[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-aimock":3},{"tool":4,"categoryPool":34},{"id":5,"name":6,"slug":6,"description":7,"url":8,"githubUrl":9,"logoUrl":10,"openSource":11,"categories":12,"repo":17,"company":-1,"articles":32,"createdAt":33},"entity_01kzpf1ejjfajsm812jm45mzh9","aimock","Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies.","http:\u002F\u002Faimock.copilotkit.dev\u002F","https:\u002F\u002Fgithub.com\u002FCopilotKit\u002Faimock","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-e7b2266f.svg",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},"CopilotKit\u002Faimock",693,45,4,"TypeScript","MIT",[25,6,26,27,28,29],"ai-testing","llm","mcp","mock-server","openai","2026-08-12T20:39:33Z",false,[],1786386627,[35,66,84,109],{"id":36,"name":37,"slug":38,"description":39,"url":40,"githubUrl":40,"logoUrl":41,"openSource":11,"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",[43],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":45,"url":40,"stars":46,"forks":47,"openIssues":48,"language":49,"license":50,"topics":51,"pushedAt":57,"archived":31},"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":11,"categories":74,"repo":76,"company":-1,"articles":82,"createdAt":83},"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":20,"openIssues":79,"language":22,"license":23,"topics":80,"pushedAt":81,"archived":31},"stevibe\u002FBenchLocal",402,12,[],"2026-08-10T15:10:36Z",[],1786390717,{"id":85,"name":86,"slug":87,"description":88,"url":89,"githubUrl":-1,"logoUrl":90,"openSource":31,"categories":91,"repo":-1,"company":-1,"articles":93,"createdAt":108},"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",[92],{"id":-1,"name":14,"slug":15,"count":16},[94],{"id":95,"name":96,"slug":97,"summary":98,"url":99,"kind":100,"platform":101,"author":102,"authorHandle":103,"publisher":104,"publishedAt":105,"about":106,"writtenBy":107,"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":110,"name":111,"slug":112,"description":113,"url":114,"githubUrl":115,"logoUrl":116,"openSource":11,"categories":117,"repo":119,"company":-1,"articles":131,"createdAt":144},"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",[118],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":120,"url":115,"stars":48,"forks":16,"openIssues":16,"language":22,"license":50,"topics":121,"pushedAt":130,"archived":31},"dynobox\u002Fdynobox",[122,123,124,125,126,127,15,26,128,129],"agent","agent-skills","claude-code","cli","codex","devtools","opencode","testing","2026-08-12T16:11:17Z",[132],{"id":133,"name":134,"slug":135,"summary":136,"url":137,"kind":138,"platform":101,"author":139,"authorHandle":140,"publisher":104,"publishedAt":141,"about":142,"writtenBy":143,"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]