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