AI Code Generator

GitHub Copilot

GitHub's own AI coding assistant, covering editors, the terminal, the desktop app and github.com. It runs the workflow from issue to code generation, PR review and merge, with controls for switching between models and agents.

Cursor

AI-native coding agent that plans and executes multi-step changes in parallel, with multi-model support and cross-repo context. Available as desktop app and CLI.

Raccoon

SenseTime's AI coding assistant, with single-line and whole-block completion, code generation from comments, multi-turn chat, and unit test and deployment script generation. It plugs into VS Code and the JetBrains IDEs, and comes in a free tier and a private deployment.

Base44

A no-code AI platform that turns a description into a working app or site. Backend, storage, database, payments and hosting are all included, with no coding required, which suits founders and teams that want a full-stack product quickly.

OpenCode

OpenCode is an open-source AI programming agent that can write code in terminals, IDEs and desktop clients. It supports LSP, multi-session parallelism and 75+ models, and prioritizes privacy without storing code.

Kiro

Amazon has launched an AI integrated development environment, with specification-driven as the main line: writing prompts into executable specifications, verifying the correctness of code, using parallel agents to work in large code bases, and its official positioning is to move from assisting in writing code to agent engineering.

TraeCode

The AI programming IDE under ByteDance's TRAE offers, according to the company, a dual development mode of IDE and SOLO. It has a built-in Coding Agent that can take over tasks and schedule tools, and supports custom agents and MCP.

Windsurf

The original Windsurf AI editor has now been integrated into Cognition's Devin system. Its website directs to Devin Desktop, where multiple coding agents on local and cloud can be scheduled on a unified interface.

LM Studio

A desktop local AI application, now positioned as a Bionic agent for writing and programming, supports local model operation, document and code generation, and real-time speech transcription. The company states that cloud-based inference features zero data retention within the United States.

MindStudio

A platform for designing, building and deploying AI agents without writing any code, with over two hundred built-in models and numerous integrations. The company states that users can bring their own API keys, and it has recently launched a product agent that can directly generate complete applications from ideas.

MiMo Code

Xiaomi has launched a new generation of AI programming assistant that supports unlimited context and is ready to use out of the box. It provides free multimodal models and efficiently completes coding collaboration with the help of Agents and memory organization.

Unsloth

Open-source local AI workstation: download models and chat directly on the desktop, fine-tune models without writing code, locally generate and edit images and videos, and connect coding agents to your own GPU.

Kilo

Open-source AI coding agent, covering VS Code, JetBrains, CLI and cloud, supporting access to more than 500 models and zero markup for self-provided keys, and using local models can protect code privacy.

Codebuddy Code

The terminal form of Tencent Cloud's official intelligent coding tool uses the command line to complete project understanding, code generation and refactoring, as well as test and document generation. The company states that code analysis is prioritized locally, making it suitable for daily development, code review and learning exploration.

Tencent Cloud CodeBuddy

A code assistant launched by Tencent Cloud, it provides technical dialogue, code completion, diagnosis and optimization capabilities based on Hunyuan Code LLM. It now covers three forms: plug-ins, IDEs and CLIs, and supports generating code from design drafts and one-click deployment and launch.

T3 Code

T3 Code is an open-source control plane for coding agents that schedules multiple mainstream coding agents in a single interface. It comes with built-in subscriptions, enabling one-click commit, push and PR creation, and is available on both desktop and mobile platforms.

Context7

The document retrieval service launched by Upstash directly feeds the latest version-related library documents and code examples into the context of AI programming assistants. The company claims that it can reduce outdated writing and fictional APIs, and is compatible with a variety of mainstream programming tools.

Rosebud AI

You can create a playable game in plain language of description or by picking a template, without writing any code at all. The company provides built-in game hosting and sharing, along with asset tools for character, portrait, and 3D model generation, and also offers story creation and digital human product lines.

C Zhidao

A developer AI search product co-developed by CSDN and external partners, covering AI Q&A and dialogue, file analysis, and code generation. It also provides in-depth thinking and code analysis, and the site also includes entrances for homework, interviews, etc.

Zeabur

Zeabur is a deployment platform that positions itself as an AI DevOps engineer. The company says that AI writes code and Agents run infrastructure. It supports servers, domain names, emails and one-click deployment, and completes operation and maintenance through prompts.

Morph

A model inference service specially optimized for coding agents. A single interface compatible with the OpenAI specification can call multiple LLMs, and is also equipped with dedicated models for rapid code modification, code retrieval, context compression and behavior evaluation.

Amp

Coding agents and development environments for cutting-edge models run each task in an isolated runtime environment. The agents can continue working even after you close your laptop, and they support three usage methods: desktop, web, and command line.

Magic Patterns

Magic Patterns is a design tool that directly turns requirements into high-fidelity interfaces. It can read your components and design specifications, compare multiple schemes side by side on an infinite canvas, and then hand the selected version to the coding agent, making it suitable for product teams to create functional prototypes.

Conductor

The combined tool for running coding agents in a cloud isolated sandbox runs multiple tasks in parallel in independent micro-VMs. It can reuse your existing subscriptions and keys to drive mainstream command-line coding assistants and supports web and mobile terminals.

Clipy

Clipy is a screen recording tool for coding agents. Record a defect reproduction or interface feedback once. Humans watch the video, while Claude Code, Codex and Cursor read the summary, transcription, clicks and key frames. It starts for free, and viewers don't need to register.

CatDoes

CatDoes is an autonomous AI agent-based application builder. It can write code, run tests, and build packages, going from a single sentence to app stores and web pages, and allows exporting the complete codebase at any time. Best for independent founders.

Macroscope

An AI code review tool for R&D teams that checks the correctness, security, testing and regression risks of each change before merging, automatically generates PR descriptions and summarizes multi-repository changes, and also includes a cloud-based coding Agent.

Bito

The model routing and code context layer for coding agents, officially stated that existing tools can be connected by changing just one Base URL, routing each request to a more suitable model, and the official announced task cost reduction of about half in customer A/B tests.

Refact.ai

Open-source self-hostable AI coding agent that covers end-to-end task execution, in-IDE dialogue and real-time completion. It claims to support more than 25 programming languages and local deployment.

Momen

A no-code application building tool for founders who can't write code. Just describe your requirements, and it will generate databases, logic and pages. The company claims it supports millions of daily active users and one-click release. It can export React components and view searchable logs.

CodeGeeX

The intelligent programming assistant launched by Zhipu AI provides code generation and completion, comment generation, code translation and intelligent Q&A. It is compatible with mainstream IDEs such as VS Code and the JetBrains series. The model weights are open-source, and it is available for personal and enterprise private deployment scenarios.

Zof

Zof is an independent verification and control layer located between AI and production environments. After the changes generated by AI arrive, Zof first judges the possible scope of impact, then runs unit tests, security and compliance checks and leaves evidence, and finally decides to allow, block or transfer to manual approval through strategies. It covers scenarios such as output from coding agents, release review and audit forensics.

Qoder CN

The AI programming AI agent launched by Alibaba Cloud (formerly known as "Tongyi Lingma", officially renamed in May 2026) is said to provide capabilities such as intelligent code generation, intelligent R&D Q&A, multi-file modification, and programming AI agents, and supports free switching of various Chinese LLMs.

Feishu Technology has launched an AI programming assistant that provides code completion, intelligent Q&A, unit test generation, code optimization and comment generation. The company stated that it supports more than a dozen mainstream IDEs and programming languages.

CodeMate.ai

A private-focused AI programming assistant that provides in-editor coding agents, design-to-application conversion, automated PR reviews, and an AI terminal. The company emphasizes self-hosting and on-device architecture, ensuring code never leaves the local environment.

Coldtea

Coldtea is a governance layer for AI-generated code. It integrates change understanding, regression testing and production observation into the same workflow, helping teams assess impacts before release and automatically fix issues when they occur.

Antigma

Antigma is a terminal coding agent and agent runtime: a single command to install a single-file program, switch between cloud or local models in a session, built with Rust and with no external runtime dependencies.

MySpec

MySpec is a specification generation tool for coding agents: it first clarifies the scope, user flows and boundary conditions through structured interviews, then produces four specification documents for coding agents to follow, and supports export and interface integration.

Harden AIF

Harden AIF is the security layer for coding agents: according to its website, its local model makes judgments before the execution of supported AI agent tool calls, allowing, recording, desensitizing, correcting, or blocking dangerous actions, and retaining the local decision-making history.

Stenography

A tool that automatically generates documentation for code, providing VS Code extensions and APIs, automatically updating the entire library documentation on save, and attaching Stack Overflow and official document references to issues.

Maiya AI

A one-stop AI collaborative development platform for product and R&D teams, officially covering four stages: requirement prototyping, professional documentation, code development, and testing and delivery. It offers AI prototyping, AI documentation writing, AI code writing, and AI automated testing.

Fillo

Form infrastructure for developers, enabling coding agents to directly build forms into products, handling validation, uploads, responses, versions, and submissions, and supporting mainstream front-end frameworks such as React.

Tiden

An intent verification platform for coding agents, which is said to capture requirements into versionable specifications and require each change to be proven by tests to prevent requirement deviations caused by agents' self-verification.

Lispa

Lispa is the cloud control plane for coding agents. It integrates Claude Code, Codex, Grok and Gemini into a single workspace. After the agent tasks are built and tested in the cloud, the results are viewed and merged through a browser.