[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fgpn2VhbWdINYhr2wtLSs7YPX91w5aUkWyb0xElVuMGg":3},{"tool":4,"categoryPool":47},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"repo":18,"articles":45,"createdAt":46},"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",true,[14],{"name":15,"slug":16,"count":17},"Extraction","extraction",0,{"fullName":19,"url":10,"stars":20,"forks":21,"openIssues":22,"language":23,"license":24,"topics":25,"pushedAt":42,"archived":43,"licenseSpdx":24,"licenseOsi":12,"licenseVerifiedAt":44},"lumpinif\u002Fdeepcrawl",656,77,2,"TypeScript","MIT",[26,27,28,29,30,7,31,32,33,34,35,36,37,38,39,40,41],"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","2026-03-12T18:02:48Z",false,"2026-08-20T19:25:02.444Z",[],1787253898,[48,54,88,131],{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":49,"repo":51,"articles":53,"createdAt":46},[50],{"name":15,"slug":16,"count":17},{"fullName":19,"url":10,"stars":20,"forks":21,"openIssues":22,"language":23,"license":24,"topics":52,"pushedAt":42,"archived":43,"licenseSpdx":24,"licenseOsi":12,"licenseVerifiedAt":44},[26,27,28,29,30,7,31,32,33,34,35,36,37,38,39,40,41],[],{"id":55,"name":56,"slug":57,"description":58,"url":59,"githubUrl":60,"logoUrl":61,"openSource":12,"categories":62,"repo":64,"articles":86,"createdAt":87},"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",[63],{"name":15,"slug":16,"count":17},{"fullName":65,"url":60,"stars":66,"forks":67,"openIssues":68,"language":69,"license":24,"topics":70,"pushedAt":84,"archived":43,"licenseSpdx":24,"licenseOsi":12,"licenseVerifiedAt":85},"ucbepic\u002Fdocetl",3983,424,43,"Python",[71,72,73,74,75,76,77,78,79,80,81,82,83],"agents","data","data-pipelines","document-analysis","document-processing","elt","etl","llm","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow","2026-08-10T15:00:22Z","2026-08-09",[],1784585384,{"id":89,"name":90,"slug":91,"description":92,"url":93,"githubUrl":94,"logoUrl":95,"openSource":12,"categories":96,"repo":101,"articles":118,"createdAt":130},"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",[97,100],{"name":98,"slug":99,"count":17},"Evals","evals",{"name":15,"slug":16,"count":17},{"fullName":102,"url":94,"stars":103,"forks":104,"openIssues":105,"language":69,"license":106,"topics":107,"pushedAt":116,"archived":43,"licenseSpdx":106,"licenseOsi":12,"licenseVerifiedAt":117},"run-llama\u002FExtractBench",57,8,1,"Apache-2.0",[108,109,110,111,112,113,114,78,115],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","vision-language-model","2026-08-20T17:32:54Z","2026-08-11",[119],{"id":120,"name":121,"slug":122,"summary":123,"url":124,"kind":125,"platform":126,"publisher":127,"publishedAt":117,"about":128,"writtenBy":129},"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","announcement","web","LlamaIndex",[],[],1786475215,{"id":132,"name":133,"slug":134,"description":135,"url":136,"githubUrl":136,"openSource":12,"categories":137,"repo":139,"articles":145,"createdAt":146},"entity_01kzhfcs4xeh2vtra99mntepyy","Knowledge Graph Builder","knowledge-graph-builder","Repository for building knowledge graphs from specific datasets using generative language model through ollama","https:\u002F\u002Fgithub.com\u002FFabioYanezRomero\u002FKnowledge-Graph-Builder",[138],{"name":15,"slug":16,"count":17},{"fullName":140,"url":136,"stars":141,"forks":142,"openIssues":22,"language":69,"license":24,"topics":143,"pushedAt":144,"archived":43,"licenseSpdx":24,"licenseOsi":12,"licenseVerifiedAt":85},"FabioYanezRomero\u002FKnowledge-Graph-Builder",98,12,[],"2026-07-04T18:27:20Z",[],1786219226]