{
 "repo": "trymirai/uzu",
 "url": "https://github.com/trymirai/uzu",
 "what": "uzu is a high-performance inference engine for running AI models directly inside your app, with zero latency, full data privacy and no inference costs. It has a simple high-level API in Rust, Python, Swift and TypeScript, downloads models such as Qwen 3.5 0.8B automatically, uses unified memory on Apple devices and supports streaming chat replies.",
 "language": "Rust",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "Uzu",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/trymirai-uzu/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/trymirai-uzu.json",
 "json": "https://dedupedai.com/repos/r/trymirai-uzu.json",
 "slug": "trymirai-uzu",
 "api": "https://dedupedai.com/api/v1/repos/trymirai-uzu.json",
 "api_version": "v1"
}