SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,721 results · Page 861 of 993

ShadowDancer

AI developer platforms

ShadowDancer is a project published by AlayaLab on GitHub, with the corresponding project homepage at https://shadowdancer-1.github.io/。根据仓库说明，该项目旨在让交互式视频世界模型具备“任意动作、帧级控制”的能力，其核心理念是“从一段视频及其影子中教会视频世界模型任意动作”。目前仓库处于代码发布阶段，代码和模型权重正在清理并接受内部审查，尚未正式发布。仓库中暂未提供具体的安装命令、使用步骤、功能细节或平台支持信息。

Read more

ShadowGit

AI coding

ShadowGit is a local tool that provides automatic code version management and AI memory capabilities. It captures every change to code and, through an MCP server, allows AI coding assistants such as Claude, Cursor, and Copilot to query code history. It is officially stated to run 100% locally and support instant recovery. Its core value lies in providing AI with code context memory, reducing repeated explanations and lowering debugging frequency, and through one-click recovery, preventing experimental modifications from destroying work results. It requires no configuration and can automatically connect with any AI tool.

Read more

shap-e

Other AI tools

Shap-E is the official code and model released by OpenAI for generating 3D objects conditioned on text or images, with the paper titled "Shap-E: Generating Conditional 3D Implicit Functions." The project provides example notebooks for text-to-3D and image-to-3D, as well as a demo for encoding a model back to rendering. Installation is via pip install -e . . When using image conditioning, it is recommended to first remove the background of the input image for the best results; encode_model.ipynb requires Blender 3.3.1 or higher to be installed and the environment variable BLENDER_PATH to be set to the path of the Blender executable.

Read more

ShareSpeak

AI productivity

ShareSpeak is an invisible AI teleprompter for Mac and Windows, designed for screen recording, conference calls, and video recording scenarios. It supports voice-activated scrolling, which can automatically advance the script according to the speaking rhythm, as well as manual speed control; it is completely invisible during screen sharing and recording. It offers script library management, real-time word count and estimated speaking duration, window size memory, opacity and color adjustments, keyboard shortcuts, and other customization options, and can optionally use Gemini, Whisper, or Apple speech recognition models, with support for fully offline local models. The Mac version can also reside in the notch area, close to the camera to maintain natural eye contact. It uses a one-time buyout payment, with no subscription, includes lifetime updates, each license supports floating switching between 2 devices, and offers a 21-day refund policy.

Read more