[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f1HtwPefu9sWhf_MFLZNIvvruvJM0yvnk1RObjZgZPhY":3},{"tool":4,"categoryPool":52},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"createdAt":18,"repo":19,"articles":50,"related":51},"entity_01m7js6jf9eh3b0pkmsyw9qsw3","MCPJam Inspector","mcpjam-inspector","Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.","https:\u002F\u002Fwww.mcpjam.com\u002F","https:\u002F\u002Fgithub.com\u002FMCPJam\u002Finspector","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fmcpjam-inspector-da629a35.png",true,[14],{"name":15,"slug":16,"count":17},"Evals","evals",0,1794852997,{"id":20,"fullName":21,"url":10,"stars":22,"forks":23,"openIssues":24,"language":25,"topics":26,"pushedAt":46,"archived":47,"licenseSpdx":48,"licenseOsi":12,"licenseVerifiedAt":49},"entity_01m7js6k49eh3b0pm0cfkmg7ec","MCPJam\u002Finspector",2331,305,375,"TypeScript",[27,28,29,30,16,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"anthropic","chatgpt","cicd","debugger","evaluation","inspector","mcp","mcp-apps","mcp-clients","mcp-inspector","mcp-server","mcp-tools","modelcontextprotocol","oauth","oauth2","openai","openai-apps-sdk","opensource","tracing","2026-11-19T05:14:22Z",false,"Apache-2.0","2026-11-16T18:14:15.760Z",[],[],[53,86,109,154],{"id":54,"name":55,"slug":56,"description":57,"url":58,"githubUrl":58,"logoUrl":59,"openSource":12,"categories":60,"createdAt":62,"repo":63,"company":78,"articles":84,"related":85},"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",[61],{"name":15,"slug":16,"count":17},1786217846,{"id":64,"fullName":65,"url":58,"stars":66,"forks":67,"openIssues":68,"language":69,"license":48,"topics":70,"pushedAt":76,"archived":47,"licenseSpdx":48,"licenseOsi":12,"licenseVerifiedAt":77},"entity_01kzhe2qyzfagsad286a44dm07","alibaba\u002Faacr-bench",265,35,9,"Python",[71,72,73,74,75],"benchmark","code-review","multi-language","repository-level-context","software-engineering","2026-11-16T12:36:19Z","2026-08-09",{"id":79,"name":80,"slug":81,"url":82,"bio":83,"githubOrg":81},"entity_01kzmeveq2f22bbn6jcepyspwk","Alibaba","alibaba","https:\u002F\u002Fwww.alibabagroup.com","Alibaba Open Source",[],[],{"id":87,"name":88,"slug":89,"description":90,"url":91,"githubUrl":92,"logoUrl":93,"openSource":12,"categories":94,"createdAt":96,"repo":97,"articles":107,"related":108},"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",[95],{"name":15,"slug":16,"count":17},1786390717,{"id":98,"fullName":99,"url":92,"stars":100,"forks":101,"openIssues":102,"language":25,"license":103,"topics":104,"pushedAt":105,"archived":47,"licenseSpdx":103,"licenseOsi":12,"licenseVerifiedAt":106},"entity_01kzpjybr1e4fah37p1vzk0558","stevibe\u002FBenchLocal",434,52,20,"MIT",[],"2026-08-10T15:10:36Z","2026-08-10",[],[],{"id":110,"name":111,"slug":112,"description":113,"url":114,"logoUrl":115,"openSource":47,"categories":116,"createdAt":121,"company":122,"articles":126,"related":153},"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",[117,118],{"name":15,"slug":16,"count":17},{"name":119,"slug":120,"count":17},"Observability","observability",1784930776,{"id":123,"name":111,"slug":112,"url":124,"bio":113,"githubOrg":125},"entity_01kzmevhdaf22bbn7meq79a9a8","https:\u002F\u002Fbraintrust.dev\u002F","braintrustdata",[127,141],{"id":128,"name":129,"slug":130,"summary":131,"url":132,"kind":133,"platform":134,"author":135,"authorHandle":136,"publisher":137,"publishedAt":138,"about":139,"writtenBy":140},"entity_01m7jtkq31e4davq4vs52gzkm8","The Trace Lake","the-trace-lake","Tracing was originally conceived as a mechanism to understand the bottlenecks in complex, multi-service software.","https:\u002F\u002Fx.com\u002Fankrgyl\u002Fstatus\u002F2117696780741771638","article","x","Ankur Goyal","ankrgyl","X","2026-11-03",[],[],{"id":142,"name":143,"slug":144,"summary":145,"url":146,"kind":147,"platform":134,"author":148,"authorHandle":149,"publisher":137,"publishedAt":150,"about":151,"writtenBy":152},"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","Sam Z Liu","samzliu","2026-07-23",[],[],[],{"id":155,"name":156,"slug":157,"description":158,"url":159,"logoUrl":160,"openSource":47,"categories":161,"createdAt":163,"company":164,"articles":171,"related":182},"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",[162],{"name":15,"slug":16,"count":17},1786655638,{"id":165,"name":166,"slug":167,"url":168,"bio":169,"githubOrg":170},"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",[172],{"id":173,"name":174,"slug":175,"summary":176,"url":177,"kind":133,"platform":134,"author":166,"authorHandle":178,"publisher":137,"publishedAt":179,"about":180,"writtenBy":181},"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","_hex_tech","2026-08-13",[],[],[]]