[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f3jRqQN1YVVDdLHEt0ancUewr9ss-kdpkIHQ0ypc0n_I":3},{"tool":4,"categoryPool":44},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"createdAt":18,"repo":19,"articles":42,"related":43},"entity_01m7js6x81eh3b0pr98c2v1fdb","Knowhere","knowhere","Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.","https:\u002F\u002Fknowhereto.ai","https:\u002F\u002Fgithub.com\u002FOntos-AI\u002Fknowhere","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fknowhere-53a48c6e.png",true,[14],{"name":15,"slug":16,"count":17},"Extraction","extraction",0,1794853008,{"id":20,"fullName":21,"url":10,"stars":22,"forks":23,"openIssues":24,"language":25,"license":26,"topics":27,"pushedAt":39,"archived":40,"licenseSpdx":26,"licenseOsi":12,"licenseVerifiedAt":41},"entity_01m7js6xwzeh3b0prvaqt4hrh1","Ontos-AI\u002Fknowhere",4073,340,49,"Python","Apache-2.0",[28,29,30,31,32,33,34,35,36,37,38],"agent-harness","ai-agents","claude-code","codex","cursor","document-intelligence","langchain","mutli-agent","rag-pipeline","skills","vector-database","2026-11-19T10:11:34Z",false,"2026-11-16T18:14:17.840Z",[],[],[45,85,120,145],{"id":46,"name":47,"slug":48,"description":49,"url":50,"githubUrl":51,"logoUrl":52,"openSource":12,"categories":53,"createdAt":55,"repo":56,"articles":83,"related":84},"entity_01m0ga4f5ve8gsxx919e5c5j6h","Deepcrawl","deepcrawl","100% free and full open-source edge Firecrawl alternative with better links extraction for agents - that you can deploy to cloudflare or vercel by yourself.","https:\u002F\u002Fdeepcrawl.dev","https:\u002F\u002Fgithub.com\u002Flumpinif\u002Fdeepcrawl","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-feed6609.ico",[54],{"name":15,"slug":16,"count":17},1787253898,{"id":57,"fullName":58,"url":51,"stars":59,"forks":60,"openIssues":61,"language":62,"license":63,"topics":64,"pushedAt":81,"archived":40,"licenseSpdx":63,"licenseOsi":12,"licenseVerifiedAt":82},"entity_01m0ga4k8ze8gsxx9z58g27yyx","lumpinif\u002Fdeepcrawl",703,80,2,"TypeScript","MIT",[65,66,67,68,69,48,70,71,72,73,74,75,76,77,78,79,80],"ai-agent-tools","ai-sdk","better-auth","cloudflare-workers","crawling","hono","html-cleaner","html-to-markdown","links-extraction","links-tree","nextjs","nextjs16","orpc","typescript","web-scraper","web-scraping","2026-08-24T16:23:20Z","2026-08-20T19:25:02.444Z",[],[],{"id":86,"name":87,"slug":88,"description":89,"url":90,"githubUrl":91,"logoUrl":92,"openSource":12,"categories":93,"createdAt":95,"repo":96,"articles":118,"related":119},"entity_01ky0s7wgrf239sywgdkw7e8gz","DocETL","docetl","Open-source toolkit, built by the EPIC Data Lab at UC Berkeley, for creating LLM-powered pipelines that extract, transform, and link knowledge from unstructured documents.","https:\u002F\u002Fwww.docetl.org\u002F","https:\u002F\u002Fgithub.com\u002Fucbepic\u002Fdocetl","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fdocetl-favicon-color-9d034c86.png",[94],{"name":15,"slug":16,"count":17},1784585384,{"id":97,"fullName":98,"url":91,"stars":99,"forks":100,"openIssues":101,"language":25,"license":63,"topics":102,"pushedAt":116,"archived":40,"licenseSpdx":63,"licenseOsi":12,"licenseVerifiedAt":117},"entity_01ky37vbf4fanrdjqmf9tbh6ay","ucbepic\u002Fdocetl",4262,471,29,[103,104,105,106,107,108,109,110,111,112,113,114,115],"agents","data","data-pipelines","document-analysis","document-processing","elt","etl","llm","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow","2026-11-17T17:51:36Z","2026-08-09",[],[],{"id":121,"name":122,"slug":123,"description":124,"url":125,"logoUrl":126,"openSource":40,"categories":127,"createdAt":129,"articles":130,"related":144},"entity_01m5g4a3qmfvm9anhzfadwzz85","Expand Fetch","expand-fetch","Fetch and crawl with frontier System One models.","https:\u002F\u002Fexpand.ai\u002F","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-9a569456.ico",[128],{"name":15,"slug":16,"count":17},1792616500,[131],{"id":132,"name":133,"slug":134,"summary":135,"url":136,"kind":137,"platform":138,"author":139,"publisher":140,"publishedAt":141,"about":142,"writtenBy":143},"entity_01m4y6nxn7fvqsmh6gewvp1taw","Announcing Expand Fetch","announcing-expand-fetch","Iris, X-Ray, Wayback Machine and Highlights in one API, so your agent reads the web without losing the details. You can use it today.","https:\u002F\u002Fexpand.ai\u002Fblog\u002Fannouncing-expand-fetch","announcement","web","Tim Suchanek","Expand","2026-10-14",[],[],[],{"id":146,"name":147,"slug":148,"description":149,"url":150,"githubUrl":151,"logoUrl":152,"openSource":12,"categories":153,"createdAt":158,"repo":159,"articles":176,"related":186},"entity_01kzs3gy7rfantmwgtrzpzt8yn","ExtractBench","extractbench","A benchmark for schema-guided extraction from real enterprise documents. 370 documents, 4,869 pages, 67 document types, each with its own JSON Schema. Scored on value accuracy, completeness, and evidence.","https:\u002F\u002Fwww.extractbench.ai\u002F","https:\u002F\u002Fgithub.com\u002Frun-llama\u002FExtractBench","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fapple-touch-icon-da922544.png",[154,157],{"name":155,"slug":156,"count":17},"Evals","evals",{"name":15,"slug":16,"count":17},1786475215,{"id":160,"fullName":161,"url":151,"stars":162,"forks":163,"openIssues":164,"language":25,"license":26,"topics":165,"pushedAt":174,"archived":40,"licenseSpdx":26,"licenseOsi":12,"licenseVerifiedAt":175},"entity_01kzs3h16cfantmwh9s6ztemea","run-llama\u002FExtractBench",121,20,6,[166,167,168,169,170,171,172,110,173],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","vision-language-model","2026-11-19T03:00:53Z","2026-08-11",[177],{"id":178,"name":179,"slug":180,"summary":181,"url":182,"kind":137,"platform":138,"publisher":183,"publishedAt":175,"about":184,"writtenBy":185},"entity_01kzs3krzxfantmwj9zrcz3hbt","ExtractBench: The Most Comprehensive Extraction Benchmark","introducing-extractbench","The most comprehensive document extraction benchmark: 14 systems scored on accuracy, completeness, grounding, and cost across 370 enterprise documents.","https:\u002F\u002Fwww.llamaindex.ai\u002Fblog\u002Fintroducing-extractbench","LlamaIndex",[],[],[]]