AI-assisted coding tools

SenseChat - AI Life Assistant for Chat, Q&A, and Creative Content

SenseChat is an AI life assistant developed by SenseTime, specializing in chat-based Q&A and content creation. It excels at summarizing financial news, interpreting policies, analyzing earnings reports, and assisting with copywriting, image generation, coding, and engaging conversations on various topics. From writing Xiaohongshu notes and generating PPT outlines to English conversation practice, programming help, poetry creation, children's book illustration, Emoji expression, and logo design, SenseChat offers diverse intelligent services to make life and work easier.

heyCLI - Your Copilot for Linux Commands

heyCLI is a natural language tool for Linux commands that lets you work in the terminal using plain English. Instead of memorizing complex syntax, simply describe what you want to do in everyday language, and heyCLI will generate and execute the appropriate commands. It acts as your copilot for file management, system administration, networking, and more. Ideal for beginners, DevOps engineers, developers, and anyone looking to boost terminal productivity. Supports common commands and piping, making the Linux command line as easy as chatting.

imgcook: An Intelligent Tool Turning Design Drafts into Code with One Click

imgcook is an intelligent tool that automatically generates front-end code from design drafts with one click. It supports various design formats such as Sketch, PSD, and images, intelligently recognizing layers, styles, and layouts to produce high-quality code (React, Vue, Mini Programs, etc.). No manual coding needed, significantly boosting development efficiency for designers and front-end developers.

Code Snippets AI - AI-Powered Code Snippet Library & Chat

Code Snippets AI is an open-source AI-powered code snippets library and contextual AI chat platform. It helps development teams efficiently manage code snippets, build new features, fix bugs, add comments, and understand codebases through rich AI conversations. Features include user management, AI model usage tracking, and AI context generation, enabling teams to focus on what truly matters.

MarsX: AI-Powered Coding Platform Combining AI, NoCode, Code and MicroApps

MarsX is an AI-powered development platform that unites AI, NoCode, code, and MicroApps, enabling developers to build SaaS tools in days. It leverages AI for intelligent coding assistance, supports multiple development paradigms, and provides a rich marketplace of reusable MicroApps to accelerate development. Whether you are a professional developer or a NoCode enthusiast, MarsX helps you go from idea to fully functional product in record time.

Fitten Code - AI-Powered Code Generation and Completion Tool

Fitten Code is an AI-powered intelligent code generation and completion tool that supports multiple programming languages and major IDEs, helping developers quickly write, complete, and optimize code to boost productivity.

Qodo AI Code Review and Governance Platform

Qodo is an AI-driven code review and governance platform that helps engineering teams standardize code quality and review processes at the speed AI writes code. It offers 15+ agentic workflows for IDEs, PRs, and security reviews, detecting critical issues, logic gaps, enforcing standards, and providing context-aware suggestions to accelerate reviews and improve code quality.

Fronty - AI-Powered Image to HTML CSS Code Converter

Fronty is an AI-powered tool that converts images into clean, responsive HTML and CSS code. Simply upload a design or screenshot, and the AI automatically generates production-ready frontend code, saving developers and designers hours of manual coding work.

Codiga: Real-Time Static Code Analysis & Autofix

Codiga is a real-time static code analysis tool that works across VS Code, JetBrains, Visual Studio, GitHub, GitLab, and Bitbucket. It offers customizable analysis rules, security analysis (covering OWASP 10, MITRE CWE, SANS/CWE Top 25), autofix for vulnerabilities and coding issues, code snippet management, and automated code reviews. Users can create their own analysis rules in under 5 minutes and share them within teams. Codiga supports 12+ languages and 1800+ rules, helping teams improve code quality and security.

Tabby - Open-source, self-hosted AI coding assistant with code completion and chat

Tabby is an open-source, self-hosted AI coding assistant designed to bring the power of AI to your development workflow while keeping you in control. Whether coding in the cloud or on-premises, Tabby offers a flexible, transparent, and highly configurable alternative to proprietary solutions. It features cutting-edge AI capabilities for code completion, answering queries, inline chat, and more, easily integrates with existing infrastructure including Cloud IDEs, supports consumer-grade GPUs, and requires no external DBMS or cloud services, ensuring software supply chain safety.

AskCodi - AI Coding Assistant, Multi-Model Chat & Developer Tools

AskCodi is an AI coding assistant for developers, offering multi-model AI chat, code generation, refactoring, and custom agents. It supports OpenAI-compatible API, IDE integrations, and developer-first workflows to help developers build faster.

CodeGeeX - AI-Powered Coding Assistant for Code Generation and Translation

CodeGeeX is an AI-based coding assistant powered by a 13-billion-parameter multilingual code generation model. It supports over 20 programming languages and offers features like automatic code generation, code translation, and comment generation, helping developers boost productivity in various coding tasks.

Soloist - Free AI Website Builder for Business Launch

Soloist is a free AI-powered website builder designed for small businesses and entrepreneurs. With just a few simple inputs, it automatically creates a beautiful, mobile-friendly website. Features include automatic SEO keyword insertion for better search visibility, importing reviews from social media, calendar integration for online booking, Google Analytics support, and free custom domain connection. No coding required, ideal for accountants, barbershops, cafes, clinics, restaurants and more to quickly establish an online presence.

AirOps: Growth Platform for AI Search & AEO - Optimize for Google, Gemini, Perplexity, Claude, ChatGPT

AirOps is a growth platform purpose-built for AI search and AEO (AI Engine Optimization). It helps brands increase visibility, click-through rates, and conversions across major AI search engines including Google, Gemini, Perplexity, Claude, and ChatGPT. The platform offers visibility dashboards, competitor intelligence, AI citation tracking, content strategy development, and execution tools, enabling users to prioritize key actions, produce high-quality content at scale, and continuously optimize based on data. Leading brands like Webflow, Chime, Ramp, and Carta have achieved significant results, including a 6% increase in AI-attributed signups, 5x faster content refresh velocity, and up to 79% higher conversion rates on longtail pages.

Hocoos AI Website Builder - Create Your Website in 5 Minutes

Hocoos AI Website Builder is an AI-powered online tool that enables users to create professional, credible business websites in under 5 minutes without any coding or design skills. It provides comprehensive sales and marketing tools to help small businesses quickly launch and grow their online presence. Trusted by over 500,000 small businesses worldwide, it offers a free trial with payment only if satisfied.

JiHu GitLab - Enterprise DevOps Platform for Software Development and Operations

JiHu GitLab is the official distribution of GitLab in China, based on open-source GitLab EE, providing a secure, stable, and compliant enterprise DevOps platform for Chinese enterprises. It integrates project management, code hosting, CI/CD, security scanning, container registry, and more, supporting full lifecycle management from requirements to deployment, helping teams accelerate software delivery and improve R&D efficiency.

TRAE Work: Your Professional AI Work Assistant

TRAE Work is a professional AI work assistant designed to help users complete tasks more efficiently. It integrates intelligent writing, document processing, information retrieval, and other features, supporting AI assistance in various scenarios to streamline workflows. It also offers TRAE IDE, a 10x AI coding engineer tool, and TRAE Work Web version to meet diverse user needs.

Devin Desktop: Unified Command Center for Local and Cloud AI Agents

Devin Desktop is a powerful AI agent management platform that lets users dispatch and monitor fleets of local and cloud agents from a single command center. By partnering with Cognition, it enables engineers to plan, delegate, review, and ship within one shared workspace, preserving context and boosting productivity across tasks.

Tabnine AI Code Completion Assistant - Intelligent Code Generation and Autocomplete Tool

Tabnine is an AI-powered code completion tool that supports multiple programming languages and IDE integrations. It uses deep learning models to provide intelligent code suggestions based on context, helping developers write code faster. Tabnine offers free and paid versions, with paid plans supporting longer context understanding and team collaboration features.

Sourcegraph: Code Intelligence Platform for Code Search, AI Assistant & Batch Changes

Sourcegraph is a Code Intelligence platform that deeply understands your code, no matter how large or where it's hosted. It powers modern developer experiences with Code Search across all branches and code hosts, Deep Search for natural language queries answered by an AI agent, Code Intelligence for navigation and references, Batch Changes for large-scale code modifications across repositories, and the Cody AI coding assistant to read, write, and understand your entire codebase faster.

Jam AI - Never Write Repro Steps Again, One-Click Bug Reports with AI Summary

Jam AI is a smart bug reporting tool designed for developers and QA teams. With a single click via its browser extension, it captures page anomalies, console logs, network requests, and system environment details, then uses AI to automatically generate clear, reproducible steps and summaries. No more manual repro steps—create professional bug reports with full context including backend logs and recording links, speeding up issue triage and resolution. Supports iOS and offers advanced features like developer utilities and system reports.

Augment Code: Agentic Software Development at Organizational Scale

Augment Code is an agentic software development platform designed for organizational scale, leveraging AI agents to boost engineering throughput by 2-3 times. It closes the gap between individual engineers and organizational efficiency, enabling smarter, faster development at scale.

Warp - The Agentic Development Environment

Warp is a modern, open-source AI terminal built for agentic development environments. It enables developers to run coding agents like Oz, Claude Code, Codex, and Gemini CLI with fine-grained control, either locally or in the cloud. Designed as the best interface for working with any coding agent, Warp offers AI-assisted command completion, collaborative editing, and a streamlined terminal experience. Free to download.

Junie AI Coding Agent by JetBrains

Junie is an AI coding agent by JetBrains that allows developers to delegate complex tasks to AI and focus on results. Integrated into JetBrains IDEs, it supports code generation, refactoring, debugging, and automated workflows to boost development productivity.

Tencent Cloud CodeBuddy - AI-Powered Smart Coding Assistant with Code Completion, Diagnosis, and Optimization

Tencent Cloud CodeBuddy is an AI-powered coding assistant based on the Hunyuan code large model, offering capabilities such as technical dialogue, code completion, code diagnosis, and optimization. It helps developers generate high-quality code, solve technical problems, and significantly improve coding efficiency. Supporting multiple programming languages and mainstream IDEs, it is the intelligent programming companion for developers in the AI era.

ClackyAI - No-Code Full-Stack AI App Builder for Production-Ready Products

ClackyAI is a no-code full-stack AI app builder that empowers non-technical users to turn ideas into production-ready applications. Simply describe your idea in plain English, and it automatically generates a complete frontend, backend, and database system with integrated payments, authentication, AI models, email, SMS, storage, background jobs, and more. From idea to deployment in minutes, with real-time preview, iteration, and launch capabilities. Ideal for building websites, internal tools, content apps, productivity tools, AI assistants, and more.

Firebase Studio - Full Stack AI Workspace

Firebase Studio is an entirely web-based workspace for full-stack application development, complete with the latest generative AI from Gemini, and full-fidelity app previews powered by cloud emulators. It accelerates the entire development lifecycle, allowing developers to build backends, frontends, and mobile apps from the browser in minutes. Supports importing repositories from GitHub, GitLab, Bitbucket, or local machine, and creating new apps via natural language, mockups, drawing tools, and templates. Features AI-assisted coding, debugging, testing, refactoring, and collaboration with shared workspaces. Includes Android emulators, web previews, and one-click deployment to Firebase App Hosting. Free during preview with 3 workspaces; Google Developer Program members get up to 30 workspaces.

Bolt AI Builder: Create Websites, Apps & Prototypes with Words

Bolt is an AI-powered online builder that lets you create websites, apps, and prototypes simply by describing them in words. It features powerful coding agents that automatically test, refactor, and iterate, reducing errors by up to 98%. Supports imports from Figma and GitHub, includes built-in databases, user authentication, SEO optimization, and hosting—empowering product managers and entrepreneurs to turn ideas into live products fast.

Doubao - AI Chat Assistant for Writing, Copywriting, Translation, and Programming

Doubao is an AI-powered conversational assistant developed by ByteDance, integrating the Seedance 2.0 video generation model for free use. It offers intelligent Q&A, writing, copywriting, translation, programming assistance, and more, helping you solve problems, spark inspiration, assist in creation, and chat about any topic of interest.

Genie - AI-Powered Creative Generation and Design Tool

Genie is an AI-powered creative generation tool that helps users quickly generate design concepts, images, and creative content. By using natural language descriptions, Genie transforms ideas into visual works, suitable for designers, marketers, and creative professionals. It streamlines the creative process, offering an efficient and intuitive AI-assisted design experience.

Replit Agent: AI-Powered App Builder That Turns Ideas into Apps, Designs, Slides & More from Plain Language

Replit Agent is an AI-powered creative development tool that transforms your plain language descriptions into fully functional apps, websites, mobile apps, designs, slides, data visualizations, and more. Unlike a chatbot that only answers questions, Agent takes action: it sets up your project, writes code, creates applications, checks its work, and fixes problems along the way. Describe what you want in everyday language — no coding or technical knowledge required. Agent handles everything from planning to deployment. Plan mode allows you to brainstorm, break down complex projects into ordered task lists, and refine before any code is written.

Devin Desktop: Unified Command Center for Managing Local and Cloud AI Agents

Devin Desktop is a powerful AI agent management platform that allows users to dispatch and monitor fleets of local and cloud agents from a single command center. It integrates planning, delegation, review, and shipping capabilities without leaving your editor. In partnership with Cognition, Devin Desktop brings the agents Ramp engineers already use into one shared workspace, making it easier to jump between tasks, preserve context, and get more done. Whether for individual developers or teams, this command center enables more efficient completion of complex tasks.

Huawei Cloud CodeArts Code Agent

Huawei Cloud CodeArts Code Agent is a pragmatic AI development expert that understands project requirements, masters coding principles, and leverages various tools. It enables developers to enter a coding autopilot mode, improving coding efficiency and quality. Features include natural language code generation, intelligent completion, project understanding, and resource management. A free trial version is available for one-click activation.

v0 by Vercel - Build Full-Stack Web Apps with AI

v0 by Vercel is a collaborative AI assistant that helps you design, iterate, and scale full-stack web applications. Simply describe your idea, and v0 generates code, UI components, and complete pages. Start with templates to create contact forms, image editors, mini games, finance calculators, and more. Built-in drag-and-drop file attachment support greatly enhances development efficiency.

JetBrains AI: Intelligent Coding Assistance, AI Solutions, and More

JetBrains AI is an integrated artificial intelligence solution and service by JetBrains, designed to boost developer productivity and accelerate innovation through intelligent coding assistance, AI-powered development tools, and deep software development ecosystem expertise. It is embedded within JetBrains IDEs, offering code completion, error detection, automated refactoring, and enterprise-level customization and deployment.

Replit Agent: AI-Powered App & Site Builder from Natural Language Prompts

Replit Agent is a revolutionary AI development tool that enables anyone to automatically generate fully working apps and websites from natural language prompts. No coding required—just describe your idea in a chat, and Agent acts like an on-demand team of software engineers to build, debug, and deploy your application. From business software, AI chatbots, games, online shops to health trackers and marketing tools, it quickly turns ideas into working prototypes. Supports screenshot upload for inspiration, with a rich community showcase, making it ideal for both technical and non-technical creators.

Cursor: AI Coding Agent for Supercharged Productivity

Cursor is an AI coding agent designed for developers, deeply integrated into the editor and CLI. It offers context-aware completions, semantic search, reinforcement learning-driven intelligent navigation, and multi-agent collaboration to help teams build high-quality software faster. It enables developers to focus on decisions while delegating coding tasks to AI.

C Knowledge - CSDN AI Search Engine for Developers, AI Q&A, Code Generation & File Analysis

C Knowledge is a leading AI product co-developed by CSDN and external partners, designed specifically for developers. It efficiently supports AI Q&A, AI conversation, file analysis, code generation, and various development-related queries, helping users significantly improve work and learning efficiency. Whether solving technical problems, assisting with code writing, or analyzing document content, C Knowledge provides intelligent and accurate responses, making it the preferred AI search engine for developers.

GitHub Copilot - AI Pair Programmer for Code Completion and Agent Workflows

GitHub Copilot is an AI pair programmer by GitHub that provides intelligent code completion, explanations, edit suggestions, and autonomous agent execution across VS Code, JetBrains, CLI, and more. It integrates leading LLMs (OpenAI Codex, Claude) and supports custom agents. The GitHub Copilot app enables unified multi-agent workflow management. Enterprise plans allow customized knowledge bases, behavior policies, and service connections, boosting developer productivity by 94% for companies like Grupo Boticário.

Tianrang Intelligent - Enterprise AI Decision Platform for Urban Governance and Business Intelligence

Tianrang Intelligent is an enterprise-level AI decision intelligence platform, offering end-to-end solutions from data collection and model training to intelligent decision-making. Core features include AI applications for city brain, financial risk control, and smart retail, supporting real-time data analysis, predictive modeling, and automated decision-making. Suitable for government, finance, retail and other industries, helping enterprises achieve intelligent transformation.

Miracle Vision - Professional AI Video Generation and Editing Platform for Fast Creative Content

Miracle Vision is an AI-powered video generation and editing tool designed for content creators, marketers, and video enthusiasts. It leverages advanced AI technology to quickly generate high-quality videos from text, images, or video footage, and offers intelligent editing, special effects, voice synthesis, and subtitle generation. Users can produce professional-grade video content in minutes without professional video editing skills. It is suitable for social media short videos, promotional videos, educational training videos, and more, greatly improving creative efficiency.

Evidently AI - Open-source ML model monitoring and data drift detection platform for production AI quality

Evidently AI is an open-source ML model monitoring and data quality evaluation platform focused on detecting model performance degradation, data drift, and concept drift in production. It supports various scenarios from tabular data to NLP and recommendation systems, offering visual dashboards, automated report generation, and real-time alerts. Helps data scientists and ML engineers quickly identify root causes of model decay, ensuring continuous reliability of AI systems.

AGPT - AI-Powered Code Generation and Collaborative Development Platform for Efficient Software Project Building

AGPT is an AI-powered code generation and collaborative development platform designed to help development teams quickly build, iterate, and deliver software projects. It integrates intelligent code completion, automated code generation, project template management, and team collaboration features, supporting multiple programming languages and frameworks. By describing requirements in natural language, AGPT can generate high-quality code snippets, functions, and even complete modules, significantly improving development efficiency. Suitable for agile development, prototyping, rapid iteration, and especially beneficial for small to medium-sized teams and individual developers.

Mobvoi Open Platform - One-stop AI Voice Interaction and NLP Services for Speech Recognition, Semantic Understanding and TTS

Mobvoi Open Platform is a one-stop AI capability platform launched by Mobvoi, offering a range of artificial intelligence services including speech recognition, semantic understanding, text-to-speech (TTS), and wake-up word customization. Designed for developers, enterprises, and partners, the platform supports rapid integration of intelligent voice interaction features, widely used in smart hardware, in-car systems, smart home, and customer service robots. With rich APIs and SDKs, it helps users lower the barrier to AI development and achieve efficient, stable voice interaction experiences.

AgentGPT - Autonomous AI Agent Creation Tool for Building and Deploying Custom AI Assistants

AgentGPT is a powerful autonomous AI agent creation tool that allows users to configure and deploy custom AI agents through a simple web interface. No programming experience is required; users only need to name the target AI agent and set goals. AgentGPT will automatically break down tasks, execute operations, and iterate optimizations until the goal is achieved. The tool supports a variety of use cases, such as workflow automation, content generation, data analysis, customer service, etc., making it suitable for individual developers, enterprises, and teams to quickly implement AI-driven automation solutions. Its core advantages include zero-code operation, autonomous task planning and execution, and scalable agent behavior.

Beijing Academy of Artificial Intelligence - Leading AI Research Institute in China, Driving Cutting-Edge AI Technology and Open-Source Ecosystem

The Beijing Academy of Artificial Intelligence (BAAI) is a leading AI research institute in China, focusing on cutting-edge AI technology development, open-source ecosystem building, and talent cultivation. Core features include: releasing world-leading AI large models (e.g., WuDao series), building open-source platforms (e.g., FlagOpen), hosting AI academic conferences (e.g., BAAI Conference), and promoting AI ethics and safety research. It serves researchers, developers, enterprises, and policymakers, providing comprehensive support from fundamental research to industrial application.

Coze - All-in-One AI Bot Development and Agent Building Platform with Custom Plugins and Knowledge Base

Coze is an all-in-one AI bot development platform launched by ByteDance, enabling users to quickly build, debug, and deploy intelligent agents without coding. It features a rich plugin marketplace, knowledge base management, workflow orchestration, and long-term memory capabilities. Bots can be published across multiple platforms (e.g., Feishu, WeChat, Web). Ideal for customer service bots, content generation assistants, educational tutoring, and office automation, significantly lowering the barrier to AI application development.

Gradio - Open Source Python Library for Quickly Building Machine Learning Model Demo Web Interfaces

Gradio is an open-source Python library designed for machine learning engineers and data scientists to quickly create interactive model demo web interfaces. Without front-end development experience, you can encapsulate a model into a web application with input controls (such as text boxes, image uploads, sliders, etc.) and output displays in just a few lines of code. It supports local operation and one-click deployment on platforms like Hugging Face Spaces, greatly accelerating model sharing, testing, and collaboration.

Jan - Open Source Offline AI Assistant Tool for Running LLMs Locally with Privacy Protection

Jan is a free and open-source AI assistant tool designed to run large language models locally on user devices without requiring internet connectivity. It supports multiple mainstream models (e.g., Llama, Mistral) and offers a clean, intuitive interface for easy model loading and management. Jan prioritizes privacy by processing all data entirely on-device, making it ideal for users concerned about data security. Suitable for personal learning, writing assistance, and lightweight development tasks, Jan delivers efficient and private AI experiences.

Cohere - Enterprise AI Platform for Building RAG and Intelligent Search Applications

Cohere is an enterprise-focused AI large language model platform that provides powerful natural language processing (NLP) capabilities, including text generation, semantic search, classification, and retrieval-augmented generation (RAG). Its key advantages include support for private deployment, data security and control, and optimized model accuracy and efficiency for enterprise use cases. It is widely used in intelligent customer service, knowledge base retrieval, document analysis, content generation, and more, helping enterprises quickly build LLM-based intelligent applications.

Chatbox AI - Cross-Platform AI Desktop Client Tool with Multi-Model Integration and Smart Chat

Chatbox AI is a cross-platform AI desktop client tool supporting Windows, macOS, and Linux. It integrates multiple mainstream AI models (such as GPT, Claude, Gemini, etc.), offering features like smart chat, code generation, text translation, and document analysis. Users can interact with AI through a clean interface, making it suitable for programming assistance, study research, daily office work, and more. The tool supports offline use to protect user privacy and provides custom API access for advanced users.

AnythingLLM – Full-stack AI applications and private knowledge bases, enabling you to build your own ChatGPT with any model.

AnythingLLM is a full-stack AI application that supports any commercial or open-source LLM. It features built-in RAG, AI agents, and no-code agent builders. It can run locally or be remotely hosted, intelligently converse with documentation, and requires no cumbersome setup. Supporting the MCP protocol, it offers Desktop and Docker deployment options, making it suitable for individuals and businesses to build private, fully functional AI assistants.

Cherry Studio – an all-in-one AI workstation, a desktop client that provides unified access to 300+ mainstream large-scale models.

Cherry Studio is a cross-platform AI desktop client that integrates over 300 mainstream models from OpenAI, Claude, Gemini, and other sources, as well as local Ollam models. It supports intelligent dialogue, autonomous agents, document processing, global search, and other functions, with local data storage for enhanced privacy and security. The community edition is completely free and open-source, supporting Windows, macOS, and Linux.

iFlytek AI University – iFlytek's official AI learning and training platform, providing one-stop coverage from model fine-tuning to application development.

iFlytek AI University is an AI professional learning and training platform under iFlytek's open platform. Leveraging iFlytek's technological expertise in NLP, intelligent speech, and other fields, it offers a full-chain course from beginner to advanced model fine-tuning and agent development. The platform is deeply integrated with iFlytek's MaaS tools, supporting zero-code model customization and deployment. Upon completion, students receive official certification and it serves as a core hub for offline developer communities in multiple cities across China.

GPT-4o—OpenAI's all-around multimodal flagship model, featuring real-time voice and video interaction, and freely available to all users.

GPT-4o (“o” stands for Omni) is OpenAI's next-generation flagship multimodal large model, released in May 2024. It enables real-time inference across text, audio, images, and video, with an audio response time as fast as 232 milliseconds, approaching human conversational reaction speed. It possesses groundbreaking capabilities such as emotion perception, real-time translation, and image generation. Its API is twice as fast as GPT-4 Turbo, costs only half the price, and is available to all free ChatGPT users.

ModelScope – China's largest and most active open-source AI model platform, boasting a "model-as-a-service" ecosystem with over 30 million developers.

ModelScope is a leading open-source AI model platform in China, initiated by Alibaba DAMO Academy in conjunction with the CCF Open Source Development Committee. Adhering to the "Model as a Service" (MaaS) concept, the community has gathered over 200,000 open-source models, 30 million developers, and over 500 contributing organizations. It provides end-to-end services from model experience, download, fine-tuning, training to deployment, covering LLM, multimodal, speech, and AIGC fields. As a core infrastructure for AI developers in China, it is promoting the democratization of AI technology through "open source."

Google PaLM 2—A next-generation AI language model with multilingual, strong reasoning, and coding capabilities.

PaLM 2 is Google's next-generation large language model, introduced at Google I/O 2023. It boasts enhanced multilingual capabilities (covering over 100 languages), logical reasoning and mathematical abilities, and code generation capabilities, offering four versions ranging from mobile-friendly Gecko to high-performance Unicorn. PaLM 2 has been integrated into over 25 Google products, including Bard, Google Workspace, Med-PaLM 2, and Sec-PaLM, serving as a core model driving Google's AI strategy.

Replicate – a cloud platform that allows you to run open-source AI models with just one line of code; thousands of models are ready to use immediately.

Replicate is a cloud platform that allows developers to run, fine-tune, and deploy open-source AI models through a simple API. It offers thousands of community-contributed models covering areas such as image generation, large language models, and audio/video processing. No infrastructure management is required, and billing is based on actual computing power used. New users receive a free $25 credit.

Google DeepMind Gemma – A lightweight, open-source, commercially viable next-generation AI model family

Gemma is an open-source AI model family built by Google DeepMind based on Gemini technology. It offers various parameter scales from 2B to 31B, supports multimodal understanding including text, images, and audio, and supports over 140 languages. It is licensed under the Apache 2.0 license and can be used commercially for free. Known for its lightweight and high performance, Gemma can run locally on consumer hardware and has been downloaded over 400 million times, making it a mainstream choice for developers building AI applications.

Meta AI Developer Platform – Llama Open Source Ecosystem and Muse Spark Programming Model: Reshaping the Paradigm of AI Application Development

The Meta AI Developer Platform is the core entry point for Meta's generative AI ecosystem. Through the open-source Llama model, the high-performance Muse Spark programming model, and the Meta Model API, it provides developers with end-to-end support, from model fine-tuning and application building to commercial deployment. Its core strategy is to evolve from "content-generating AI" to "task-execution AI Agents," aiming to make AI the infrastructure driving product efficiency and commercial transformation.

Hugging Face – the "GitHub" of AI, the world's largest open-source model and dataset collaboration platform.

Hugging Face is a leading global AI open-source community and model hosting platform, widely hailed as the "GitHub of machine learning." It provides core services such as model libraries, datasets, and Spaces application hosting, aggregating over 2.7 million models, 950,000 datasets, and 1.2 million AI applications. Through open-source tool libraries like Transformers, the platform significantly lowers the barrier to AI development, becoming an indispensable infrastructure for modern AI developers.

Tiangong AI — A platform featuring an agent model with a million-token context window and an intelligent canvas, enabling end-to-end delivery from demo to product.

Skywork is an AI agent platform under Kunlun Tech that integrates SkyClaw-v1.0 (an agent model supporting a million-token context window), the visual canvas Skywork Design, and Dynamic Workflows for parallel multi-agent scheduling. The platform covers the entire workflow—from research, design, and code generation to deployment—and the annual recurring revenue (ARR) from its AI-native business has surpassed $800 million.

H2O.ai – From a pioneer in open-source machine learning to a guardian of "sovereign AI," redefining enterprise-level intelligent agents with a converged architecture.

H2O.ai is a leading enterprise AI platform that integrates predictive and generative AI, focusing on AI deployments utilizing private, protected data. Its flagship products, h2oGPTe and H2O Super Agent, enable the creation of secure, autonomous agents in on-premises, VPC, and air-gapped environments. These agents consistently rank at the forefront of accuracy in authoritative benchmarks such as GAIA and FutureX. The company is trusted by more than half of the Fortune 500 and organizations within the world's most highly regulated industries.

PubMedQA—an "AI benchmark" specifically designed for biomedical question answering; only by comprehending research papers can an AI truly pass the "Medical Turing Test."

PubMedQA is the first question-answering dataset requiring reasoning over biomedical research texts; it was released in 2019 by institutions including the University of Pittsburgh. The task involves answering "Yes," "No," or "Maybe" questions based on PubMed abstracts. Comprising 1,000 expert-annotated samples and 211,000 artificially generated ones, the dataset aims to evaluate the ability of AI models to comprehend and reason about complex medical literature. It is widely used to benchmark the performance of large language models in the medical domain.

SuperCLUE—A benchmark for Chinese large models: from foundational capabilities to AI agents, a single test reveals who is "swimming naked."

SuperCLUE is a comprehensive evaluation benchmark for general-purpose Chinese large models, released by the CLUE team. It provides authoritative, multi-dimensional capability assessments and rankings for Chinese large models by regularly publishing monthly and semi-annual reports based on three key benchmarks—open-domain multi-turn dialogue, closed-domain objective questions, and anonymous head-to-head battles—as well as dimensions such as mathematical reasoning, code generation, and AI agents.

Midjourney Prompt Helper – From "Inspiration Desire" to "Prompt Master," this amazing tool doubles your AI drawing efficiency.

Midjourney Prompt Helper is a tool designed specifically for Midjourney users to create and manage prompts, and it has become a core feature of the PromptFolder ecosystem. It provides a visual interface that helps users build high-quality AI drawing prompts by selecting elements such as style, artist, lighting, and composition, significantly reducing the learning curve and improving creative efficiency. The tool is perfectly compatible with the latest Midjourney models and parameters, making it an essential productivity tool for digital artists, designers, and AI painting enthusiasts.

Generrated – DALL·E 2 and DALL·E 3: Cue Words and Inspiration

Generrated is a personal interest project and a library of prompts for DALL·E 2 and DALL·E 3. The website contains over 9,300 AI-generated images and publishes the full prompts for each image, aiming to provide a platform for AI drawing enthusiasts to reference, learn, and find inspiration.

AI Prompt Generator – A free tool for optimizing and generating prompts that supports multiple models including ChatGPT and Midjourney.

AI Prompt Generator is a free online tool that helps users generate and optimize prompts for mainstream AI models such as ChatGPT, Claude, Midjourney, and Stable Diffusion. It offers real-time generation, multi-model support, and optimization suggestions, aiming to improve the efficiency and output quality of AI interactions. An API service is planned for developer integration.

Public Prompts—a free and open-source repository of high-quality AI-generated prompts, a source of inspiration for Stable Diffusion gamers.

Public Prompts is a community-driven, free library of AI prompts, models, and embeddings designed for image generation tools like Stable Diffusion. The platform features carefully selected high-quality examples categorized by style, providing detailed parameter "recipes" to help users efficiently generate high-quality AI images. No registration is required; it's completely free.

AiShort—a universal suggestion dictionary for ChatGPT, DeepSeek, and Claude, allowing you to copy suggestions with a single click and instantly understand your needs.

AiShort is a curated library of AI prompts, providing high-quality, reusable prompt templates for mainstream AI models such as ChatGPT, DeepSeek, Claude, and Gemini. The content covers dozens of fields including writing, programming, translation, academic research, critical thinking training, and productivity tools, aiming to help users save time and improve the efficiency and quality of their AI interactions.

prompts.chat—a "free and open-source" AI-powered suggestion community—is reshaping sharing rules with its protocols and code.

prompts.chat is a free, open-source, and self-hosted AI-powered prompting word social platform. The community focuses on sharing and discovering high-quality prompts, covering content from various fields including code, image generation, and writing. The platform emphasizes data privacy and community-driven development, providing a decentralized communication space for AI creators and users.

Snack Prompt—a discovery platform that aggregates over 350,000 AI-generated suggestions and automated workflows—is now transforming into an "AI agent app store."

Snack Prompt is an AI-powered marketplace for suggestion and automation, offering a vast library of free and paid suggestions, with community ratings, categorized browsing, and search capabilities. The platform is expanding into a marketplace for AI agents and automated workflows, designed to help individuals and businesses easily discover and adopt AI solutions. It was acquired by Spectral Capital in 2025 to accelerate its commercialization.

Ginlix – an "AI construction team" tailored for Wall Street, enabling investment analysis to be continuously iterated like writing code.

Ginlix is ​​an AI-powered company specializing in financial investment research. Its flagship product, LangAlpha, is an open-source investment research framework. Employing a Programmatic Tool Call (PTC) architecture, it allows AI agents to process financial data by writing and executing code, with a persistent workspace that enables research to accumulate like a codebase. It supports built-in models and can be deployed privately. It is suitable for individuals and institutions looking to leverage AI for deep, verifiable investment decisions.

Flowith—a canvas-like creative space that liberates AI from chat windows, allowing you to complete all complex tasks with an infinite whiteboard.

Flowith is a canvas-based AI creation platform and agent system product that replaces traditional chat boxes with an infinite canvas. It features over 30 built-in models and offers innovative functionalities such as Neo Infinite Agents capable of performing tasks exceeding 1000 steps, a Knowledge Garden, and multi-agent collaboration. It has already secured tens of millions of dollars in funding. It is suitable for creators, researchers, and knowledge workers seeking deep creative work and automation of complex tasks.

Manus—a general AI agent integrated with Meta, compresses 20 hours of work into 1 hour.

Manus is the world's first general-purpose AI agent, developed by Butterfly Effect and now a product of Meta. Unlike chatbots that only provide answers, Manus can independently think, plan, and execute complex tasks in a cloud-based virtual computer, directly delivering complete deliverables such as PowerPoint presentations, websites, and research reports. With a user rating of 4.7, the app is ushering in an era of "autonomous driving" for knowledge work.

Genspark – An all-in-one AI workspace that puts tedious tasks on autopilot, chosen by over 20 million users.

Genspark is a versatile AI workspace that automates end-to-end tasks through Super Agent. It generates presentations, analyzes data, writes code, and makes phone calls without the need for prompt word engineering. The platform integrates over 30 top-tier models, including GPT, Claude, and Gemini, and provides suites for AI slideshows, AI spreadsheets, and AI developer tools. With over 20 million users and annualized revenue exceeding $100 million, it empowers knowledge workers to shift from "task processing" to "product creation."

Kortix – an AI operating system that puts your entire company into a single Git repository; open source, self-hosted, and entirely yours.

Kortix is ​​an open-source AI command center that treats company operations as a Git repository. By deploying autonomous AI agents (Suna), it connects to 3000+ tools, executes multi-step tasks in an isolated sandbox, and generates actual outputs such as reports and code. Self-hosting is supported, giving you complete control over data and configuration. It's ideal for developers and teams looking to build autonomous AI workflows with full ownership.

Mavis – By distributing my work to an AI team, the MiniMax Agent has finally grown a "brain".

Mavis is a major upgrade to MiniMax's AI Agent, positioned as "your AI butler." Through its Agent Team mechanism, it can break down complex tasks, execute them in parallel, and perform adversarial verification, collaborating like a real team. It supports local file operations, browser automation, and multi-platform collaboration (Web/IM), and can independently complete long tasks. It's ideal for professionals who want to completely delegate repetitive tasks to AI.

Skywork – bringing AI-powered smart workstations to the entire office, the "AI colleagues" that office workers dream of.

Skywork is an AI-powered smart workbench developed by Kunlun Tech, covering the generation of all modal content, including documents, PPTs, spreadsheets, web pages, and podcasts. It offers a local desktop version that allows direct reading of computer files for cross-format processing without requiring file uploads. It features over 100 built-in AI skills and supports seamless switching between multiple models such as Claude and Gemini. A free personal version is available, providing every working professional with a 24/7 online AI work partner.

Rabbit R1 – An AI hardware device that challenges the "App terminator," a small orange box that went from being ridiculed to gaining popularity.

The Rabbit R1 is an AI-native pocket assistant launched by Rabbit Inc. It features a Large Motion Model (LAM) and allows users to directly control apps and complete tasks via voice commands. Although it was controversial due to its incomplete functionality after its release in early 2024, its reputation has reversed after more than 35 OTA updates over two years and a rewrite of Rabbit OS 2. The company also plans to launch a more geeky Cyberdeck product.

Visual Studio—the world's most powerful IDE, fully AI-powered, making coding feel like having a top-notch team working for you.

Visual Studio is Microsoft's most popular integrated development environment (IDE) worldwide. The 2026 version is fully AI-enabled, deeply integrated with GitHub Copilot, and supports .NET 10, C# 14, and C++ 23/26. It offers features such as intelligent code completion, AI-assisted debugging, asynchronous cloud tasks, and personalized Fluent UI themes.

Amazon Q Developer, AI Programming Assistant, AWS CodeWhisperer, Proxy Coding

Baidu Comate is an intelligent programming assistant built by Baidu based on the Wenxin big data model. It supports 200+ programming languages ​​and covers the entire process of code generation, completion, interpretation, debugging, and unit testing. It offers two usage modes: IDE plugin and standalone Comate AI IDE. It pioneered the one-click design draft to code (F2C) function and is equipped with the multi-agent Zulu, which can autonomously break down complex tasks.

Amazon Q Developer—AWS's official AI programming assistant, doing the entire coding process for you, from writing code to deployment.

Amazon Q Developer is a generative AI programming assistant launched by AWS, an upgrade from AWS CodeWhisperer. It supports over 25 programming languages ​​and is deeply integrated with mainstream IDEs such as VS Code, JetBrains, and Eclipse, as well as command lines.

Toast – Tencent's AI app generator, allowing you to create your own app simply by speaking.

Toast is an AI application generation platform launched by Tencent in May 2026, positioned as an "exploratory atmosphere coding (Vibe Coding) product." Users only need to describe their ideas in natural language, and AI can automatically complete the entire process from function breakdown and interface design to APK packaging.

Alibaba's M6—the world's first 10 trillion-parameter multimodal large model—consumes only 1% of the energy of GPT-3.

M6 is a general-purpose multimodal large model developed by Alibaba DAMO Academy. In October 2021, it became the world's first AI pre-trained model with 10 trillion parameters. Based on the self-developed Whale distributed framework, it was trained in just 10 days using only 512 V100 GPUs, with energy consumption only 1% of GPT-3. It supports tasks such as image and text generation, visual question answering, and poetry creation, and has been deployed in more than 40 scenarios, including Tmall virtual anchors and Taobao search. It is the core predecessor of the Tongyi Thousand Questions large model.

StableLM—an open-source AI model from the same family as Stable Diffusion, capable of running with only 3B parameters and commercially viable.

StableLM is an open-source large language model series launched by Stability AI. It is trained on The Pile extended dataset, which contains 1.5 trillion tokens. It offers multiple parameter versions, including 1.6B, 3B, 7B, and 12B, and supports text generation and code writing. It is licensed under the CC BY-SA 4.0 open-source license, allowing free commercial use. Stable LM 2 12B outperforms Llama 2 70B in some benchmark tests. It is suitable for developers, researchers, and small and medium-sized enterprises for private deployment.

LLaMA—Meta's open-source AI model revolution, with performance comparable to GPT-4 and completely free for commercial use.

LLaMA is an open-source family of large language models launched by Meta, evolving from LLaMA 1 in February 2023 to multimodal LLaMA 4. The 70B parameter version boasts performance close to GPT-4, while the 405B version rivals GPT-4o. It is completely open-source and commercially viable. Enterprises can download and deploy it on their own servers without data sharing, meeting compliance requirements in industries such as finance and healthcare. With over 1.2 billion downloads globally, it is suitable for developers and enterprises requiring private deployment and deep customization.

Tencent's Hybrid Model: Starting from Pragmatism, Tencent's AI Remastered Intelligent Efficiency

Tencent Hybrid is an industrial level AI model independently developed by Tencent. After the reconstruction of pre training and reinforcement learning infrastructure in February 2026, it has been repositioned with "pragmatism" as its core. The Hy3 preview, released in April 2026, is a 295 billion

Codex: From code completion to cloud based intelligent agent command center

OpenAI Codex is an AI programming agent launched by OpenAI, with a cloud based software engineering agent as its core form, capable of independently completing the entire development process from requirement understanding to code delivery. After users describe the task objectives through natural

Wenxin Big Model: Baidu's Industry level Knowledge Enhancement Model that has been honed over the

ERNIE is an industry level knowledge enhancement model independently developed by Baidu. Starting from the release of version 1.0 in 2019, it has undergone multiple generations of technological iterations and has established a three-level system of basic model, task model, and industry model. The

AstronClaw: Cloud AI intelligent agent development platform and zero code security deployment

AstronClaw is a cloud based AI intelligent agent platform officially launched by iFlytek on March 12, 2026. It is built on the OpenClaw core architecture and focuses on security and usability. The product adopts a hybrid architecture of "cloud rapid deployment+local sandbox operation", supporting

Volcanic engine: the leader of enterprise level cloud and AI service platform and whole stack

Mountain Engine is an enterprise level technical service platform under ByteDance, which was officially launched in June 2020 and positioned as a window for opening up ByteDance's technical capabilities. The platform provides a complete cloud service matrix, including infrastructure services such

Atoms: DeepWisdom's Multi Agent AI Native Entrepreneurship Platform and "One Person Company"

Atoms is a multi-agent AI startup platform launched by Shenzhen AI company DeepWisdom (formerly known as MetaGPT team), formerly known as MetaGPT. Users do not need to write code, they only need to describe product ideas in natural language. The platform can dispatch an intelligent agent team

AGI Eval: A large model evaluation community and authoritative third-party evaluation platform

AGI Eval is a large model evaluation community jointly created by top universities and institutions such as Shanghai Jiao Tong University, Tongji University, East China Normal University, and DataWhale, with the mission of "assisting evaluation and making AI a better partner for humanity". The

OpenCompass: An Open Source Large Model Comprehensive Evaluation System and Sinan Open Platform

OpenCompass is an open-source large model evaluation system launched by Shanghai Artificial Intelligence Laboratory, providing one-stop evaluation services for large language models, multimodal models, and scientific intelligence models. The platform supports one click distributed evaluation of

FlagEval: The internationally authoritative large model evaluation system and Libra open platform

FlagEval (Libra) is a large-scale model evaluation system and open platform initiated by Beijing Zhiyuan Artificial Intelligence Research Institute, aiming to establish scientific, fair, and open evaluation benchmarks and methods. The platform has innovatively constructed a three-dimensional

MMLU: The International Authoritative Benchmark for Multi Task Language Understanding Ability of

MMLU (Massive Multitask Language Understanding) is a large-scale multi task language understanding evaluation dataset jointly released by the University of California, Berkeley and other institutions. It covers 57 disciplinary fields, including humanities, social sciences, natural sciences,

HELM: Stanford University led comprehensive evaluation framework for large language models and high

HELM (Holistic Evaluation of Language Models) is a comprehensive language model evaluation framework initiated by the Stanford University Center for Fundamental Model Research (CRFM), aimed at systematically evaluating large language models through multidimensional, standardized, and reproducible

CMMLU: Authoritative Chinese Language Model Knowledge Understanding Ability Evaluation Benchmark

CMMLU (Chinese Massive Multitask Language Understanding) is a large-scale language understanding benchmark designed specifically for the Chinese language context, covering 67 subject topics from beginner to advanced professional levels, including natural sciences, social sciences, engineering

Tip Engineering Guide: A Systematic Learning Roadmap from Zero Foundation to AI Dialogue Master

The Tip Engineering Guide is the world's most popular open-source tip engineering learning project initiated by the renowned AI research institution DAIR.AI. It has accumulated over 30000 stars on GitHub and covers the entire knowledge system from basic principles to advanced technologies. The

PromptHero: The world's leading AI painting prompt word search engine and millions of level prompt

PromptHero is the world's top ranked AI prompt search engine, supporting the search of millions of AI art image prompt words generated by mainstream models such as Stable Diffusion, Midjourney, FLUX, Ideogram, DALL-E, Sora, etc. The platform provides classification search by model, style, and

AIPRM: The preferred prompt word management tool and community driven prompt word library for

AIPRM is a browser extension and prompt management tool for mainstream AI platforms such as ChatGPT, Claude, Gemini, Midjourney, etc. It provides over 5400 community approved ready to use prompt words. It supports guided creation of prompt words, multivariable settings, customization of tone and

PromptPilot: A professional prompt optimization and automation tuning platform for AI instruction

PromptPilot is a systematic prompt word engineering platform launched by Volcano Engine, aimed at addressing the pain point of "how to efficiently ask AI questions". It provides full lifecycle management covering Prompt generation, debugging, evaluation, and iteration, supports one click rewriting

AI Prompt Genius, ChatGPT prompt word management and dialogue export tool: Keep your AI

AI Prompt Genius is an open-source browser extension tool designed specifically for ChatGPT users. Its core functions include: automatically saving ChatGPT conversation history, importing/exporting prompt word templates, one click exporting conversations to PDF/image/Macrodown/JSON formats, local

LangGPT - Structured Prompt Word Design Framework: Natural Language Programming for Large Language

LangGPT is a structured prompt word design framework inspired by programming languages, aimed at solving the problem of non AI experts having difficulty writing high-quality prompt words. Drawing on the design ideas of object-oriented programming languages, LangGPT proposed a dual layer structure

OpenAI Operator， The world's first CUA intelligent agent, an AI assistant that simulates human

Operator is OpenAI's first AI agent product released on January 23, 2025. Unlike ChatGPT, which only outputs text, Operators can operate browsers autonomously like humans - they can view screenshots, move the mouse, click buttons, input text, and automatically complete complex tasks such as booking

AutoGLM Reflection - Zhipu AI's First Free Intelligent Agent: Deep Research+Automated Web Operations

AutoGLM Contemplation is an autonomous intelligent agent (AI Agent) product launched by Zhipu AI on March 31, 2025. It is also the first domestically produced agent that integrates deep research and web operator capabilities.

Fairies Universal AI Agent: Local File Operations+Cross Application Automation Execution of

Fairies is a general-purpose AI agent developed by the Fundamental Research Laboratory founded by Robert Yang, an alumnus of Peking University. Unlike traditional AI chatbots, Fairies can truly "hands-on" operate computers - performing over 1000 operations, covering scenarios such as file

Fellou, The world's first Agentic AI browser: Multi agent collaborative execution of complex tasks

Fellou is the world's first Agentic AI browser, which was created by the post-95 team founded by Xie Yang, the former technical director of ByteDance. Unlike traditional browsers, Fellou is not a passive information display tool, but an "action oriented browser" capable of thinking, planning, and

Atoms AI， New generation AI native entrepreneurship platform, multi-agent collaboration from

Atoms is an AI native application development and entrepreneurship platform launched by DeepWisdom, positioned as "directing a complete development team to transform ideas into actionable full stack commercial applications using natural language. Unlike traditional AI programming tools, Atoms' core

Deep Intelligent Connection, an AI native platform for the real estate vertical field under E-house

DeepLink is an AI native application and digital employee platform under E-House China, focusing on the real estate vertical field. It was established in 2025. The company has built an exclusive AI solution for the real estate industry covering the entire chain of land, development, trading, and