[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-raindrop":3},{"tool":4,"categoryPool":45},{"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":44},"entity_01kyb2metweshatkpk90b9xdwm","Raindrop","raindrop","Monitor your AI Agent the right way. Get alerted when your agent fails in production, trace exactly what went wrong, and prove your fix worked.","https:\u002F\u002Fwww.raindrop.ai\u002F","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fweb-app-manifest-192x192-bf87c429.png",false,[13],{"id":-1,"name":14,"slug":15,"count":16},"Evals","evals",0,[18,30],{"id":19,"name":20,"slug":21,"summary":22,"url":23,"kind":24,"platform":25,"author":26,"authorHandle":-1,"publisher":6,"publishedAt":27,"about":28,"writtenBy":29,"createdAt":-1},"entity_01kzew0b8me00sxrt30ebtxv9r","MCPs need to be designed too","mcps-need-to-be-designed-too","Our MCP tools were fine in isolation, but nothing chained, so conversations came back fragmented. Rebuilding them as a hierarchy cut cost 12% and time to final answer 27%.","https:\u002F\u002Fwww.raindrop.ai\u002Fblog\u002Fmcp-design\u002F","article","web","Jackson Ferrigno","2026-08-07",[],[],{"id":31,"name":32,"slug":33,"summary":34,"url":35,"kind":36,"platform":37,"author":38,"authorHandle":39,"publisher":40,"publishedAt":41,"about":42,"writtenBy":43,"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",[],[],1784930777,[46,78,99,113],{"id":47,"name":48,"slug":49,"description":50,"url":51,"githubUrl":51,"logoUrl":52,"openSource":53,"categories":54,"repo":56,"company":70,"articles":76,"createdAt":77},"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,[55],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":57,"url":51,"stars":58,"forks":59,"openIssues":60,"language":61,"license":62,"topics":63,"pushedAt":69,"archived":11},"alibaba\u002Faacr-bench",206,16,6,"Python","Apache-2.0",[64,65,66,67,68],"benchmark","code-review","multi-language","repository-level-context","software-engineering","2026-08-04T05:36:38Z",{"id":71,"name":72,"slug":73,"url":74,"bio":75,"githubOrg":73},"entity_01kzmeveq2f22bbn6jcepyspwk","Alibaba","alibaba","https:\u002F\u002Fwww.alibabagroup.com","Alibaba Open Source",[],1786217846,{"id":79,"name":80,"slug":81,"description":82,"url":83,"githubUrl":84,"logoUrl":85,"openSource":53,"categories":86,"repo":88,"company":-1,"articles":97,"createdAt":98},"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",[87],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":89,"url":84,"stars":90,"forks":91,"openIssues":92,"language":93,"license":94,"topics":95,"pushedAt":96,"archived":11},"stevibe\u002FBenchLocal",402,45,12,"TypeScript","MIT",[],"2026-08-10T15:10:36Z",[],1786390717,{"id":100,"name":101,"slug":102,"description":103,"url":104,"githubUrl":-1,"logoUrl":105,"openSource":11,"categories":106,"repo":-1,"company":-1,"articles":108,"createdAt":112},"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",[107],{"id":-1,"name":14,"slug":15,"count":16},[109],{"id":31,"name":32,"slug":33,"summary":34,"url":35,"kind":36,"platform":37,"author":38,"authorHandle":39,"publisher":40,"publishedAt":41,"about":110,"writtenBy":111,"createdAt":-1},[],[],1784930776,{"id":114,"name":115,"slug":116,"description":117,"url":118,"githubUrl":119,"logoUrl":120,"openSource":53,"categories":121,"repo":123,"company":-1,"articles":136,"createdAt":148},"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",[122],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":124,"url":119,"stars":60,"forks":16,"openIssues":16,"language":93,"license":62,"topics":125,"pushedAt":135,"archived":11},"dynobox\u002Fdynobox",[126,127,128,129,130,131,15,132,133,134],"agent","agent-skills","claude-code","cli","codex","devtools","llm","opencode","testing","2026-08-12T16:11:17Z",[137],{"id":138,"name":139,"slug":140,"summary":141,"url":142,"kind":24,"platform":37,"author":143,"authorHandle":144,"publisher":40,"publishedAt":145,"about":146,"writtenBy":147,"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","bhk","bhkdotdev","2026-08-11",[],[],1786482227]