[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-llama-cpp":3},{"tool":4,"categoryPool":52},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"repo":18,"company":-1,"articles":29,"createdAt":51},"entity_01kxwf9zs3fk0tcfyx58d6mr4e","llama.cpp","llama-cpp","LLM inference in C\u002FC++","https:\u002F\u002Fllama-cpp.com\u002F","https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fggml-org-5776db6c.png",true,[14],{"id":-1,"name":15,"slug":16,"count":17},"Local Inference","local-inference",0,{"fullName":19,"url":10,"stars":20,"forks":21,"openIssues":22,"language":23,"license":24,"topics":25,"pushedAt":27,"archived":28},"ggml-org\u002Fllama.cpp",123744,21650,2010,"C++","MIT",[26],"ggml","2026-08-13T08:41:39Z",false,[30,43],{"id":31,"name":32,"slug":33,"summary":34,"url":35,"kind":36,"platform":37,"author":38,"authorHandle":38,"publisher":39,"publishedAt":40,"about":41,"writtenBy":42,"createdAt":-1},"entity_01ky652fr4exrtp2zyeyte2szz","Every llama-server Flag Explained: The Tuning Guide For Local LLMs","every-llama-server-flag-explained-the-tuning-guide-for-local-llms","","https:\u002F\u002Fx.com\u002Fwitcheer\u002Fstatus\u002F2058980556524704220","article","x","witcheer","X","2026-05-25",[],[],{"id":44,"name":45,"slug":46,"summary":34,"url":47,"kind":36,"platform":37,"author":38,"authorHandle":38,"publisher":39,"publishedAt":48,"about":49,"writtenBy":50,"createdAt":-1},"entity_01ky65234bexrtp2z2q8x6a4cc","llama.cpp - Run Local LLMs On Your GPU","llama-cpp-run-local-llms-on-your-gpu","https:\u002F\u002Fx.com\u002Fwitcheer\u002Fstatus\u002F2057114938972291379","2026-05-20",[],[],1784440749,[53,78,96,113],{"id":54,"name":55,"slug":56,"description":57,"url":58,"githubUrl":59,"logoUrl":-1,"openSource":12,"categories":60,"repo":62,"company":-1,"articles":76,"createdAt":77},"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",[61],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":63,"url":59,"stars":64,"forks":65,"openIssues":66,"language":67,"license":68,"topics":69,"pushedAt":75,"archived":28},"dosco\u002Faithy",107,7,1,"TypeScript","Apache-2.0",[70,71,72,73,74],"ai","ai-agent","llm","local-ai","personal-ai","2026-07-16T08:25:13Z",[],1783120976,{"id":79,"name":80,"slug":81,"description":82,"url":83,"githubUrl":83,"logoUrl":-1,"openSource":12,"categories":84,"repo":86,"company":-1,"articles":94,"createdAt":95},"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",[85],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":87,"url":83,"stars":88,"forks":89,"openIssues":90,"language":91,"license":68,"topics":92,"pushedAt":93,"archived":28},"JustVugg\u002Fcolibri",24369,2658,125,"C",[],"2026-08-12T15:34:41Z",[],1784534307,{"id":97,"name":98,"slug":99,"description":100,"url":101,"githubUrl":101,"logoUrl":-1,"openSource":12,"categories":102,"repo":104,"company":-1,"articles":111,"createdAt":112},"entity_01kxz8q9j7e4eb13m7d5zqk7m7","DwarfStar","ds4","DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm","https:\u002F\u002Fgithub.com\u002Fantirez\u002Fds4",[103],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":105,"url":101,"stars":106,"forks":107,"openIssues":108,"language":91,"license":24,"topics":109,"pushedAt":110,"archived":28},"antirez\u002Fds4",21282,1937,469,[],"2026-08-09T18:31:13Z",[],1784534509,{"id":114,"name":115,"slug":116,"description":117,"url":118,"githubUrl":119,"logoUrl":120,"openSource":12,"categories":121,"repo":123,"company":-1,"articles":130,"createdAt":131},"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",[122],{"id":-1,"name":15,"slug":16,"count":17},{"fullName":124,"url":119,"stars":125,"forks":126,"openIssues":17,"language":127,"license":-1,"topics":128,"pushedAt":129,"archived":28},"Blaizzy\u002Ffastmlx",24,4,"Python",[],"2024-11-18T22:51:05Z",[],1784440758]