[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fwvGIsAW61Yo5Jlmuot6Hm2IlnIc0CU1QluNtIBFeG58":3},{"tool":4,"categoryPool":30},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"openSource":11,"categories":12,"createdAt":17,"repo":18,"articles":28,"related":29},"entity_01m5mwkfh5ecxa8p23hq35kvyd","MemoryTax","memorytax","MemoryTax: The Bitter Lesson of Agent Memory. Code, data and paper.","https:\u002F\u002Fzedongpeng.com\u002Fmemorytax\u002F","https:\u002F\u002Fgithub.com\u002Fzedong-peng\u002Fmemorytax",true,[13],{"name":14,"slug":15,"count":16},"Evals","evals",0,1792776191,{"id":19,"fullName":20,"url":10,"stars":21,"forks":16,"openIssues":16,"language":22,"license":23,"topics":24,"pushedAt":25,"archived":26,"licenseSpdx":23,"licenseOsi":11,"licenseVerifiedAt":27},"entity_01m5mwkmp6ecxa8p2wv1bz4zhm","zedong-peng\u002Fmemorytax",6,"HTML","MIT",[],"2026-10-25T18:53:55Z",false,"2026-10-23T17:23:16.679Z",[],[],[31,65,88,121],{"id":32,"name":33,"slug":34,"description":35,"url":36,"githubUrl":36,"logoUrl":37,"openSource":11,"categories":38,"createdAt":40,"repo":41,"company":57,"articles":63,"related":64},"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",[39],{"name":14,"slug":15,"count":16},1786217846,{"id":42,"fullName":43,"url":36,"stars":44,"forks":45,"openIssues":46,"language":47,"license":48,"topics":49,"pushedAt":55,"archived":26,"licenseSpdx":48,"licenseOsi":11,"licenseVerifiedAt":56},"entity_01kzhe2qyzfagsad286a44dm07","alibaba\u002Faacr-bench",255,33,9,"Python","Apache-2.0",[50,51,52,53,54],"benchmark","code-review","multi-language","repository-level-context","software-engineering","2026-10-15T07:13:55Z","2026-08-09",{"id":58,"name":59,"slug":60,"url":61,"bio":62,"githubOrg":60},"entity_01kzmeveq2f22bbn6jcepyspwk","Alibaba","alibaba","https:\u002F\u002Fwww.alibabagroup.com","Alibaba Open Source",[],[],{"id":66,"name":67,"slug":68,"description":69,"url":70,"githubUrl":71,"logoUrl":72,"openSource":11,"categories":73,"createdAt":75,"repo":76,"articles":86,"related":87},"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",[74],{"name":14,"slug":15,"count":16},1786390717,{"id":77,"fullName":78,"url":71,"stars":79,"forks":80,"openIssues":81,"language":82,"license":23,"topics":83,"pushedAt":84,"archived":26,"licenseSpdx":23,"licenseOsi":11,"licenseVerifiedAt":85},"entity_01kzpjybr1e4fah37p1vzk0558","stevibe\u002FBenchLocal",433,51,20,"TypeScript",[],"2026-08-10T15:10:36Z","2026-08-10",[],[],{"id":89,"name":90,"slug":91,"description":92,"url":93,"logoUrl":94,"openSource":26,"categories":95,"createdAt":100,"company":101,"articles":105,"related":120},"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",[96,97],{"name":14,"slug":15,"count":16},{"name":98,"slug":99,"count":16},"Observability","observability",1784930776,{"id":102,"name":90,"slug":91,"url":103,"bio":92,"githubOrg":104},"entity_01kzmevhdaf22bbn7meq79a9a8","https:\u002F\u002Fbraintrust.dev\u002F","braintrustdata",[106],{"id":107,"name":108,"slug":109,"summary":110,"url":111,"kind":112,"platform":113,"author":114,"authorHandle":115,"publisher":116,"publishedAt":117,"about":118,"writtenBy":119},"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",[],[],[],{"id":122,"name":123,"slug":124,"description":125,"url":126,"logoUrl":127,"openSource":26,"categories":128,"createdAt":130,"company":131,"articles":138,"related":150},"entity_01kzyfk0nweh5b7faygzq2rgzz","DataBench","databench","DataBench scores frontier AI on the analytics work that matters — reasoning, reporting, and investigation on realistic, messy warehouse data.","https:\u002F\u002Fhex.tech\u002Fdatabench\u002F","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-32ee2db0.svg",[129],{"name":14,"slug":15,"count":16},1786655638,{"id":132,"name":133,"slug":134,"url":135,"bio":136,"githubOrg":137},"entity_01kzyfhc52eh5b7fac540s653f","Hex","hex","https:\u002F\u002Fhex.tech","Finally — anyone can get data insights grounded in the facts of their business. Hex has a flexible approach to context that earns trust without slowing you down.","hex-inc",[139],{"id":140,"name":141,"slug":142,"summary":143,"url":144,"kind":145,"platform":113,"author":133,"authorHandle":146,"publisher":116,"publishedAt":147,"about":148,"writtenBy":149},"entity_01kzye6311esg9ae93nr6enft3","Introducing DataBench","introducing-databench","DataBench v1: 100 realistic analytical tasks across Q&A and open-ended prompts, run in a synthetic Hex workspace — built because existing analytics benchmarks test \"overspecified pub trivia\" rather than the vague, directional questions people actually ask.","https:\u002F\u002Fx.com\u002F_hex_tech\u002Fstatus\u002F2087946398390206512","article","_hex_tech","2026-08-13",[],[],[]]