Repositories

GitHub Trending repo Aug 5

cursorgrok4-5free/Cursor-Grok-4.5-xAI-free: Cursor Grok 4.5 free desktop for Windows, macOS and Linux without X Premium. Grok 4.5 free on Cursor, grok 4.5 free API key and free tier, grok 4.5 vs Opus 5 vs GPT-5.6, grok 4.5 EU release, grok 4.5 app download, grok 4.5 benchmark. No X Premium needed. Real-time web search and coding. Download Cursor Grok 4.5 desktop free 2026.

Cursor Grok 4.5 free desktop for Windows, macOS and Linux without X Premium. Grok 4.5 free on Cursor, grok 4.5 free API key and free tier, grok 4.5 vs Opus 5 vs GPT-5.6, grok 4.5 E...

OpenAI xAI Code Generation

63

GitHub Trending repo Aug 5

BennyDaBall930/ComfyUI-Latent-Tiled-PiD: Tile the latent, not the pixels: native ComfyUI nodes for latent-native tiled NVIDIA PiD decoding. Seam-free 33-107MP masters; tested on Krea 2 Turbo.

Tile the latent, not the pixels: native ComfyUI nodes for latent-native tiled NVIDIA PiD decoding. Seam-free 33-107MP masters; tested on Krea 2 Turbo.

NVIDIA

35

GitHub Trending repo Aug 5

mithinsagar/aws-ai-resource-cleanup: Smart cloud hygiene tool that scans your AWS account for dead resources and cleans them up automatically. Powered by Boto3, scikit-learn and a Flask dashboard. Research backed, production ready.

Smart cloud hygiene tool that scans your AWS account for dead resources and cleans them up automatically. Powered by Boto3, scikit-learn and a Flask dashboard. Research backed, pro...

42

GitHub Trending repo Aug 5

liujunxibaba/douyin-tiktok-story-skill-agent: Local-first AI Skill and Agent for creating original Douyin and TikTok story scripts with a searchable SQLite reference database.

Local-first AI Skill and Agent for creating original Douyin and TikTok story scripts with a searchable SQLite reference database.

65

GitHub Trending repo Aug 5

lucidrains/light-loco-parkour: Implementation of Light Loco Parkour, Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation, out of Light Origins Labs

Implementation of Light Loco Parkour, Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation, out of Light Origins Labs

45

GitHub Trending repo Aug 5

redrob-labs/redrob-studio: Local Next.js studio for image and audio tools, backed by ComfyUI on your own GPU. Nothing is sent to a hosted inference API (Apache-2.0).

Local Next.js studio for image and audio tools, backed by ComfyUI on your own GPU. Nothing is sent to a hosted inference API (Apache-2.0).

AI Hardware API

38

GitHub Trending repo Aug 5

alexscheinker/round-trip-consistency: Bidirectional diffusion models that predict their own rollout errors: code for arXiv:2608.00675.

Bidirectional diffusion models that predict their own rollout errors: code for arXiv:2608.00675.

35

GitHub Trending repo Aug 5

UditAkhourii/neuroarxiv: A skill to kill from-scratch coding — Claude checks real arXiv prior art before it designs a new architecture.

A skill to kill from-scratch coding — Claude checks real arXiv prior art before it designs a new architecture.

Anthropic

64

GitHub Trending repo Aug 5

redrob-labs/redrob-image: Redrob Image: open-weight text-to-image model by Redrob. Free to use, free for commercial use (Apache-2.0).

Redrob Image: open-weight text-to-image model by Redrob. Free to use, free for commercial use (Apache-2.0).

Image Generation

35

GitHub Trending repo Aug 5

Binaryify/open-kimi-ppt-skill: 非官方 Kimi Slides Skill：让 AI Agent 生成可编辑 PPTD + PPTX，并附带本地浏览器编辑器 Unofficial Kimi Slides skill for AI agents — generate editable PPTD + PPTX with a local browser editor

非官方 Kimi Slides Skill：让 AI Agent 生成可编辑 PPTD + PPTX，并附带本地浏览器编辑器 Unofficial Kimi Slides skill for AI agents — generate editable PPTD + PPTX with a local browser editor

Agents

66

GitHub Trending repo Aug 5

GabriWar/bc250-rocm-working: Stable Diffusion working on an AMD BC-250 (gfx1013 / PS5 APU): kernel patches, rocBLAS gfx1013 kernels, and the full investigation

Stable Diffusion working on an AMD BC-250 (gfx1013 / PS5 APU): kernel patches, rocBLAS gfx1013 kernels, and the full investigation

Stability AI

38

GitHub Trending repo Aug 5

Zirakin/airport-recommendation: 2026年最新高性价比机场推荐 | 科学上网 | 梯子推荐 | VPN推荐 | 支持 Clash | V2Ray | Sing-box | Shadowrocket 节点，附带详细的配置教程，包你满意

2026年最新高性价比机场推荐 | 科学上网 | 梯子推荐 | VPN推荐 | 支持 Clash | V2Ray | Sing-box | Shadowrocket 节点，附带详细的配置教程，包你满意

63

GitHub Trending repo Aug 5

KKKKhazix/human-writing: 让 AI 写的中文读起来像一个具体的人在说话。通用创作与改稿 Skill，开箱即用。

让 AI 写的中文读起来像一个具体的人在说话。通用创作与改稿 Skill，开箱即用。

77

GitHub Trending repo Aug 4

fxfx122344/polymarket-btc-5m-reverse-trading-bot-using-AI-making-decision-model: polymarket bitcoin btc trading-bot prediction-markets ai-trading machine-learning gradient-boosting backtesting paper-trading crypto python quantitative-finance algorithmic-trading

polymarket bitcoin btc trading-bot prediction-markets ai-trading machine-learning gradient-boosting backtesting paper-trading crypto python quantitative-finance algorithmic-trading

48

GitHub Trending repo Aug 4

ayoubfliless/edge-stress-detection: Real-time deep-learning crop-stress detection on Edge devices from UAV multispectral imagery

Real-time deep-learning crop-stress detection on Edge devices from UAV multispectral imagery

39

GitHub Trending repo Aug 4

claude-mythos5/Claude-Mythos5-AI-Free-desktop: Claude Mythos 5 AI free desktop app - what is Claude Mythos? Anthropic's restricted AI model released June 9, 2026 for US government Project Glasswing. Claude Fable 5 vs Mythos 5 vs Opus 5 vs GPT 5.6 Sol comparison: same weights, Mythos has cybersecurity capabilities. Download Claude desktop app free, includes Fable 5.

Claude Mythos 5 AI free desktop app - what is Claude Mythos? Anthropic's restricted AI model released June 9, 2026 for US government Project Glasswing. Claude Fable 5 vs Mythos 5 v...

Anthropic

64

GitHub Trending repo Aug 4

Anil-matcha/wan-3.0-comfyui: ComfyUI custom nodes for Wan 3.0 — text-to-image, image edit, text-to-video, and image-to-video via MuAPI.

ComfyUI custom nodes for Wan 3.0 — text-to-image, image edit, text-to-video, and image-to-video via MuAPI.

Image Generation Video Generation

35

GitHub Trending repo Aug 4

Morteza-Asadi-Shalmaiy/Superres-fr: Convolutional autoencoder trained from scratch on CelebA faces — 128-dim latent space, full checkpoint/resume support, built to run end-to-end in Google Colab.

Convolutional autoencoder trained from scratch on CelebA faces — 128-dim latent space, full checkpoint/resume support, built to run end-to-end in Google Colab.

Google

43

GitHub Trending repo Aug 4

criptogus/HermesOffice: HermesOffice — AI-native office suite forked from GenOffice (Apache-2.0), with native Hermes Agent AI

HermesOffice — AI-native office suite forked from GenOffice (Apache-2.0), with native Hermes Agent AI

63

GitHub Trending repo Aug 4

lemonade-sdk/thenoise: A text-to-image diffusion inference engine.

A text-to-image diffusion inference engine.

Image Generation API

32

GitHub Trending repo Aug 4

Icyoung/ComfyUI-MiniMaxH3-TeaCache: Timestep-cache acceleration for MiniMax H3 in ComfyUI — open source, cross-platform, ~3x speedup measured

Timestep-cache acceleration for MiniMax H3 in ComfyUI — open source, cross-platform, ~3x speedup measured

Open Source

35

GitHub Trending repo Aug 4

iqrakhan07/Machine-Learning-Day-10-Projects: Machine Learning Day 10 Projects using XGBoost | Electricity Consumption Prediction & Air Quality Index (AQI) Prediction | Python, Pandas, Scikit-learn, XGBoost

Machine Learning Day 10 Projects using XGBoost | Electricity Consumption Prediction & Air Quality Index (AQI) Prediction | Python, Pandas, Scikit-learn, XGBoost

38

GitHub Trending repo Aug 4

crawfordxx/xiaoma-durex-copywriter: 杜蕾斯式文案与海报 Skill for Claude Code —— 双层语义方法论 + 8 个文案公式 + 从 260 张原始海报拆解的视觉系统 + AI 出图/代码排版管线

杜蕾斯式文案与海报 Skill for Claude Code —— 双层语义方法论 + 8 个文案公式 + 从 260 张原始海报拆解的视觉系统 + AI 出图/代码排版管线

Anthropic

65

GitHub Trending repo Aug 4

lgpintomkt/pimmm: Physics-Informed Marketing Mix Modeling (pimmm) is a Python library that unifies machine learning response surfaces with continuous-time innovation-diffusion physics to forecast long-term product adoption and return on ad spend (ROAS).

Physics-Informed Marketing Mix Modeling (pimmm) is a Python library that unifies machine learning response surfaces with continuous-time innovation-diffusion physics to forecast lo...

35