最新推荐

Revolutionizing hiring with AI-driven voice interviews that adapt to candidate responses and provide deep insights.
FoloUp is an open-source AI-powered platform for conducting voice-based hiring interviews, enabling personalized, conversational interactions with candidates and providing detailed performance insights.
AI文字
更多内容AI工具
更多内容
Revolutionizing hiring with AI-driven voice interviews that adapt to candidate responses and provide deep insights.
FoloUp is an open-source AI-powered platform for conducting voice-based hiring interviews, enabling personalized, conversational interactions with candidates and providing detailed performance insights.

OmniParser v2.0 turns UI screenshots into actionable, structured data for enhanced AI-driven user agents.
OmniParser v2.0 is an advanced UI screenshot parsing tool that converts unstructured screenshots into structured data, enhancing LLM-based UI agents. It includes an improved dataset and powerful model optimizations.
MCP Servers
更多内容
Enhance Claude AI's interaction with persistent memory, leveraging SQLite for efficient storage and knowledge retrieval.
A Python-based MCP server with SQLite backend to store persistent memory for Claude AI using a local knowledge graph. It allows for entity-based memory retention across chats, facilitating more personalized interactions.
AI教程
更多内容
High-quality datasets and tools for LLM fine-tuning across various domains including code, math, and instruction following.
A collection of high-quality datasets, tools, and concepts for fine-tuning large language models (LLMs), including data for math, code, instruction following, and preference alignment.
AI绘画
更多内容
Transform ideas into stunning visuals and gain insights with Janus Pro’s advanced AI image generation and comprehension tools.
Janus Pro is a powerful AI-driven platform offering advanced image generation and visual understanding capabilities, backed by DeepSeek technology. Ideal for developers and researchers.

Luma Ray2 harnesses AI to create photorealistic visuals and dynamic motion for a variety of creative projects.
Luma Ray2 is a cutting-edge AI tool designed to generate high-quality visual content with stunning realism and natural motion. Its advanced physics simulation and ability to follow detailed instructions make it ideal for cinematic scenes, surrealism, and world exploration.

CreatiLayout utilizes a Siamese transformer model to generate high-quality, controllable layouts from images and text.
CreatiLayout introduces a novel Siamese multimodal diffusion transformer for high-quality, controllable layout-to-image generation, leveraging layout and text guidance for precise rendering of complex attributes.
AI插件
更多内容
Effortlessly manage your Google Calendar events with Claude Desktop and natural language processing.
This server enables seamless integration with Google Calendar for AI assistants in Claude Desktop, allowing natural language interaction to manage calendar events. It supports auto authentication, event creation, updating, deletion, and more.
AI音乐
更多内容
Create high-quality, royalty-free songs effortlessly with AI Song Maker, your go-to music creation tool.
AI Song Maker is an innovative tool that allows users to effortlessly create royalty-free songs, including instrumental tracks, custom lyrics, and more. Generate high-quality music quickly with this AI-powered music maker.

Efficient and fast text-to-speech solution with Kokoro model and ONNX runtime.
kokoro-onnx is a lightweight Text-to-Speech (TTS) system based on the Kokoro model and ONNX runtime, offering fast, high-quality speech synthesis with multiple voices and languages. It’s optimized for macOS M1 devices and provides easy setup.
GPTs
更多内容
ChatGPT Gov is a specialized AI tool for U.S. government agencies, improving security and service delivery with advanced AI models.
ChatGPT Gov is a tailored version of OpenAI's ChatGPT, designed to enhance efficiency and security in U.S. government operations. It allows agencies to deploy AI models within secure cloud environments while meeting compliance and privacy needs.
数字人
更多内容
OmniHuman-1 enables the creation of highly realistic human animations from minimal inputs like a single image and audio.
OmniHuman-1 is an end-to-end multimodality-conditioned human video generation framework that generates highly realistic human videos from a single image and motion signals, such as audio and video. It uses a mixed training strategy for improved data scalability and outperforms existing methods, offering exceptional realism even from weak signal inputs like audio.