Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
- apple-silicon
- inference
- machine-learning
- mlx
142,273 visible repositories in the index
49–72 of 918 · Most stars
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
TranslatedAnti-getting-lost | 禁漫天堂 (JMComic, "Forbidden Manga Paradise") APK | 禁漫 (JMComic) app Android installation package | jm天堂 (JM Paradise) | 回家 (Going Home) | GitHub Actions | JMComic3 | JMComic2
The control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimes—from local SQLite to team scale.
Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling salesman)
TranslatedThe most comprehensive game development technology map (Game Development Map). It helps game developers save time on known problems, so they can put more energy into more creative work.
TranslatedKorean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells — a Claude skill that polishes Korean text written by AI so it reads like human writing
TranslatedFirefly: a large model training tool that supports training large models such as Qwen2.5, Qwen2, Yi1.5, Phi-3, Llama3, Gemma, MiniCPM, Yi, Deepseek, Orion, Xverse, Mixtral-8x7B, Zephyr, Mistral, Baichuan2, Llma2, Llama, Qwen, Baichuan, ChatGLM2, InternLM, Ziya2, Vicuna, Bloom, etc.
TranslatedOpen source online judge based on Vue, Django and Docker. | Qingdao University open source Online Judge | QQ group 496710125 | [email protected]
TranslatedClaude Code + OpenClaw + Codex + WorkBuddy Chinese tutorials | 50 complete tutorials + 1 quick reference card | 800,000+ characters of content | 1,500+ hands-on examples | AI Coding / Agent four-track learning path (programming + assistant + Agent + office work)
95.47% on CIFAR10 with PyTorch
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
🕵️♂️ (2-in-1) Email & Username OSINT suite featuring native MCP support for deep data extraction just from a single Email/Username. Analyzes 2720+ actively maintained scan vectors (210+ email / 2510+ username) for security research, investigations, and digital footprinting.
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Translated[deepin repository port] A quick way to install QQ/WeChat on Debian/Ubuntu
Free, offline checks for known mercenary spyware on Windows, Mac, Linux, iPhone and Android - plus the doors left open, suspicious links, emails, files and QR codes, your accounts, home network and nearby trackers. Apps with a window, 27 languages. Nothing leaves your computer.
Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative
Count the MACs / FLOPs of your PyTorch model.
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
AI powered OSINT engine to discover and map 7,700+ social media identities across the web
The repository host gives no description.
Modern YouTube downloader with a clean PySide6 interface. Download videos in any quality, extract audio, fetch subtitles, sponsorBlock, and view video metadata. Built with yt-dlp for reliable performance.