AI Code Assistant

GitHub Copilot

GitHub's official AI coding assistant spans editors, the terminal, desktop, and the GitHub website, supporting the full workflow from issues and code generation to PR review and merge, with multiple model and agent controls.

Gemini CLI

Google's open-source command-line AI agent brings model capabilities directly to the terminal. It features built-in search grounding, file and command operations, supports collaboration via standard extension protocols and code hosting platforms, and offers 1,000 free daily requests upon personal account login.

Claude Code

Anthropic's programming agent tool can read the entire codebase, directly modify files and run commands. It can take on the entire work of defect repair and cross-day migration. Terminals, editors, chat software and web pages are all its entry points.

Google AI Studio

Google's official AI development platform allows you to test the latest models such as Gemini online and get API keys with one click. The official claims it is the fastest path from prompt engineering to production, and it also provides official SDKs in multiple languages and a library of sample applications.

Lovable

A low-code AI platform that turns ideas into deployable full-stack applications using natural language. It covers conversational generation, hosting, payment integration, and security, enabling you to go from prototype to launch without extensive coding experience.

OpenRouter

An aggregation gateway that unifies various models into a single interface, with text, images, videos, and audio sharing a single channel, charged by token, and the interface compatible with mainstream writing methods. Suitable for teams that want to switch between multiple models for price comparison.

Raccoon

The AI code assistant launched by SenseTime supports single-line and full-segment completion, code generation from comments, multi-turn conversations, as well as unit test and deployment script generation. It is compatible with IDEs such as VS Code and the JetBrains series, and offers a free version and private deployment.

Google Antigravity

Google has launched an agent development platform that offers desktop, command-line, IDE extensions and SDK forms, enabling parallel management of multiple local agents; the personal version is free, with additional Pro and Ultra subscription tiers.

Base44

Base44 is a no-code AI development platform that turns ideas into functional applications and websites using natural language. It comes with built-in backends, storage, databases, payment processing and hosting, requiring no coding. It is ideal for entrepreneurs and teams to quickly build full-stack products.

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.

Replit

Replit is a cloud-based IDE and AI application building platform. In the browser, use Replit Agent to generate and deploy full-stack applications conversationally, with built-in authentication, databases, hosting, and integrations, suitable for going from prototype to production.

Mistral Code

Mistral's official agent programming tool covers terminals, IDEs, web pages and background tasks. It supports understanding the entire codebase, migrating legacy code to modern tech stacks, and the official says it can also be fine-tuned based on enterprise code.

Emergent

Emergent is an AI application building platform from YC S24. It uses natural language conversations to let multiple AI agents complete design, coding, testing and deployment, generating full-stack Web/mobile applications that you can own, and is suitable for quickly going from an idea to launch.

Junie

An AI programming agent developed by JetBrains, it can run in terminals, IDEs, GitHub and GitLab CI, supports built-in model keys and scheduling mode, and can remotely drive tasks.

Hermes Agent

Nous Research's open-source and self-hostable AI agent, officially available for free under the MIT license, supports persistent memory, automatic skill generation, multi-platform access, and isolated sandboxes. It can be downloaded for desktop or terminal installation.

Bolt.new

Bolt.new is an AI building tool for generating applications and websites through conversation. It automatically selects models and provides real-time previews. With built-in databases, authentication, hosting, and SEO features, it claims to handle large-scale projects while automatically testing and fixing errors. It is suitable for the rapid launch of products, startups, and marketing campaigns.

CodeBuddy

Tencent Cloud has launched an AI full-process intelligent programming tool, which the official says is available in three forms: IDE, editor plug-ins and CLI. Based on conversational large models such as Hunyuan, it covers demand analysis, design draft to code conversion, code completion and one-click deployment.

TraeCode

The AI programming IDE under ByteDance's TRAE offers, according to the official statement, 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.

Composio

A platform that provides tool access and authorization infrastructure for AI agents, officially claiming to connect over 1500 applications, retrieve tools on demand, host OAuth authorizations, and support CLI, MCP gateway, and sandbox execution.

Skills.sh

The AI agent skill directory launched by Vercel allows programming agents to install reusable skill packages with a single command. The official stated that the leaderboard is generated based on anonymous installation data, and it also provides security audit and skill package packaging functions.

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 official 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.

Zed

Zed is a high-performance multi-person code editor created by the authors of Atom and Tree-sitter. Written in Rust, it supports parallel editing with AI agents and in-line assistants, enables real-time collaboration for teams, and is ideal for developers who value speed and collaboration.

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.

CodeRabbit

CodeRabbit is an AI-first Pull Request review tool that provides line-by-line contextual suggestions before code merging, automatically sorts review priorities, and monitors security vulnerabilities, enabling teams to deliver more stable code faster.

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 official 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 Large Model. It now covers three forms: plug-ins, IDEs and CLIs, and supports generating code from design drafts and one-click deployment and launch.

Comate

Wenxin Kuaima Comate is a programming tool developed by Baidu based on the Wenxin large model. It supports code completion, unit testing, commenting and intelligent Q&A, provides multi-agent scheduling and multi-file editing, and can be integrated with IDEs such as VS Code and JetBrains.

Kane CLI

Kane CLI is a command-line testing tool for developers. You can describe test cases in natural language to execute them on browsers and mobile devices. Its official website states that it will provide pass/fail conclusions and shareable execution evidence. New users can get a free quota.

Warp

Products that started from terminals but have shifted to platforms abstract agents, models, computing power, and evaluations into "software factories" defined by usable code, covering the entire software delivery chain and providing a clear cost basis for each request.

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 official claims that it can reduce outdated writing and fictional APIs, and is compatible with a variety of mainstream programming tools.

Glide

Glide is an AI building tool for enterprise internal applications. The official claims that it can turn spreadsheets into trustworthy business applications and agents, allowing users to get started without development, and it is suitable for frontline personnel to build software by themselves.

Rosebud AI

You can create a playable game with just one sentence of description or by picking a template, without writing any code at all. The official 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.

Verdent AI

A development tool that can use multi-agent parallel promotion. You state the goal, and it breaks down tasks and writes a complete product, covering launch-ready modules such as login, storage, and payment. It provides desktop and editor plugins, and can also be driven by sending messages through chat software.

Atoms

An application building platform featuring an AI employee team, officially stated to have agents such as researchers, architects, product managers, engineers, SEO specialists and advertisers collaborate in a division of labor to turn ideas into launchable products, and it supports code export and GitHub synchronization.

tabnine

An enterprise-level AI code assistant focusing on code privacy and compliance, offering completion and agent capabilities. It can be deployed controllably in the enterprise's own environment through an enterprise context engine and has been acquired by Tricentis.

CodeBuddy IDE

Tencent Cloud's AI code editor for the overseas market, powered by self-developed large code models, provides code completion, error diagnosis, technical Q&A and performance optimization, covering the entire development process from design drafts to deployment verification.

Zite

Zite is a team-oriented AI business system construction tool that generates applications, workflows and databases in one sentence. Its official website states that the underlying layer is exportable data tables, it does not charge by seat, and it provides templates for sales, recruitment and other scenarios.

Browserbase

A platform that provides cloud browsers and sandbox runtime environments for AI agents. With a single prompt, you can initiate tasks and let them operate on web pages like humans. It is equipped with headless browsing, proxy login, and debugging and playback capabilities.

Continue

Open-source AI code assistant project, focusing on integrating any model for custom completion and conversation; the team has been acquired by Cursor, and the open-source code repository is still freely available for self-deployment and modification.

Gemini Code Assist

Google's AI coding assistant for teams and enterprises, available in Standard and Enterprise editions, offers conversational Q&A, code completion, code refactoring, and code conversion capabilities, and can assist with development tasks in agent mode in terminals and IDEs.

Marblism

Marblism offers a team of AI employees divided by job roles, taking over inboxes and schedules, social media content, SEO writing, lead generation and phone reception, and directly logging into your existing tools to start working, suitable for small teams with limited staff.

aider

An AI pair programming tool that runs in the terminal, automatically maps codebases, supports over 100 languages and multi-model access, directly commits every change to Git, and is fully traceable throughout the process.

Augment Code

Focusing on an organization-scale intelligent agent software development platform, the official core product is a continuous delivery system that links the entire process from requirements to launch, and is equipped with automated links such as code review, vulnerability repair, and incident response.

Jules

Google's asynchronous programming agent pulls the repository into a cloud virtual machine to work independently. It first provides a plan for you to confirm, then runs tests to verify the changes, and finally returns a reviewable merge request. It can be invoked via the command line or an API.

AgentMail

AgentMail is an infrastructure that provides dedicated email inboxes for AI agents. With a single API call, you can create an inbox, send and receive emails, manage conversation threads and attachments, and trigger workflows. It is suitable for lead follow-up, customer service replies, and multi-agent collaboration.

NxCode

NxCode is an AI application builder for non-technical founders. You can describe your ideas in English to complete the development, testing and deployment. Its official website states that it starts at a minimum of five US dollars and no credit card is required. Thousands of founders have already used it.

MonkeyCode

Online AI programming platform, officially available for free use with unlimited quota. It comes with a cloud development environment and terminal, file management, and port preview, and links projects, requirements, and Git Review in the same workflow.

Dyad

A free and open-source desktop AI application builder. You can generate a fully functional full-stack project that can be run directly by describing your ideas. The code is entirely stored on your local machine and can be exported freely. It supports connecting to multiple model providers on your own and also supports local models.

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.

CodeGPT

CodeGPT is an AI programming agent embedded in mainstream development environments. It supports integrating multiple models with its own API Key. It first reads the code, provides modifiable solutions, and then takes action, making it suitable for teams that value data controllability.

Qodo

An AI platform for code review provides cross-repository context and more than 15 agent workflows, covers IDE, PR and security scenarios, and transforms team specifications into executable governance rules.

Cody

AI coding assistants launched by code intelligence vendors can leverage code search capabilities to retrieve symbols and usages from local and remote repositories as context, provide conversational Q&A, code completion and rewriting, and support mainstream editors and command lines.

Huawei Cloud Code Channel

Huawei Cloud has launched an enterprise-grade code intelligent agent, focusing on Agent team collaboration, specification-driven development and large-scale code repository understanding. It supports HarmonyOS-specific models and command-line terminal access, and is targeted at the entire team R&D process and security and compliance scenarios.

Glif

Glif is an AI creative agent integrating images, videos and audios. According to the official statement, it can call all creative tools with one prompt, complete tasks across models, no need to switch applications or write prompts, and is suitable for materials with a unified tone.

Vibecode App

Vibecode is an AI application generator for non-developers. Just describe your idea in one sentence, and you can get a publishable mobile and web application. It comes with a large number of customizable templates and supports continued development on mobile devices, making it ideal for quickly validating product ideas.

marimo

Open-source responsive notebook: changing code in one cell automatically recalculates relevant cells. Files are saved as pure Python, enabling version control. It can also be run as a script or deployed as a web application, making it ideal for data analysis and teaching demonstrations.

PaddlePaddle

PaddlePaddle is an open-source deep learning platform developed by Baidu. Originating from industrial practices, it supports dynamic graphs and static graphs, provides large-scale parallel training and unified inference capabilities, and serves developers from beginners to industrial practitioners.

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. The official website says it starts for free, and viewers don't need to register.

Crush

A terminal AI coding tool by Charm, which connects your tools, code and workflows to the large model of your choice, and is officially available on macOS, Linux, Windows and BSD.

Palmier

Palmier Pro is a video editor built for AI. Officially, it claims to use Claude or Codex for automatic clipping, generate materials on the timeline, and then export them to professional editing software for further refinement, making it suitable for agency workflows.

CopilotKit

Embed the agent into the front-end framework of the product interface, providing dialogue components, generative interfaces and in-app operations, which can connect to multiple agent backends, and is suitable for adding AI assistants to existing products while retaining permissions and audits.

MindSpore

Huawei's open-source self-developed full-scenario AI framework supports training and inference on edge, end, and cloud devices. It provides automatic differentiation, distributed parallelism, and a rich set of toolkits, targeting algorithm engineers and data scientists, and covers the entire process from training to deployment.

Manifest

Open-source LLM router and gateway that uses a single OpenAI-compatible endpoint to access subscription-based, pay-as-you-go, local models and custom providers, automatically fixes erroneous requests, and switches to backup models in case of failures.

Codebuff

An AI coding assistant that runs in the terminal, modifies codebases and executes commands in natural language. The official claims it completes full library indexing in two seconds, delivers higher output quality and is over 100 seconds faster than similar products, and supports global npm installation.

BuildAI

A conversational no-code AI application building platform with built-in databases, user management, and paid subscriptions. The official claims that it can turn ideas into applications that can be launched on your own domain within minutes, and it also provides digital employee capabilities.

Sourcery

Sourcery is a team-oriented AI code review tool. After integrating with GitHub and GitLab, it automatically reviews every pull request, detects defects, scans for security vulnerabilities, and provides one-click repair suggestions.

Refact.ai

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

Tabby

Open-source self-hosted AI coding assistant offering code completion, a question-answering engine, and in-line chat. The official states it supports deployment on consumer-grade GPUs, requires no external databases or cloud services, and keeps data within your own environment.

Screenshot to Code

An online tool that converts screenshots, design drafts or screen recording videos into clean code, supporting multiple tech stacks such as HTML, React, Vue, etc. The official states that each generation or modification consumes one credit.

Softgen

An AI website-building tool that can generate full-stack web applications from your ideas. The official says it offers more than ten model options, managed databases and exportable proprietary code, and the free trial does not require a credit card.

Inference.net

Inference infrastructure for AI-native teams, enabling the deployment and monitoring of open-source, self-trained, and fine-tuned models. The official website lists full provider production monitoring, 99.99% available model deployment, minute-level fine-tuning, and cost and quality evaluation based on production traces.

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.

Kodus

Open-source self-hostable AI code review tool, officially claiming that you can use your own model keys with no markup, unlimited PRs, the ability to identify issues across files and enforce team-specific custom rules.

Swimm

Service providers and platforms for legacy system modernization, according to official statements, combine static analysis, generative AI and senior engineers to extract business logic into reusable services and build an agent context layer.

Capacity.so

A conversational no-code website building tool that can generate applications with accounts, login functions and payment features by describing your ideas in plain language. The official says it can connect to Claude or ChatGPT and be launched on your own domain on the same day.

Autocoder.cc

A conversational AI website building and web application development tool. The official claims it can generate data, implement login, payment and deployment functions, provide visual editing, role permission management, code export, and can generate websites from map links.

PearAI

Open-source AI code editor. The official statement says that the built-in model routing automatically selects the best-performing coding model available at that time. It also provides agents, project creation and debugging capabilities, and can be downloaded for free.

Draftly

Draftly is an AI 3D website building tool. According to its official website, you can generate a cinematic scrolling site with just one prompt: first create a cinematic still frame, then generate an approximately 8-second video, extract frames, and then have the browser drive playback with scrolling. It comes with 50+ presets, layer-by-layer regeneration and ZIP export, covering product launches, portfolios and event pages.

Qoder CN

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

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

Cleanlab

Cleanlab real-time assigns credibility scores to AI responses, identifies hallucinations, incorrect context usage and knowledge gaps, uses a single metric to decide when to intercept responses or route them to human agents, and safeguards the output quality of question-answering and customer service systems.

NoCode

The no-code application generation platform under Meituan's ecosystem is officially said to allow generating applications and websites through natural language conversations without programming experience. It has built-in capabilities for data storage, identity authentication and file storage, and supports version rollback and release approval.

Phoenix

Phoenix is an open-source Agent development and evaluation platform by Arize: visualize every step of the calls, prove the effectiveness of changes through experiments, start locally with one command, support self-hosting, and provide a solid basis for improving Agent quality.

QMuse

AI application creation and release platform. The official description states that it enables collaboration with AI through natural language to create runnable web applications, supports continuous editing, previewing, releasing and sharing, and provides a creation IDE, digital avatars and a skill center.

LLM

An open-source command-line tool and Python library for calling OpenAI, Claude, Gemini, Qwen, DeepSeek, and other models from the terminal. It stores prompts, responses, and embeddings locally in SQLite.

CodeRider

The AI programming and DevOps R&D assistant launched by JiHu GitLab integrates intelligent capabilities into workflows such as code hosting, CI/CD and security auditing. It supports SaaS and private deployment, and is targeted at enterprise R&D efficiency and data security scenarios.

Brancher.ai

A no-code AI application building platform that connects different models into shareable mini-apps. The official provides 100+ templates and 100 free credits, and creator monetization is not yet available.

DAIMAX

An AI-driven no-code application generation platform, according to its official website, allows users to generate mini-programs, small tools and mobile applications by describing their ideas in natural language, and supports multi-Agent collaboration, real-time preview and the WeChat Mini Program launch process.

Ciyuan Infinite is an AI programming agent built for Chinese enterprise R&D teams. It supports IDE plugins and native IDEs, can be deployed privately, and improves R&D efficiency and code quality in real-world projects.

Cline

Open-source AI programming agent, officially said to adopt the Plan-then-Act mode to modify code across files and execute bash commands in editors and terminals, supporting MCP extensions and multi-Agent collaboration.

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 official emphasizes self-hosting and on-device architecture, ensuring code never leaves the local environment.

Zof

Zof is an independent verification and control layer located between AI and production environments. According to its official website, 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.

opcode

A desktop client built for Claude Code, officially described as managing Claude sessions through a graphical interface, creating custom Agents, tracking usage, and transforming command-line operations in the terminal into visual panels.

Supermaven

A speed-focused AI code completion tool, the official claims it supports a 1 million token context, with a response time of about 250 milliseconds. It covers VS Code, JetBrains and Neovim, and comes with a multi-model dialogue panel.

HarnessRouter

HarnessRouter integrates harnesses such as Codex, Claude Code, and Hermes into your product as runtime environments, allowing you to switch between harnesses and models with a single set of APIs. It configures isolated sandboxes for each task and provides Arena to compare the time consumption and costs of various combinations.

Bloxks

According to the official website, Bloxks is a natural language-driven no-code mobile app building platform that can generate Android and iOS applications, integrate with APIs such as database and payment APIs, and assist in submitting to app stores. It is suitable for idea validation, independent development, and lightweight game development.

Zide

According to the official website, Zide is an intelligent agent desktop for developers, integrating code, Git, Issues, PRs, CI, terminals, and AI assistants into a native workspace. It supports multi-model access, repository-level modifications, Worktree, and cross-repository project management.

Mireye

Mireye is a physical world data infrastructure for AI agents. It provides cited data, plot enhancement, signals and computing capabilities through the same set of APIs and MCP tools, covering U.S. scenarios such as data center site selection, renewable energy site selection, insurance underwriting, mortgages and commercial credit.

Zinc

Zinc is an API that covers the entire e-commerce procurement lifecycle. According to its official website, it enables cross-retailer product search, real-time price and inventory retrieval, order placement, logistics tracking, and return initiation through a single interface. It also provides access methods such as MCP, sandbox, and SDK for agents and developers.

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.

CartAI

CartAI is a programmatic checkout API for developers: its official website states that it provides a unified interface for product discovery, checkout and payment, enabling cross-merchant product search, valuation generation, transaction execution, and order tracking. It also offers MCP services and hosted checkout components.

Lyzo AI

Lyzo is an AI-native standalone IDE. Officially, it features Claude-powered completion and conversation, full codebase indexing, cross-session persistent memory and autonomous engineering agents. It also integrates zero-configuration CI/CD, Docker and automatic deployment, supporting more than 40 programming languages.

Coommit

Coommit is an AI-native workspace for product teams: officially, collaborate on a shared canvas and launch video calls with one click. AI Echo listens in throughout, visualizes ideas in real time, and documents decisions and tasks. You can one-click send tasks to Claude Code or Codex, with each host seat priced at $29 per month.

Tiden

An intent verification platform for coding agents, officially 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.

BetterDB

A monitoring and auditing platform for Valkey and Redis, officially claims to persist slow queries and command history, provides real-time dashboards, anomaly detection, Prometheus integration and MCP interface, and supports offline deployment.

Irmu

A web scraping API platform for developers, the official website states that it provides capabilities such as JavaScript rendering, screenshot taking, anti-scraping processing, and AI structured extraction. It can obtain clean data from web pages or third-party interfaces with a single REST request and supports SDKs in multiple languages.

LovedByAI

LovedByAI is a WordPress GEO plugin that scans AI readiness for free and provides optimizations such as Schema, FAQ, and LLMs.txt. The official claims that more than 58,000 sites have completed the scan.

Sharp API

Sharp API provides more than 30 pre-built AI API endpoints, covering resume parsing, invoice parsing, 80+ language translation and e-commerce copywriting, outputting clean JSON and providing full-language SDKs.