New Generation

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.

A general-purpose AI image generation framework that supports Hugging Face, Gitee, Model Scope, and more.

CircleToSearch with multi search engine support for all android

[🚀 ICLR 2026 Oral] NextStep-1: SOTA Autogressive Image Generation with Continuous Tokens. A research project developed by the StepFun’s Multimodal Intelligence team.

支持平台:网易云，抖音，快手，小红书，汽水音乐，微博，bilibili，皮皮虾，皮皮搞笑等，支持短视频图集去水印

🧈 Smoothly transition one element into another with just a few lines of code.

Evidence-first local memory for AI agents with temporal versions, admission policies, citations, explainable recall, MCP, and audit tooling.

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

5G NR Attacks against Qualcomm and Mediatek smartphones. Fuzzer included⚡

DeOldify for Stable Diffusion WebUI：This is an extension for StableDiffusion's AUTOMATIC1111 web-ui that allows colorize of old photos and old video. It is based on deoldify.

Top iOS app subscription paywall and onboarding gallery with screenshots, videos, pricing models, patterns, and monetization signals.

See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views, and session-level usage insight.

Native-first Claude Code plugin for third-party models with silent Agent model injection and output styles.

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

A unified framework for easy fine-tuning in Flow-Matching models

Launch apps by casting spells! 🪄

Netcat with automated NAT traversal, secure P2P, and advanced features for shell access, file transfer, and network proxying.

The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"

You've reached your trial request limit. / Too many free trial accounts used on this machine. Please upgrade to pro. We have this limit in place to prevent abuse. Please let us know if you believe this is a mistake.

DiffuEraser is a diffusion model for video inpainting, which performs great content completeness and temporal consistency while maintaining acceptable efficiency.

Beginner-friendly AI conversation practice application

Genshin Impact & HKSR Fps Unlock 原神崩铁帧率解锁

用于抖音直播间福袋挂机

Software Internship Guide for Egyptian Undergraduates

Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

The utility-based animation framework for the web.

A zlib implementation in rust available as a C dynamic library and as a rust crate

PrimeVue Components Styled with Tailwind CSS