[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-openinfer":3},{"tool":4,"categoryPool":49},{"id":5,"name":6,"slug":6,"description":7,"url":8,"githubUrl":9,"logoUrl":10,"openSource":11,"categories":12,"repo":17,"company":-1,"articles":47,"createdAt":48},"entity_01ky08gph0e8j9hpn6pwnrtrqa","openinfer","Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2","https:\u002F\u002Fopen-infer.org\u002F","https:\u002F\u002Fgithub.com\u002Fopeninfer-project\u002Fopeninfer","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-870f4cfa.png",true,[13],{"id":-1,"name":14,"slug":15,"count":16},"Local Inference","local-inference",0,{"fullName":18,"url":9,"stars":19,"forks":20,"openIssues":21,"language":22,"license":23,"topics":24,"pushedAt":45,"archived":46},"openinfer-project\u002Fopeninfer",642,98,146,"Rust","Apache-2.0",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"cuda","cuda-kernels","deepseek","gpu","inference","inference-engine","kimi","kimi-k2","kv-cache","llm","llm-inference","llm-serving","model-serving","moe","openai-api","paged-attention","qwen","qwen3","rust","vllm","2026-08-13T09:02:31Z",false,[],1784567847,[50,73,91,109],{"id":51,"name":52,"slug":53,"description":54,"url":55,"githubUrl":56,"logoUrl":-1,"openSource":11,"categories":57,"repo":59,"company":-1,"articles":71,"createdAt":72},"entity_01kwn4npgyf25rdkpzwh66v1kr","Aithy","aithy","Aithy is a private local AI runtime for state-of-the-art agent research, local inference, sandboxed tools, durable memory, and LAN Mesh resource sharing.","https:\u002F\u002Faithy.dev\u002F","https:\u002F\u002Fgithub.com\u002Fdosco\u002Faithy",[58],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":60,"url":56,"stars":61,"forks":62,"openIssues":63,"language":64,"license":23,"topics":65,"pushedAt":70,"archived":46},"dosco\u002Faithy",107,7,1,"TypeScript",[66,67,34,68,69],"ai","ai-agent","local-ai","personal-ai","2026-07-16T08:25:13Z",[],1783120976,{"id":74,"name":75,"slug":76,"description":77,"url":78,"githubUrl":78,"logoUrl":-1,"openSource":11,"categories":79,"repo":81,"company":-1,"articles":89,"createdAt":90},"entity_01kxz8h4cxe4eb13j1t9zbqnfc","Colibri","colibri","Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦","https:\u002F\u002Fgithub.com\u002FJustVugg\u002Fcolibri",[80],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":82,"url":78,"stars":83,"forks":84,"openIssues":85,"language":86,"license":23,"topics":87,"pushedAt":88,"archived":46},"JustVugg\u002Fcolibri",24369,2658,125,"C",[],"2026-08-12T15:34:41Z",[],1784534307,{"id":92,"name":93,"slug":94,"description":95,"url":96,"githubUrl":96,"logoUrl":-1,"openSource":11,"categories":97,"repo":99,"company":-1,"articles":107,"createdAt":108},"entity_01kxz8q9j7e4eb13m7d5zqk7m7","DwarfStar","ds4","DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm","https:\u002F\u002Fgithub.com\u002Fantirez\u002Fds4",[98],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":100,"url":96,"stars":101,"forks":102,"openIssues":103,"language":86,"license":104,"topics":105,"pushedAt":106,"archived":46},"antirez\u002Fds4",21282,1937,469,"MIT",[],"2026-08-09T18:31:13Z",[],1784534509,{"id":110,"name":111,"slug":112,"description":113,"url":114,"githubUrl":115,"logoUrl":116,"openSource":11,"categories":117,"repo":119,"company":-1,"articles":126,"createdAt":127},"entity_01kxwfa7trfk0tcg0ej31575e7","FastMLX","fastmlx","FastMLX is a high performance production ready API to host MLX models.","https:\u002F\u002Fblaizzy.github.io\u002Ffastmlx\u002F","https:\u002F\u002Fgithub.com\u002FBlaizzy\u002Ffastmlx","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-5325c06d.png",[118],{"id":-1,"name":14,"slug":15,"count":16},{"fullName":120,"url":115,"stars":121,"forks":122,"openIssues":16,"language":123,"license":-1,"topics":124,"pushedAt":125,"archived":46},"Blaizzy\u002Ffastmlx",24,4,"Python",[],"2024-11-18T22:51:05Z",[],1784440758]