],{"type":45,"value":549},"Prefer HTTPS URLs for file inputs. Output URLs from one prediction can be passed directly as file inputs to the next model.",{"type":39,"tag":52,"props":551,"children":552},{},[553],{"type":45,"value":554},"Output file URLs expire after 1 hour. Download and store them immediately if you need to keep them.",{"type":39,"tag":40,"props":556,"children":558},{"id":557},"multi-model-workflows",[559],{"type":45,"value":560},"Multi-model workflows",{"type":39,"tag":48,"props":562,"children":563},{},[564,569,574],{"type":39,"tag":52,"props":565,"children":566},{},[567],{"type":45,"value":568},"Chain models by passing output URLs as file inputs to the next model.",{"type":39,"tag":52,"props":570,"children":571},{},[572],{"type":45,"value":573},"Start all independent predictions in parallel, then collect results.",{"type":39,"tag":52,"props":575,"children":576},{},[577],{"type":45,"value":578},"Output URLs are valid for 1 hour, which is enough for pipeline steps.",{"items":580,"total":661},[581,593,607,617,631,643,655],{"slug":582,"name":582,"fn":583,"description":584,"org":585,"tags":586,"stars":22,"repoUrl":23,"updatedAt":592},"build-models","build and package custom AI models","Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like \"build a model\", \"package a model\", \"create a Cog model\", \"wrap a model\", \"containerize an AI model\", \"predict.py\", \"cog.yaml\", \"BasePredictor\", or \"Cog container\", and when referencing cog.run, github.com\u002Freplicate\u002Fcog, or github.com\u002Freplicate\u002Fcog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[587,588,591],{"name":20,"slug":21,"type":15},{"name":589,"slug":590,"type":15},"Deployment","deployment",{"name":17,"slug":18,"type":15},"2026-07-16T06:02:28.318441",{"slug":594,"name":594,"fn":595,"description":596,"org":597,"tags":598,"stars":22,"repoUrl":23,"updatedAt":606},"compare-models","compare Replicate AI models","Compare Replicate models by cost, speed, quality, and capabilities.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[599,602,605],{"name":600,"slug":601,"type":15},"Analysis","analysis",{"name":603,"slug":604,"type":15},"Benchmarking","benchmarking",{"name":13,"slug":14,"type":15},"2026-07-16T06:03:10.401096",{"slug":608,"name":608,"fn":609,"description":610,"org":611,"tags":612,"stars":22,"repoUrl":23,"updatedAt":616},"find-models","find AI models on Replicate","Find AI models on Replicate using search and curated collections.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[613,614,615],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-07-16T06:01:52.508562",{"slug":618,"name":618,"fn":619,"description":620,"org":621,"tags":622,"stars":22,"repoUrl":23,"updatedAt":630},"prompt-images","generate prompts for image models","Prompting techniques for AI image generation and editing models on Replicate. Use when writing prompts for image models or building image generation features.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[623,626,629],{"name":624,"slug":625,"type":15},"Creative","creative",{"name":627,"slug":628,"type":15},"Image Generation","image-generation",{"name":13,"slug":14,"type":15},"2026-07-16T06:01:52.867443",{"slug":632,"name":632,"fn":633,"description":634,"org":635,"tags":636,"stars":22,"repoUrl":23,"updatedAt":642},"prompt-videos","generate prompts for AI video models","Prompting techniques for AI video generation models on Replicate. Use when writing prompts for video models or building video generation features.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[637,638,639],{"name":624,"slug":625,"type":15},{"name":13,"slug":14,"type":15},{"name":640,"slug":641,"type":15},"Video","video","2026-07-16T06:03:10.065511",{"slug":644,"name":644,"fn":645,"description":646,"org":647,"tags":648,"stars":22,"repoUrl":23,"updatedAt":654},"publish-models","publish and deploy AI models to Replicate","Push and publish custom AI models to Replicate, and set up CI\u002FCD for releasing new model versions safely. Use when running cog push, deploying a model to Replicate, releasing a new version, validating a model with cog-safe-push before publishing, configuring a Replicate deployment, setting up GitHub Actions for model releases, or porting a community model to an official one. Trigger on phrases like \"push a model to Replicate\", \"publish a model\", \"deploy a model\", \"release a new version\", \"cog push\", \"cog-safe-push\", \"model CI\", \"r8.im\", or \"schema compatibility\", and when referencing github.com\u002Freplicate\u002Fcog-safe-push or github.com\u002Freplicate\u002Fmodel-ci-template. Covers cog push, the full cog-safe-push config (test cases, fuzz, deployment, official_model), GitHub Actions patterns, multi-model matrix pushes, and post-publish monitoring. Assumes you already have a working Cog project; see build-models if you need to package one first.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[649,650,653],{"name":20,"slug":21,"type":15},{"name":651,"slug":652,"type":15},"CI\u002FCD","ci-cd",{"name":589,"slug":590,"type":15},"2026-07-16T06:02:28.648245",{"slug":4,"name":4,"fn":5,"description":6,"org":656,"tags":657,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[658,659,660],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},7,{"items":663,"total":661},[664,670,676,682,688,694,700],{"slug":582,"name":582,"fn":583,"description":584,"org":665,"tags":666,"stars":22,"repoUrl":23,"updatedAt":592},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[667,668,669],{"name":20,"slug":21,"type":15},{"name":589,"slug":590,"type":15},{"name":17,"slug":18,"type":15},{"slug":594,"name":594,"fn":595,"description":596,"org":671,"tags":672,"stars":22,"repoUrl":23,"updatedAt":606},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[673,674,675],{"name":600,"slug":601,"type":15},{"name":603,"slug":604,"type":15},{"name":13,"slug":14,"type":15},{"slug":608,"name":608,"fn":609,"description":610,"org":677,"tags":678,"stars":22,"repoUrl":23,"updatedAt":616},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[679,680,681],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":618,"name":618,"fn":619,"description":620,"org":683,"tags":684,"stars":22,"repoUrl":23,"updatedAt":630},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[685,686,687],{"name":624,"slug":625,"type":15},{"name":627,"slug":628,"type":15},{"name":13,"slug":14,"type":15},{"slug":632,"name":632,"fn":633,"description":634,"org":689,"tags":690,"stars":22,"repoUrl":23,"updatedAt":642},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[691,692,693],{"name":624,"slug":625,"type":15},{"name":13,"slug":14,"type":15},{"name":640,"slug":641,"type":15},{"slug":644,"name":644,"fn":645,"description":646,"org":695,"tags":696,"stars":22,"repoUrl":23,"updatedAt":654},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[697,698,699],{"name":20,"slug":21,"type":15},{"name":651,"slug":652,"type":15},{"name":589,"slug":590,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":701,"tags":702,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[703,704,705],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15}]