[CVPR 2026] Physical Simulator In-the-Loop Video Generation

AgentsMesh — AI Agent Fleet Command Center. Orchestrate Claude Code, Codex CLI, Gemini CLI, Aider and more from a single platform.

🌱 SeedWorld — Plant a world. Watch it grow. An emergent world simulation engine powered by LLM. 给LLM一个世界设定,看它自己长出文明

The best automatic workflow for create your own custom flashcards in Anki

🔳 哔哩哔哩扫码获取 cookie 网页工具

Your codebase was probably AI-generated. Get a better handle on it. Noodles creates interactive diagrams that visualize how your code actually works, so you can understand what the AI built without…

✨ 望图 PixelFree 美颜SDK - 全平台美颜特效引擎（iOS/Android/harmonyOS/windows/macOS/linux）| 直播/短视频/相机/照片处理 | 高性能+轻量级

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505

Record and Replay AI Agent Trajectories.

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of search-engine interactions to …

TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

Evalyn — a lightweight, local-first eval framework for your GenAI app

AI成片工作流Agent，这是一个面向创作者，高自由度的 AI 电影生成系统。 你只需输入一个剧本，系统即可自动完成剧本拆解、分镜生成、画面与音频素材生成、视频合成，并支持一键分发到媒体。 从灵感到成片，不再需要复杂流程，让个人也能创作电影级作品。

Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.

Kand: Blazing-Fast, Modern Technical Analysis in Rust, Python, and WASM.

A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

AI is changing the way how to launch cyberattack.

DroneDetour is a Java library and Android demo for UAV path planning and automatic detour navigation. It computes the shortest safe route around polygonal no-fly zones

[CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

A blueprint for building production-ready RAG systems that minimize hallucination, featuring switchable 3-step (Speed) and 4-step (Precision) pipelines.

A fast & stable & flexible ETL tool.

A Swift-based, offline password manager built on KeePassKit, featuring multi-layer encryption, biometric authentication, password generation, and a fully localized English–Chinese interface. 一款基于 S…

NEO Series: Native Vision-Language Models from First Principles

HunyuanVideo-1.5: A leading lightweight video generation model

[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny co…

Modular multi-agent orchestration framework powered by LangGraph and FastAPI.

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".