[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-aacr-bench":3},{"tool":4,"categoryPool":40},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":9,"logoUrl":10,"openSource":11,"categories":12,"repo":17,"company":32,"articles":38,"createdAt":39},"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",true,[13],{"id":-1,"name":14,"slug":15,"count":16},"Evals","evals",0,{"fullName":18,"url":9,"stars":19,"forks":20,"openIssues":21,"language":22,"license":23,"topics":24,"pushedAt":30,"archived":31},"alibaba\u002Faacr-bench",206,16,6,"Python","Apache-2.0",[25,26,27,28,29],"benchmark","code-review","multi-language","repository-level-context","software-engineering","2026-08-04T05:36:38Z",false,{"id":33,"name":34,"slug":35,"url":36,"bio":37,"githubOrg":35},"entity_01kzmeveq2f22bbn6jcepyspwk","Alibaba","alibaba","https:\u002F\u002Fwww.alibabagroup.com","Alibaba Open Source",[],1786217846,[41,48,69,94],{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":9,"logoUrl":10,"openSource":11,"categories":42,"repo":44,"company":46,"articles":47,"createdAt":39},[43],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":18,"url":9,"stars":19,"forks":20,"openIssues":21,"language":22,"license":23,"topics":45,"pushedAt":30,"archived":31},[25,26,27,28,29],{"id":33,"name":34,"slug":35,"url":36,"bio":37,"githubOrg":35},[],{"id":49,"name":50,"slug":51,"description":52,"url":53,"githubUrl":54,"logoUrl":55,"openSource":11,"categories":56,"repo":58,"company":-1,"articles":67,"createdAt":68},"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",[57],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":59,"url":54,"stars":60,"forks":61,"openIssues":62,"language":63,"license":64,"topics":65,"pushedAt":66,"archived":31},"stevibe\u002FBenchLocal",402,45,12,"TypeScript","MIT",[],"2026-08-10T15:10:36Z",[],1786390717,{"id":70,"name":71,"slug":72,"description":73,"url":74,"githubUrl":-1,"logoUrl":75,"openSource":31,"categories":76,"repo":-1,"company":-1,"articles":78,"createdAt":93},"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",[77],{"id":-1,"name":14,"slug":15,"count":16},[79],{"id":80,"name":81,"slug":82,"summary":83,"url":84,"kind":85,"platform":86,"author":87,"authorHandle":88,"publisher":89,"publishedAt":90,"about":91,"writtenBy":92,"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":95,"name":96,"slug":97,"description":98,"url":99,"githubUrl":100,"logoUrl":101,"openSource":11,"categories":102,"repo":104,"company":-1,"articles":117,"createdAt":130},"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",[103],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":105,"url":100,"stars":21,"forks":16,"openIssues":16,"language":63,"license":23,"topics":106,"pushedAt":116,"archived":31},"dynobox\u002Fdynobox",[107,108,109,110,111,112,15,113,114,115],"agent","agent-skills","claude-code","cli","codex","devtools","llm","opencode","testing","2026-08-12T16:11:17Z",[118],{"id":119,"name":120,"slug":121,"summary":122,"url":123,"kind":124,"platform":86,"author":125,"authorHandle":126,"publisher":89,"publishedAt":127,"about":128,"writtenBy":129,"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","2026-08-11",[],[],1786482227]