[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-extractbench":3},{"tool":4,"categoryPool":53},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"repo":21,"company":-1,"articles":39,"createdAt":52},"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",true,[14,18],{"id":-1,"name":15,"slug":16,"count":17},"Evals","evals",0,{"id":-1,"name":19,"slug":20,"count":17},"Extraction","extraction",{"fullName":22,"url":10,"stars":23,"forks":24,"openIssues":17,"language":25,"license":26,"topics":27,"pushedAt":37,"archived":38},"run-llama\u002FExtractBench",39,4,"Python","Apache-2.0",[28,29,30,31,32,33,34,35,36],"benchmark","coding-agent","document-ai","evaluation","extract","extract-data","llamaindex","llm","vision-language-model","2026-08-08T18:34:23Z",false,[40],{"id":41,"name":42,"slug":43,"summary":44,"url":45,"kind":46,"platform":47,"author":-1,"authorHandle":-1,"publisher":48,"publishedAt":49,"about":50,"writtenBy":51,"createdAt":-1},"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","2026-08-11",[],[],1786475215,[54,82,103,128,163,194,204,220],{"id":55,"name":56,"slug":57,"description":58,"url":59,"githubUrl":59,"logoUrl":60,"openSource":12,"categories":61,"repo":63,"company":74,"articles":80,"createdAt":81},"entity_01kzhe2n9gfagsad1ydt1e7gkn","AACR-Bench","aacr-bench","An Alibaba open-source multi-language benchmark for evaluating LLMs in repository-level automatic code review, featuring an AI-assisted and expert-verified dataset.","https:\u002F\u002Fgithub.com\u002Falibaba\u002Faacr-bench","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Falibaba-0f6c077a.png",[62],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":64,"url":59,"stars":65,"forks":66,"openIssues":67,"language":25,"license":26,"topics":68,"pushedAt":73,"archived":38},"alibaba\u002Faacr-bench",206,16,6,[28,69,70,71,72],"code-review","multi-language","repository-level-context","software-engineering","2026-08-04T05:36:38Z",{"id":75,"name":76,"slug":77,"url":78,"bio":79,"githubOrg":77},"entity_01kzmeveq2f22bbn6jcepyspwk","Alibaba","alibaba","https:\u002F\u002Fwww.alibabagroup.com","Alibaba Open Source",[],1786217846,{"id":83,"name":84,"slug":85,"description":86,"url":87,"githubUrl":88,"logoUrl":89,"openSource":12,"categories":90,"repo":92,"company":-1,"articles":101,"createdAt":102},"entity_01kzpjy8r7fvn8q0rcmcw8xg56","BenchLocal","benchlocal","Test LLMs on real tasks. Compare models side-by-side.","https:\u002F\u002Fbenchlocal.com\u002F","https:\u002F\u002Fgithub.com\u002Fstevibe\u002FBenchLocal","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fstevibe-cd02357b.png",[91],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":93,"url":88,"stars":94,"forks":95,"openIssues":96,"language":97,"license":98,"topics":99,"pushedAt":100,"archived":38},"stevibe\u002FBenchLocal",402,45,12,"TypeScript","MIT",[],"2026-08-10T15:10:36Z",[],1786390717,{"id":104,"name":105,"slug":106,"description":107,"url":108,"githubUrl":-1,"logoUrl":109,"openSource":38,"categories":110,"repo":-1,"company":-1,"articles":112,"createdAt":127},"entity_01kyb2mdndeshatkngff89rdmc","Braintrust","braintrust","Ship quality agents at scale. Braintrust is the AI observability platform for tracing production, running evals, and catching regressions before they reach users.","https:\u002F\u002Fwww.braintrust.dev\u002F","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ficon180-ef918139.png",[111],{"id":-1,"name":15,"slug":16,"count":17},[113],{"id":114,"name":115,"slug":116,"summary":117,"url":118,"kind":119,"platform":120,"author":121,"authorHandle":122,"publisher":123,"publishedAt":124,"about":125,"writtenBy":126,"createdAt":-1},"entity_01kyb1ndrmf6esz3naek99dvk8","The context gold rush: Why everyone is building the same thing.","the-context-gold-rush-why-everyone-is-building-the-same-thing","You either die building product or live long enough to do context management.","https:\u002F\u002Fx.com\u002Fsamzliu\u002Fstatus\u002F2080210797465379147","blog","x","Sam Z Liu","samzliu","X","2026-07-23",[],[],1784930776,{"id":129,"name":130,"slug":131,"description":132,"url":133,"githubUrl":134,"logoUrl":135,"openSource":12,"categories":136,"repo":138,"company":-1,"articles":150,"createdAt":162},"entity_01kzsa6ykgextv2krhnxvx212d","Dynobox","dynobox","Cross-harness testing for multi-step agent flows","https:\u002F\u002Fdynobox.xyz","https:\u002F\u002Fgithub.com\u002Fdynobox\u002Fdynobox","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-6008b356.svg",[137],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":139,"url":134,"stars":67,"forks":17,"openIssues":17,"language":97,"license":26,"topics":140,"pushedAt":149,"archived":38},"dynobox\u002Fdynobox",[141,142,143,144,145,146,16,35,147,148],"agent","agent-skills","claude-code","cli","codex","devtools","opencode","testing","2026-08-12T16:11:17Z",[151],{"id":152,"name":153,"slug":154,"summary":155,"url":156,"kind":157,"platform":120,"author":158,"authorHandle":159,"publisher":123,"publishedAt":49,"about":160,"writtenBy":161,"createdAt":-1},"entity_01kzsa7tgbextv2kt75xknj5mg","Over engineering a pipeline to email me about strangers’ skills for dynobox","over-engineering-a-pipeline-to-email-me-about-strangers-skills-for-dynobox","For the past few weeks I've been building Dynobox - a local test runner that records what an agent does inside a harness (Claude Code, Codex, OpenCode etc.) and lets you write deterministic assertions against its non-deterministic behavior: tool calls, shell commands, files created or changed and so on.","https:\u002F\u002Fx.com\u002Fbhkdotdev\u002Fstatus\u002F2087281766440546814","article","bhk","bhkdotdev",[],[],1786482227,{"id":164,"name":165,"slug":166,"description":167,"url":168,"githubUrl":169,"logoUrl":170,"openSource":12,"categories":171,"repo":173,"company":-1,"articles":192,"createdAt":193},"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",[172],{"id":-1,"name":19,"slug":20,"count":17},{"fullName":174,"url":169,"stars":175,"forks":176,"openIssues":177,"language":25,"license":98,"topics":178,"pushedAt":191,"archived":38},"ucbepic\u002Fdocetl",3964,423,43,[179,180,181,182,183,184,185,35,186,187,188,189,190],"agents","data","data-pipelines","document-analysis","document-processing","elt","etl","python","semantic-data","unstructured-data","unstructured-data-analysis","workflow","2026-08-10T15:00:22Z",[],1784585384,{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":195,"repo":198,"company":-1,"articles":200,"createdAt":52},[196,197],{"id":-1,"name":15,"slug":16,"count":17},{"id":-1,"name":19,"slug":20,"count":17},{"fullName":22,"url":10,"stars":23,"forks":24,"openIssues":17,"language":25,"license":26,"topics":199,"pushedAt":37,"archived":38},[28,29,30,31,32,33,34,35,36],[201],{"id":41,"name":42,"slug":43,"summary":44,"url":45,"kind":46,"platform":47,"author":-1,"authorHandle":-1,"publisher":48,"publishedAt":49,"about":202,"writtenBy":203,"createdAt":-1},[],[],{"id":205,"name":206,"slug":207,"description":208,"url":209,"githubUrl":209,"logoUrl":-1,"openSource":12,"categories":210,"repo":212,"company":-1,"articles":218,"createdAt":219},"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",[211],{"id":-1,"name":19,"slug":20,"count":17},{"fullName":213,"url":209,"stars":214,"forks":96,"openIssues":215,"language":25,"license":98,"topics":216,"pushedAt":217,"archived":38},"FabioYanezRomero\u002FKnowledge-Graph-Builder",98,2,[],"2026-07-04T18:27:20Z",[],1786219226,{"id":221,"name":222,"slug":223,"description":224,"url":225,"githubUrl":226,"logoUrl":227,"openSource":12,"categories":228,"repo":230,"company":-1,"articles":246,"createdAt":247},"entity_01ky09k25gfanafx44rj2f9dpf","LangExtract","langextract","A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.","https:\u002F\u002Fpypi.org\u002Fproject\u002Flangextract\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Flangextract","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon.35549fe8-6dd120da.ico",[229],{"id":-1,"name":19,"slug":20,"count":17},{"fullName":231,"url":226,"stars":232,"forks":233,"openIssues":234,"language":25,"license":26,"topics":235,"pushedAt":245,"archived":38},"google\u002Flangextract",38325,2685,120,[236,237,238,239,240,241,242,35,243,186,244],"gemini","gemini-ai","gemini-api","gemini-flash","gemini-pro","information-extration","large-language-models","nlp","structured-data","2026-08-11T15:31:39Z",[],1784568973]