[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fc_OTAiCvHp8s82gqU7sjoHdV3qP7BfTyQ49c6twjlI4":3},{"tool":4,"categoryPool":53},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"createdAt":18,"repo":19,"company":31,"articles":38,"related":52},"entity_01m1j4rthkecrra0201jpxwm1h","Lily","lily","A small Metal inference server for one checkpoint: Qwen3.6-35B-A3B converted to MLX affine 4-bit weights. Lily exposes a minimal subset of the OpenAI chat completions API and always decodes greedily.","https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fpplx-garden\u002Ftree\u002Fmain\u002Flily","https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fpplx-garden","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fperplexityai-5f13f60b.png",true,[14],{"name":15,"slug":16,"count":17},"Local Inference","local-inference",0,1788389124,{"id":20,"fullName":21,"url":10,"stars":22,"forks":23,"openIssues":24,"language":25,"license":26,"topics":27,"pushedAt":28,"archived":29,"licenseSpdx":26,"licenseOsi":12,"licenseVerifiedAt":30},"entity_01m1j4s3dtecrra02nv5hcmaj5","perplexityai\u002Fpplx-garden",663,76,11,"Rust","MIT",[],"2026-09-02T22:40:14Z",false,"2026-09-02T22:45:33.550Z",{"id":32,"name":33,"slug":34,"url":35,"bio":36,"githubOrg":37},"entity_01m0x1n0vde8psca6weak9cqeq","Perplexity","perplexity","https:\u002F\u002Fwww.perplexity.ai","Perplexity is a free AI-powered answer engine that provides accurate, trusted, and real-time answers to any question.","ppl-ai",[39],{"id":40,"name":41,"slug":42,"summary":43,"url":44,"kind":45,"platform":46,"author":47,"publisher":48,"publishedAt":49,"about":50,"writtenBy":51},"entity_01m1j4kg0qe8g85y7vkv3m9nen","Optimizing On-Device Inference for Apple Silicon","optimizing-on-device-inference-for-apple-silicon","Perplexity's engineering team details Lily, a Rust-and-Metal local inference engine built specifically for Apple silicon and Qwen3.6-35B-A3B, which averages 1.23x MLX-LM's prefill and 1.35x its decode throughput on an M5 Max.","https:\u002F\u002Fwww.perplexity.ai\u002Fhub\u002Fblog\u002Foptimizing-on-device-inference-for-apple-silicon","blog","web","Perplexity Engineering","Perplexity AI","2026-09-01",[],[],[],[54,82,122,142],{"id":55,"name":56,"slug":57,"description":58,"url":59,"githubUrl":60,"openSource":12,"categories":61,"createdAt":63,"repo":64,"articles":80,"related":81},"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",[62],{"name":15,"slug":16,"count":17},1783120976,{"id":65,"fullName":66,"url":60,"stars":67,"forks":68,"openIssues":69,"language":70,"license":71,"topics":72,"pushedAt":78,"archived":29,"licenseSpdx":71,"licenseOsi":12,"licenseVerifiedAt":79},"entity_01ky37ze45fanrdkq2tpppa5wn","dosco\u002Faithy",107,7,1,"TypeScript","Apache-2.0",[73,74,75,76,77],"ai","ai-agent","llm","local-ai","personal-ai","2026-08-31T22:22:25Z","2026-08-09",[],[],{"id":83,"name":84,"slug":85,"description":86,"url":87,"githubUrl":88,"logoUrl":89,"openSource":12,"categories":90,"createdAt":92,"repo":93,"articles":120,"related":121},"entity_01m043e0bqecrveee97dwnb4ye","Atomic Chat","atomic-chat","Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.","https:\u002F\u002Fatomic.chat","https:\u002F\u002Fgithub.com\u002FAtomicBot-ai\u002FAtomic-Chat","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002F69e2483aac5ed9e90b9a4dfc_atomic256-3951ce0a.png",[91],{"name":15,"slug":16,"count":17},1786844217,{"id":94,"fullName":95,"url":88,"stars":96,"forks":97,"openIssues":98,"language":70,"topics":99,"pushedAt":118,"archived":29,"licenseSpdx":71,"licenseOsi":12,"licenseVerifiedAt":119},"entity_01m043e576fanbyrrwd6megcen","AtomicBot-ai\u002FAtomic-Chat",1418,161,42,[100,101,102,103,104,105,106,107,108,109,75,110,76,111,112,113,114,115,116,117],"ai-chat","ai-tools","apple-silicon","chatgpt","deepseek","desktop-app","gemma","gguf","gpt-oss","llamacpp","llm-inference","local-first","local-llm","mcp","mlx","open-source","qwen","self-hosted","2026-09-02T19:02:50Z","2026-08-16T01:37:02.508Z",[],[],{"id":123,"name":124,"slug":125,"description":126,"url":127,"githubUrl":127,"openSource":12,"categories":128,"createdAt":130,"repo":131,"articles":140,"related":141},"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",[129],{"name":15,"slug":16,"count":17},1784534307,{"id":132,"fullName":133,"url":127,"stars":134,"forks":135,"openIssues":136,"language":137,"license":71,"topics":138,"pushedAt":139,"archived":29,"licenseSpdx":71,"licenseOsi":12,"licenseVerifiedAt":79},"entity_01ky37wppefanrdk26w0yvwprq","JustVugg\u002Fcolibri",26699,2923,97,"C",[],"2026-09-02T16:23:23Z",[],[],{"id":143,"name":144,"slug":145,"description":146,"url":147,"githubUrl":147,"openSource":12,"categories":148,"createdAt":150,"repo":151,"articles":159,"related":160},"entity_01kxz8q9j7e4eb13m7d5zqk7m7","DwarfStar","ds4","DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm","https:\u002F\u002Fgithub.com\u002Fantirez\u002Fds4",[149],{"name":15,"slug":16,"count":17},1784534509,{"id":152,"fullName":153,"url":147,"stars":154,"forks":155,"openIssues":156,"language":137,"license":26,"topics":157,"pushedAt":158,"archived":29,"licenseSpdx":26,"licenseOsi":12,"licenseVerifiedAt":79},"entity_01ky37wmm1fanrdk1qbajh1xt4","antirez\u002Fds4",22019,2060,591,[],"2026-09-01T15:32:48Z",[],[]]