Prisms AI is a no-code AI application building platform that supports connecting data sources and user input, combining models such as GPT-3, DALL·E, and Stable Diffusion to create and deploy applications.

ArcaneLand is an AI dungeon master game powered by ChatGPT, offering fantasy adventures and other optional modes, while adding RPG elements such as experience points, items, and quests, with support for customizable gameplay.

Vercel AI Playground is an online tool for testing and comparing AI language models. It supports parameter adjustment, text generation, and autocomplete, making it easy to quickly experience the performance of different models.

TypingMind is an enhanced client for ChatGPT, offering chat history search, folder management, a prompt library, and integration capabilities, and supports running in the browser using your own API key.

Infranodus is a research tool that combines text analysis, network visualization, and AI capabilities to organize text topics, discover conceptual relationships, identify information gaps, and assist with reading, writing, and research.

PROMPTMETHEUS is a no-code prompt engineering tool for combining, testing, and evaluating OpenAI prompts, supporting model comparison, result scoring, cost estimation, and data export.

Goatchat is an AI chat assistant platform that provides GPT-based conversation features, supports creating personalized chat assistants, and can be used together with capabilities such as web browsing, interest-based chatting, and AI art generation.

Relevance AI is a platform for building and deploying AI workflows, supporting capabilities such as LLMs, GPT, API requests, and agents, and providing a dashboard for management and access.

Prompt Space is an AI prompt marketplace that allows users to sell and buy prompts. The website provides a platform for creating interactive experiences for customers, students, or employees. The site also offers a step-by-step guide to creating products and provides prompts for sale in different categories, including ChatGPT prompts. A video is also available on YouTube demonstrating how to create interactive experiences on the platform.

OpinioAI is an AI-powered research platform that can help researchers find insights, data, and opinions in a scalable way. They use language models instead of traditional survey and polling methods. They also offer a tool to build an AI version of a buyer persona. DeepOpinion is another AI automation tool that can be used to create custom models for intelligent text and document processing.

PromptStacks is a prompt resource library for large language models such as ChatGPT, offering a curated selection of free prompts along with community features that make it easy for users to browse, submit, and discuss prompt usage.

HotBot is a Google Chrome extension with VPN support that can help users search the web more quickly.

PromptPal is a Windows tabbed command console that supports using various consoles within the same application. It features persistent command-line history and favorites, can run tabs as administrator, and includes functions such as always-on-top, printing, and saving text to files. In addition, there is a YouTube video introducing PromptPal and discussing how it revolutionizes writing and work.

Pirate Diffusion is a community service for AI image creation, offering free generation tools and combining the Graydient AI Cloud chatbot with preinstalled models and LoRA resources to make multi-style image creation more convenient.

Spellbook is an AI tool for legal contract drafting that can be used directly in Microsoft Word, helping users review contract content and provide clause language suggestions to improve drafting efficiency.

Magick is a low-code development tool for integrating artificial intelligence capabilities into applications, helping developers and beginners build AI applications more conveniently and lowering the barriers to getting started and deployment.

Kraftful is an AI user feedback analysis tool for product teams. With the help of GPT-3, it helps companies organize user needs, track changes in product perception, and uncover market insights from user feedback on competing products.

Papers GPT is an AI tool for reading and analyzing research papers. It can feed scientific paper content into GPT to help users gain more targeted understanding, interpretation, and knowledge extraction around papers.

Sagify is a command-line tool for AWS SageMaker that helps users more conveniently train, optimize, and deploy machine learning and deep learning models.

PromptPerfect is a prompt optimization tool that helps users design, rewrite, optimize, and deploy prompts. It supports a variety of mainstream text and image models, and also provides batch processing and API integration capabilities.

Run open-source machine learning models online

Winston AI is a professional AI content detection tool that can identify text generated by language models such as ChatGPT and GPT-4 with 99.98% accuracy. It supports multilingual detection and can identify rewritten and human-edited AI content.

AI real-time voice changing tool

Cohere is a platform that provides large language models, helping developers and enterprises build high-performance AI products. The platform mainly offers AI-powered search text services (multilingual embeddings, neural search, search ranking), text classification, and text generation, helping enterprises quickly deploy conversational AI chatbots, generative search engines, text summarization, and enhanced vector retrieval.

Prompt Engineering Guide is a project initiated by DAIR.AI, aimed at helping R&D and industry professionals understand prompt engineering. With the goal of disseminating AI technologies and research outcomes, DAIR.AI envisions empowering the next generation of innovators in the AI field. The project has received more than 30,000 stars on GitHub and includes the latest papers, study guides, lectures, reference materials, and tools related to LLM prompt engineering.

Label Studio is an open-source data labeling platform launched by Human Signal (formerly Heartext). The project has nearly 14,000 stars on GitHub and can help developers fine-tune large language models, prepare training data, or validate AI models.

MMLU, short for Massive Multitask Language Understanding, is an evaluation of language understanding capabilities for large models. It is currently one of the most well-known semantic understanding benchmarks for large models, introduced in September 2020 by researchers at UC Berkeley.

FlagEval (Tiancheng) is a scientific, fair, and open large model evaluation system and open platform launched by the Beijing Academy of Artificial Intelligence (BAAI), providing researchers with tools and methods to comprehensively evaluate the performance of foundation models and training algorithms. FlagEval adopts a three-dimensional evaluation framework of "Capability-Task-Metric" to assess the cognitive abilities of large models from multiple dimensions, covering various application scenarios such as dialogue, question answering, and sentiment analysis, and providing more than 22 datasets and 80,000 evaluation questions.

H2O EvalGPT is an open tool from H2O.ai for evaluating and comparing large language models (LLMs). It provides a platform to understand model performance across a large number of tasks and benchmarks. Whether you want to use large models to automate workflows or tasks, H2O EvalGPT offers detailed rankings of popular, open-source, high-performance large models to help you choose the most effective model for specific tasks in your project.

LLMEval is a large model evaluation benchmark launched by the Fudan University NLP Laboratory. The latest LLMEval-3 focuses on professional knowledge capability evaluation, covering the 13 disciplinary categories designated by the Ministry of Education, including philosophy, economics, law, education, literature, history, science, engineering, agriculture, medicine, military science, management, and arts, as well as more than 50 secondary disciplines, with a total of about 200,000 standard generative question-answering items.

Flowith is an innovative canvas-based AI agent tool. Built on a pioneering node-based interaction method, it lets users interact with AI through multithreaded and divergent thinking. Powered by top-tier large models, Flowith supports multiple advanced AI models (such as Grok4, GPT-5, Claude, etc.) as well as image and video multimodal models (Veo 3, Midjourney, SDXL). Flowith supports multiple modes including text writing, image generation, and video production, and enables automated task execution through the agent "Neo."

SiliconFlow is a generative AI computing infrastructure platform. SiliconFlow provides products including the SiliconLLM large model inference engine, the OneDiff high-performance text-to-image/video acceleration library, and the SiliconCloud model cloud service platform, reducing AI model deployment and inference costs while improving user experience.

AiPy is a free and open-source AI agent factory, a local version of Manus, built on large language models (LLMs) and Python capabilities. It supports local deployment to ensure data privacy and security. Through the "Python-Use" paradigm, AiPy gives AI "hands," enabling it to analyze local data, operate local applications, and execute complex tasks such as controlling phones, generating multi-voice speech, analyzing medical test reports, extracting speech from videos, and sending scheduled emails.