vibe coding app
ai tool directory 2026.

base44

freemium · $16-160

Pure natural-language AI app builder that generates a complete app, backend, database, auth, hosting, and integrations, from a single prompt. Ranked #1 in multiple 2025-2026 vibe-coding roundups for its end-to-end automation and beginner friendliness. Acquired by Wix in 2025 in a solo-founder $80M exit, and still shipping (Base 1 model, Superagents, GitHub sync).

softr

freemium · $49+

Softr is an AI platform for building the working software your business runs on — client portals, internal tools, dashboards, and operational systems — without relying on developers. Describe what you need, and Softr's AI Co-Builder builds a fully functional app with database structure, business logic, permissions, and interfaces already connected, secure, and ready for real users.

lovable

freemium · $25+

Prompt-first platform to build and iterate full-stack web apps through chat, producing real React/TypeScript/Tailwind code. Lovable adds Lovable Cloud (built-in backend with auth and data persistence), real-time collaboration with unlimited collaborators, agentic mode for multi-step autonomous edits, parallel AI subagents (May 2026) that research, review, and synthesise while the main agent keeps building, AI connectors (Perplexity, ElevenLabs, Firecrawl, Miro), visual CSS editing, themes, built-in analytics, and domain purchasing. Targets non-developers, designers, indie hackers, and agencies who want speed for prototypes, MVPs, and small production apps.

anything.com

freemium · $19-480

AI-powered vibe coding platform (formerly Create.xyz) that turns natural language prompts into production-ready web and native mobile apps with built-in backend services.

pearai

freemium · $15+

Open-source AI code editor built on VS Code, bringing Claude and other frontier models into the editor with your own API key, a local model, or PearAI's hosted router. The free Intern tier is a trial plus bring-your-own-key; Maker is $15 a month and refills $15 of credits rather than granting unlimited requests, with more available pay-as-you-go. Development moved to the pearai-master repository, last pushed 2026-06-19.

9router

free

Self-hosted router that puts one OpenAI-compatible endpoint in front of many model providers, so Claude Code, Codex, Cursor, Cline and Copilot keep working when a subscription hits its quota. Runs as a local Next.js service on localhost:20128 with its own dashboard, compresses tool output before it reaches the model, and falls back across three tiers of provider. Read the security section before you point a real key at it: nineteen security advisories have been published on the repository, all in July 2026, several of them authentication bypasses in the proxy itself.

shipclarity scan

freemium · $1-790

Paste a URL and get seventeen checks in about twenty seconds, with no signup and no login: exposed .env and .git files, API keys left in the front-end bundle, source maps shipped to production, SPF, DKIM and DMARC, the security headers, the mobile viewport, whether missing pages really return a 404. What makes it worth listing is the part most scanners hide. It states that the other 31 of the 48 checks in its paid audit need a human with an account, names them, and tells you they did not run: signup mail actually arriving, password reset end to end, one account seeing another's data, payments, forms that fail silently. Run on vibecoding.app on 2026-09-13, it returned 15 passes, one check marked inconclusive rather than guessed, and a list of what it could not reach.

puppyone

freemium · $19-99

A file system for agents rather than a vector store: it pulls Notion, Slack, Gmail and Postgres into one versioned tree of readable files, hands each agent a scoped access point, and keeps Git-style history over what they change. Reachable through MCP, a CLI and an API, so Claude Code and Cursor read and write the same tree. The Community Edition is Apache 2.0 and self-hostable with no seat fees, which is the version worth trying first if the point is keeping context on your own machine.

cursor

freemium · $20+

AI-native IDE (VS Code fork) with Composer for multi-file editing and Agent mode for autonomous coding. Agent picks files, runs terminal, iterates on errors, and supports up to 8 parallel agents via git worktrees. Background Agents, Bugbot PR autofix, MCP plugins, and .cursor/rules complete the picture.

bolt.new

free

AI-powered, browser-based full-stack app builder that turns natural language prompts into working applications. Built on StackBlitz WebContainers with Supabase integration, Figma/GitHub imports, and one-click deployment; no local setup required.

google antigravity

freemium · $20+

Google's agentic development platform, now split across four surfaces: the Antigravity IDE (VS Code fork), Antigravity 2.0 standalone desktop, the Go-based Antigravity CLI, and a Python SDK for custom agents.

github copilot

freemium · $10+

AI coding assistant integrated into GitHub and VS Code. Generates code, fixes bugs, merges PRs, and now supports agent workflows. The original mainstream AI code tool.

v0

free

AI-powered design-to-code tool from Vercel. Focuses on generating beautiful UIs and frontend components. Works with Figma imports and allows element-level editing. Best for UI-first web projects.

devin desktop (formerly windsurf)

freemium · $20-200

Devin Desktop (rebranded from Windsurf on June 2, 2026; originally Codeium) is Cognition's local AI coding editor. Brings the Agent Command Center, Spaces for parallel work surfaces, ACP support for plugging in Devin Cloud agents, and the SWE-1.6 proprietary model. Pairs with Devin Cloud (autonomous remote agent) and Devin CLI via the same Cognition account.

supabase

freemium · $25-599

Open-source Firebase alternative built on Postgres. Supabase combines database, auth, storage, edge functions, realtime sync, and AI-ready vectors into a single backend platform for shipping full-stack products fast.

replit

freemium · $25+

The complete browser-based development environment. Features Replit AI (Ghostwriter) for code generation, explanation, and autonomous agent capabilities. Zero setup required.

vibecode cli

paid · $20+

Build and deploy high-quality apps with your AI agent. Give the full power of the Vibecode environment including sandboxing, databases, authentication, APIs, and hosting to your agent. CLI-first platform with 30+ pre-authenticated APIs, built-in DB and auth, and App Store deploy. Works with Claude Code, Cursor, Codex, and Gemini as a multi-agent execution layer.

claude code

paid · $17-100

Anthropic's agentic coding interface that lets users describe apps or tasks in natural language and have Claude autonomously plan, write, edit, debug, and iterate code. Available as web app (claude.ai/code) with GitHub integration, and as Desktop app with local file access, visual diffs, and Cowork background agents.

claude code cli

paid

Anthropic's official terminal-based agentic coding tool that deeply understands your local codebase, autonomously edits files, runs terminal commands, handles git workflows, and iterates via natural language prompts. Now with Channels (Telegram/Discord remote messaging), Remote Control, Dispatch, and /loop scheduling for persistent autonomous agents. Designed for professional developers who live in the terminal.

gemini code assist

free

Google's AI coding assistant for supported IDEs and Google Cloud workflows.

github copilot workspace

paid · $10-39

GitHub's AI-powered, agentic development environment that lets you describe changes in natural language and generates plans, code edits, and pull requests across entire repos, all inside a web-based workspace integrated with GitHub.

Top-tier command line AI tool. Lets you pair program with LLMs (Claude 3.5, GPT-4o) directly in your git repo. Edits multiple files effectively.

cline

free

Autonomous AI coding agent for VS Code that handles complex software development tasks step-by-step, with tools for creating/editing files, executing commands, browser automation, and Model Context Protocol (MCP) integration.

cody

freemium · $9+

AI coding assistant that uses Sourcegraph's code graph to understand your entire codebase. Best-in-class for large enterprise repositories and precise context fetching.

blink.new

freemium · $25+

The 'world's first vibe coding platform' that builds full-stack apps and agents from natural language prompts. Excellent for MVPs and non-technical founders.

zed

free

The spiritual successor to Atom, built in Rust for extreme performance. Features built-in AI collaboration and supports multiple LLMs (Claude, OpenAI, etc.).

kiro

free

Agentic AI-powered IDE by AWS that turns natural language into structured requirements, designs, and task lists so solo founders can go from prototype to production with less ambiguity. Also AWS's named successor to Amazon Q Developer's IDE plugins, whose support ends 30 April 2027; the Amazon Q product page points migrating users here for agentic coding, chat and MCP support.

blackbox ai

freemium · $8+

AI coding assistant with multi-model access (Claude, Codex, Gemini, and more), autonomous agents for end-to-end tasks, and IDE integrations across VS Code, JetBrains, and 35+ platforms.

openai codex app

paid

OpenAI's native macOS desktop app for orchestrating multiple Codex agents with worktrees, skills, automations, and a human-in-the-loop review queue.

zhipu ai glm coding plan

paid

Z.ai's GLM Coding Plan by Zhipu AI offers dedicated GLM-4.7 model access for code generation, debugging, and refactoring. Starting at $3/month, this budget-friendly Copilot alternative integrates with Cursor, Continue.dev, and Cline via OpenAI-compatible API.

junie

paid · $100+

AI coding agent built into JetBrains IDEs that autonomously plans, writes, tests, and refines code across files, handling ambitious tasks so you can focus on higher-level decisions.

roo code

freemium · $20-99

Open-source VS Code extension that gives you a full AI dev team in your editor. Supports any model (Claude, GPT, Gemini, local LLMs), custom modes for specialized tasks, and agentic multi-file editing with permission-based control.

webflow

freemium · $15-39

Professional no-code website builder and CMS with pixel-perfect design control. Webflow AI generates layouts and copy, while the visual canvas produces clean semantic HTML and CSS; no templates required.

alibaba coding plan

paid · $50+

Alibaba Cloud's flat-rate subscription for AI coding models. $50/month gets you 90,000 requests across Qwen3.5-plus, Kimi K2.5, MiniMax M2.5, and GLM-5. Works with OpenClaw, Cursor, Cline, and any OpenAI-compatible client via a dedicated API endpoint.

openhands

free

Open-source AI software engineering agent (formerly OpenDevin) that browses the web, writes and executes code, runs bash commands, and resolves GitHub issues autonomously. Backed by All Hands AI and supported by 55k+ GitHub stars.

dify

freemium · $59-159

Visual platform for building LLM-powered applications, RAG pipelines, chatbots, agents, and workflows; without deep ML expertise. Self-hostable or cloud, with 154,000+ GitHub stars.

framer

freemium · $5+

Design-to-website platform with an AI assistant that generates full sites from a prompt, lets you edit visually, and publishes instantly. Beloved by designers and marketers for pixel-perfect, interactive websites without writing code.

crewai

free

Python framework for orchestrating role-playing AI agents that collaborate to complete complex tasks. Define a crew of specialized agents with goals and tools, then let them work together autonomously. 54,000+ GitHub stars and a thriving enterprise tier.

deerflow

free

Open-source SuperAgent harness from ByteDance that orchestrates sub-agents, long-term memory, extensible skills, and Docker-based sandboxes to execute complex, long-horizon tasks like deep research, coding, and content creation.

devin (cognition suite)

freemium · $2-500

Cognition's coding agent suite. Devin Cloud is the autonomous remote engineer (plans, codes, tests, opens PRs). Devin Desktop (formerly Windsurf, rebranded June 2026) is the local AI editor with the Agent Command Center, Spaces, and ACP support. Devin CLI brings the same agent into the terminal. All three share one Cognition account and the SWE-1.6 proprietary model.

openai codex cli

free

The official command-line vibe coding tool from OpenAI. Edits local files, understands your repo, and runs shell commands with your permission. Like Aider, but built by OpenAI.

amazon q developer

freemium · $19+

AWS's AI coding assistant for IDE and CLI workflows with code chat, suggestions, transformations, and security scanning. Being wound down: AWS states on its own product page that it "will discontinue support for Amazon Q Developer IDE plugins" on 30 April 2027, and points users to Kiro for agentic coding, chat and MCP support. The CLI and console experiences are not named in that notice. Treat this as a tool with a known end date rather than one to start a new team on.

deepseek harness

free

MIT-licensed agent harness from DeepSeek AI, built on the idea that everything is a plugin: models, tools, skills, sessions, sandboxes, storage, loops, scheduling and the UI can each be swapped in configuration without touching the source. Start it with one command and it opens a local Web UI at 127.0.0.1:3080, with an append-only trajectory log you can resume, fork, search and replay. Read the trade-off before installing: DeepSeek calls it a developer preview, warns there will be compatibility-breaking changes, and states plainly that it has had no security audit and must not be treated as production-ready.

autogen

free

Open-source Python framework from Microsoft Research for building multi-agent AI systems (now AG2). Agents converse, write and execute code, call tools, and collaborate to solve complex tasks, with human-in-the-loop support.

alibaba cloud ecs

paid · $4.5+

Elastic Compute Service from Alibaba Cloud for deploying and self-hosting AI tools, APIs, and full-stack apps. Popular in Asia-Pacific for OpenClaw hosting with pre-built images and competitive pricing.

hostinger ai hub

paid

AI-powered website creation and content tools to help anyone build and grow online faster.

lingguang

free

Ant Group's multimodal vibe-coding assistant that ships Flash Apps, 3D visuals, and real-time scene insights from a single prompt.

cloudflare pages + workers

freemium · $5+

Edge-first deployment platform combining static site hosting (Pages) with serverless compute (Workers). Deploy full-stack apps to 300+ global locations with a generous free tier and pay-as-you-go scaling.

airtable

free

AI-native platform for building internal tools and workflows on top of structured data.

apidog mcp server

free

Local MCP server that bridges API documentation with AI coding assistants, letting you query specs in natural language and generate type-safe code directly from Apidog projects or OpenAPI files.

wispr flow

free

AI dictation app that turns speech into polished text in any text field, with auto-edits and voice commands.

squarespace ai website builder

paid

AI-guided website builder that generates a personalized site with copy and design in minutes.

openai codex agent

paid

OpenAI's autonomous software engineering agent. Lives inside ChatGPT Pro, capable of planning, executing, and debugging end-to-end coding tasks in a secure cloud sandbox.

builder.io

freemium · $19+

AI platform that converts Figma designs and screenshots into clean React, Next.js, Angular, or Vue code. Visual CMS for non-technical teams to edit pages without touching code, while developers keep full control of the codebase.

omniroute

free

Self-hosted, MIT-licensed AI gateway that puts one OpenAI-compatible endpoint in front of a large multi-provider model catalog. Point Claude Code, Codex, Cursor, Cline, or Copilot at localhost:20128/v1 and it auto-falls back to the next provider when a quota runs out, stacks free tiers, and compresses tokens. Local-first: keys and history stay in SQLite on your machine, no telemetry, no account. Note the trade-offs: provider counts drift between official pages, and draining stacked free tiers can conflict with some upstream providers' terms.

warp

free

A modern, Rust-based terminal with AI built-in. Features intelligent command suggestions, natural language to shell translation, and collaborative tools.

snyk code

freemium · $25+

Developer-first static application security testing powered by DeepCode AI, with real-time IDE scanning, auto-fix suggestions, and data flow analysis across 19+ languages.

vercel

freemium · $20+

Frontend cloud platform for deploying web apps with global edge delivery, previews, analytics, and workflow integrations. Vercel is a top choice for Next.js and modern full-stack product teams.

pieces

free

AI-powered snippet manager and productivity tool. Saves, organizes, and explains code snippets. Works offline and integrates with your workflow.

qodo

paid

Coding assistant focused on code quality: reviews, tests, and improvements.

lemon squeezy

freemium · $24-66

Merchant of record platform for selling digital products, SaaS subscriptions, and software licenses. Handles payments, tax collection, fraud protection, and billing across 135+ countries, now part of Stripe.

langfuse

freemium · $8-249

Open-source LLM observability and engineering platform for tracing, evaluating, and debugging AI applications. Langfuse provides production-grade monitoring with trace spans, cost tracking, prompt management, evaluation datasets, and a playground, all with no per-seat fees and a self-hostable MIT-licensed core.

tempo

freemium · $30+

AI-powered prompt-to-app platform that turns natural language into full-stack React applications with visual editing, multi-agent planning, and one-click deploys.

void

free

Discontinued. The repository was archived on 2 June 2026 and the README states Void is deprecated and no longer accepting contributions. It was a VS Code fork that sent model calls straight to your own provider or a local model, and the last builds still run, but no fix or security patch is coming.

netlify

freemium · $9-20

Web deployment platform with Git-connected builds, global CDN, serverless/edge functions, built-in forms, and a credit-based usage model. Deploy JAMstack and full-stack apps with zero-config CI/CD.

vibesdk

free

Open-source AI "vibe coding" platform built on Cloudflare. Generate full-stack apps from prompts, sandboxed in WebContainers, and deploy instantly to Workers. The self-hosted alternative to Bolt.new.

bolt.diy

free

Open-source platform for prompting, running, editing, and deploying full-stack web apps with multiple model providers.

flutterflow

freemium · $39-150

Visual app builder that generates production-ready Flutter code. FlutterFlow provides a drag-and-drop UI designer, Firebase and Supabase integrations, code export, GitHub sync, branching, and AI-powered page generation, enabling vibe coders to ship cross-platform mobile and web apps without writing Dart manually.

databutton

paid

AI developer that collaborates with you to build and deploy business applications.

string

paid

AI agent builder to prompt, run, edit, and deploy agents to automate workflows quickly.

thunkable

freemium · $19-189

No-code builder for native iOS and Android apps, now led by an AI chat-to-build flow on top of its original drag-and-drop designer and block-based logic editor. The block editor descends from the MIT App Inventor tradition, which is why it has a real foothold in classrooms. Building and testing are free; putting a live app in a store starts at $59 a month for one app, which is the number that decides most purchases and sits well above competitors whose publishing tiers start nearer $36.

firecrawl

freemium · $16-333

Web scraping API that converts any webpage into clean Markdown or structured JSON for AI consumption. Features intelligent crawling, AI-powered extraction, and JavaScript rendering for building AI-ready data pipelines.

flowise

free

Open-source drag-and-drop tool for building LLM flows and AI agents using LangChain and LlamaIndex nodes. Now sunset: the team announced in July 2026 it is winding down, the repository is archived read-only on GitHub, and official support ended 31 August 2026. The Apache 2.0 code can still be forked and self-hosted, but treat it as frozen software with no security patches coming.

bubble

free

Full-stack no-code platform for building and scaling web apps with a visual editor and optional AI features.

tooljet

free

Low-code platform for building and deploying internal tools with integrations and optional AI agents.

continue.dev

free

Open-source CLI tool for Continuous AI that runs async agents on pull requests to enforce team rules, catch issues, and accelerate software shipping.

softgen

paid

AI-based builder for creating full-stack web applications by describing your project.

planetscale

paid · $5-50

Managed MySQL and PostgreSQL platform built on Vitess with database branching, non-blocking schema changes, and zero-downtime deployments. Now offers PlanetScale Metal for NVMe-backed performance.

neon

freemium · $0.1-69

Serverless PostgreSQL with autoscaling, branching, and scale-to-zero. Usage-based pricing with a generous free tier and instant database provisioning for AI-powered development workflows.

sourcery ai

freemium · $12-24

Automated code review and security scanning platform that provides instant PR reviews, real-time IDE feedback, and vulnerability detection, built for teams shipping AI-generated code at scale.

youware

freemium · $20+

AI-powered vibe coding platform that turns natural language prompts into full-stack websites and apps. Features YouBase integrated backend, model switching between GPT-5-Codex and Claude 4.5 Sonnet, and one-click publishing to web and app stores.

devika

free

Open-source AI agent that breaks down tasks into steps and executes them using LLMs and tools.

google opal

free

Google's experimental no-code tool that turns natural language into multi-step AI workflows. Think 'Zapier meets Gemini' but with a visual canvas.

intellicode

free

Microsoft's AI-assisted development tool for Visual Studio and VS Code. Provides whole-line completions and API usage examples based on thousands of open-source projects.

jetbrains ai

paid

Deeply integrated AI assistant for JetBrains IDEs (IntelliJ, PyCharm, WebStorm). Offers context-aware chat, refactoring, and code generation.

qwen3-coder

free

Alibaba's powerful open-source model (Unsloth optimized). Capable of handling huge monorepos with massive context windows. Run it locally or on private cloud.

refact.ai

free

AI coding assistant specialized in refactoring and technical debt reduction. Can run on local or remote models, emphasizing privacy and code quality.

rork

paid

AI tool that builds cross-platform native mobile apps (React Native) from your descriptions.

google jules

free

Autonomous coding agent from Google that integrates with repositories and can generate pull requests.

github spark

paid

GitHub platform to build and deploy full-stack intelligent apps using natural language, visual tools, or code. Now retired: GitHub closed it to new users on 4 August 2026 and ended access on 31 August 2026, leaving a window only to export apps already built. GitHub points builders at Copilot in VS Code, the Copilot CLI and the Copilot app instead.

AI assistant focused on automating coding, debugging, testing, and code review for startup teams.

command

paid

Tool that turns natural language prompts into production-ready AI agents for many tasks.

augment code

paid

Coding assistant that uses your team's knowledge (code, docs, dependencies) via chat, completions, and suggested edits.

goose

free

Open-source AI agent that runs locally for improved privacy and control.

heybossai

paid

Personal AI engineer for non-coders to build apps, websites, and games using natural language.

lemon ai

free

Voice-to-action AI agent for Mac that converts spoken instructions into completed tasks, drafting emails, creating docs, searching, and more; without tab switching or manual input.

openrouter

free

Unified LLM gateway providing OpenAI-compatible API access to 500+ models from 60+ providers. Pay-as-you-go pricing with no markup on model rates, automatic fallbacks, and routing optimizations.

mocha

paid

No-code builder that turns plain English ideas into apps with built-in databases and authentication. This is Mocha at getmocha.com, not the coffee drink and not the JavaScript test framework at mochajs.org: the name collides three ways, and most of the search traffic that reaches this page is looking for one of the other two.

parallel code

free

Free, open-source desktop app that dispatches AI coding agents in parallel, each in its own git worktree. It runs the real CLI agents you already trust (Claude Code, Codex, Gemini) side by side, then lets you review the diffs, merge the wins, and toss the rest.

google disco

free

Google's experimental AI browser that turns open tabs into ephemeral apps. Uses Gemini 3 to create checklists, planners, and comparison tables instantly.

google stitch

free

Experimental Google Labs tool that turns prompts and images into UI designs, supports fast iteration with variants, and offers handoff via Paste to Figma plus front-end code export.

devstral 2

free

Mistral's enterprise-grade vibe coding stack that pairs Codestral models with an open-source CLI agent and self-hosted controls for regulated teams.

jotform ai app builder

freemium · $39+

No-code AI app builder from Jotform that turns a prompt, file, URL, screenshot, or voice note into a working web and mobile app with pages, navigation, forms, workflows, and dashboards. Built on Jotform's form and data components, so it is strongest for form-heavy internal tools, client portals, and data-driven apps. Free to use, with form, submission, and user limits set by your underlying Jotform plan.

memex

paid

Desktop-based builder for creating internal tools and projects locally using natural language.

rocket

paid

AI platform that generates web and mobile apps from natural language prompts or Figma designs.

wonderish

paid

AI builder for generating websites, landing pages, and funnels from text descriptions.

AI app generator that can interpret text (and sometimes images/sketches) to produce full-stack apps.

probz ai

paid

All-in-one platform to build web apps like CRMs and portals without coding, with built-in auth and databases.

magically

paid

AI builder that creates native mobile apps including backend and authentication from prompts.

emergent

paid

Agentic vibe-coding platform designed to help you build ambitious applications with AI.

appwizzy

freemium · $20-100

Flatlogic Generator, renamed AppWizzy: an AI builder for business apps such as CRMs, ERPs and admin panels that hands you the full source code to host and extend yourself.

co.dev

paid

Platform focused on generating full-stack Next.js applications from natural language.

gocodeo

paid

Tool focused on generating tests and helping debug issues quickly.

openclaw

freemium · $6+

Free, open-source personal AI assistant by Peter Steinberger that runs on your machine and performs real tasks autonomously. Talk to it from WhatsApp, Telegram, iMessage, Discord, Slack, or Signal. One-liner install, persistent local memory, ClawHub skills marketplace, sandbox or full system access, and support for Claude, OpenAI, DeepSeek, Qwen, or local LLMs via Ollama. 247K GitHub stars by March 2026; Steinberger joined OpenAI on February 14, 2026 with a non-profit foundation taking project stewardship.

repo prompt

freemium · $14.99-399

macOS-native context engineering app that lets you visually select files and code from local repos, build structured AI prompts, and apply model-generated edits with reviewable diffs.

semantic kernel

free

Open-source SDK from Microsoft for integrating LLMs into applications using C#, Python, and Java. Semantic Kernel provides an agent framework, plugin architecture, prompt template engine, planner, and memory connectors, designed for enterprise AI orchestration with Azure OpenAI and other providers.

figma make

freemium · $15-120

AI-powered app builder inside Figma that turns text prompts into interactive prototypes and full app layouts. Figma Make combines prompt-to-UI generation, design-to-code via MCP integration, context-aware design system usage, and interactive prototyping, all within the Figma platform vibe coders already use for design.

gpt engineer

free

Open-source CLI tool that generates entire codebases from natural-language prompts. Supports OpenAI, Anthropic, and open-source models with customizable agent identity and vision input for diagrams.

agent zero

free

Open-source multi-agent AI framework that runs in a Dockerized sandbox with code execution, browser automation, subordinate agents, and a memory system for building autonomous coding and research workflows.

render

freemium · $7-25

Cloud platform for deploying web services, static sites, background workers, cron jobs, and managed PostgreSQL, all with flat monthly pricing and a generous free tier. Render supports auto-deploys from Git, built-in SSL, and private networking with zero DevOps configuration.

atoms

freemium · $15.8-100

AI employees that validate ideas, build products, and acquire customers in minutes, without coding. A multi-agent crew runs research, planning, full-stack build (frontend, backend, database, auth, Stripe), deployment via Atoms Cloud, and post-launch growth with built-in SEO and ads agents. Designed for founders who want a faster path from idea to a launchable product, not just another prototype generator.

canva code

paid · $10-12.99

Canva Code is Canva's AI-powered code generator that transforms text prompts into interactive HTML/CSS/JavaScript widgets directly within the Canva design platform. Launched in partnership with Anthropic, it lets designers, marketers, and non-developers add calculators, timers, quizzes, and mini-apps to presentations, docs, and websites; no coding required.

Lightweight dark-themed browser interface for Hermes Agent with full parity to the CLI. Three-panel layout with sessions sidebar, chat, and workspace file browser. Community project that runs against any existing Hermes install.

vibe scan

free

Free, no-login web scanner for vibe-coded apps, built by VibeZero, a Perth AI consultancy. Paste a live URL and it runs a read-only scan across six layers: transport and headers, exposed secrets, auth and access control, third-party surface, data exposure, and platform fingerprints. Most scans finish in 5 to 15 seconds. It fingerprints apps built on Lovable, Bolt.new, Cursor, Claude Code, Replit, Windsurf, v0, and Base44, then returns a graded plain-English report. It reads only what the site serves publicly: it does not log in, submit forms, or send attack payloads. The deeper Vibe Code Audit & Fix is a paid human engagement from the same firm, quoted per project rather than sold as a product. Name collision worth knowing: this scanner lives at vibe0.com.au and has nothing to do with either product called VibeKit. Superagent's July 2025 open-source v0 clone was also called vibe0; that name has since been retired and the project is simply VibeKit, now dormant, at /tools/vibekit. Separately, the mobile AI app builder at vibekit.bot shares that name too and is unrelated to both: see /tools/vibekit-bot.

cmux

free

cmux is a free, open-source native macOS terminal built on libghostty (Ghostty rendering engine) with vertical tabs, split panes, notification rings, and a built-in scriptable browser, designed for managing multiple parallel AI coding agents like Claude Code, Codex, and Gemini CLI.

vibekeys

freemium · $29-99

A six-key mechanical keypad with a rotary knob that maps Accept, Retry, YOLO, Escape and Voice to physical buttons for Claude Code, Cursor, Codex, Gemini CLI and Copilot. The Max model adds a status screen and remote control over Wi-Fi.

conductor

freemium · $50-60

macOS app for running Claude Code, Codex, Cursor, and OpenCode side by side, each in its own isolated workspace, without wrangling git worktrees by hand. You bring your own agent subscriptions and keys. The paid Conductor Cloud tier moves those workspaces into Vercel sandboxes so agents keep running after you shut the laptop, and adds shared multiplayer workspaces plus an API.

vibe island

freemium · $19.99+

Native macOS app that turns the MacBook notch into a status panel for AI coding agents. It watches sessions across 26 CLI tools, shows what each one is doing, and jumps you to the exact terminal tab and split pane when you need to intervene. Claude Code, OpenCode and MiMoCode can also be approved and answered from the panel itself; the rest are read-only. One-time licence, no subscription.

contextstream

freemium · $19-237

An MCP server that gives your AI coding agents one shared project memory. It captures decisions, corrections and conventions while you work, then loads the relevant slice into the next session, so Claude Code, Cursor, Codex, Cline and Windsurf start warm instead of asking you to re-explain the architecture every time. A Knowledge Atlas links those decisions back to the code they affect.

orca

free

Open-source Agent Development Environment for running a fleet of AI coding agents at once. Every task gets its own git worktree, its own agent terminal, and its own browser tab, so you can fan one prompt across several agents, compare the diffs, and merge the winner. It drives roughly 30 CLI agents you already pay for, including Claude Code, Codex, OpenCode, Cursor and Copilot, and ships on macOS, Windows, Linux, iOS and Android.

vibe kanban

freemium · $30+

Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.

gemini for macos

free

Google's native Swift assistant for Apple Silicon Macs. It reads the foreground window you point it at, so a question about what is on screen no longer starts with pasting the screen into a prompt.

unvibe

freemium · $15-500

Desktop layer that explains code you already have instead of writing more of it. Select a block in your editor, press a shortcut, and an overlay explains that selection in place; explanations can be saved as concepts and revisited later. It sits beside the editor rather than inside it, so it works alongside Cursor, VS Code, JetBrains, a terminal, Claude Code and Codex rather than competing for the same extension slot. Mac and Windows private beta at the time of listing, free for the first 30 explanations, with no separate API key to supply.

claude design

paid · $20-200

Anthropic Labs' conversational design studio inside Claude. Powered by Claude Opus 4.7, it turns natural-language prompts into interactive prototypes, slides, one-pagers, and polished visuals. Ingests your GitHub repo to extract the project's design system, then hands off a structured implementation bundle to Claude Code for production code. In research preview for Pro, Max, Team, and Enterprise users at claude.ai/design.

kiloclaw

freemium · $10-55

Fully managed hosting for OpenClaw, the open-source autonomous AI agent. KiloClaw reads your email, manages your calendar, monitors your projects, and talks to you wherever you already are. Each instance runs in a dedicated Firecracker VM with persistent storage, native chat-app integrations, and 500+ models via Kilo Gateway. Setup takes under 60 seconds, no Docker, SSH, or YAML required.

tabnine

freemium · $39-59

Enterprise-grade AI code assistant with inline completions, autonomous agents, and an organizational Context Engine. Deploys SaaS, VPC, on-prem, or fully air-gapped with zero code retention. Gartner 2025 Magic Quadrant Visionary for AI Code Assistants.

lance

freemium · $40+

App Store Connect manager that plugs into coding agents over MCP. Point it at a codebase, including a GitHub repo, and it builds, signs and uploads from its own cloud Mac, then handles the App Store side: creating the app record, subscriptions and in-app purchases, capabilities like Sign in with Apple and push notifications, metadata, screenshots, TestFlight distribution and submission for review. When Apple rejects a build it reads the feedback, fixes the issue and resubmits.

a0.dev

freemium · $20+

Y Combinator-backed AI platform that generates complete React Native apps from text descriptions. Ship to App Store and Google Play with one click: the world's fastest iOS build process.

ntm (named tmux manager)

free

NTM (Named Tmux Manager) is a free, open-source tool that transforms tmux into a multi-agent command center. Spawn, tile, and coordinate Claude Code, OpenAI Codex, and Gemini CLI agents across named panes with broadcast prompts, a TUI command palette, conflict tracking, context monitoring, and persistent sessions that survive SSH disconnections.

trae

freemium · $10+

Free AI-powered IDE built on VS Code by ByteDance. Features Builder Mode for autonomous project scaffolding, multimodal input for design-to-code, and access to premium models like Claude 4 and GPT-4o.

codegpt

freemium · $8+

Bring-your-own-key AI coding assistant for VS Code and JetBrains. Connect 15+ AI providers, run local models via Ollama, and keep full control of your data and costs.

coderabbit

freemium · $24+

AI-powered code review platform that automates pull request reviews across GitHub, GitLab, Azure DevOps, and Bitbucket. The most-installed AI app on GitHub with 2M+ repositories.

grok studio

freemium · $30+

xAI's web-based AI coding IDE powered by Grok 4 with real-time preview canvas. Build web apps, prototypes, and games directly in the browser with no setup required.

codegeex

free

Free, open-source AI coding assistant built on a 13B-parameter multilingual model by Tsinghua University (THUDM). Provides code completion, generation, translation, commenting, intelligent Q&A, unit test generation, and repository-level chat across 100+ programming languages. Available as extensions for VS Code, JetBrains IDEs, Visual Studio, and HBuilderX.

marble

freemium · $5-200

A deliberately small headless CMS for a blog and its media, with an API and an MCP server. The MCP server is the reason it appears here: it lets a coding agent create posts, update content and manage media without leaving the editor, which closes the loop for anyone whose agent writes the copy as well as the code. Free tier is real rather than a trial.

muse code

paid · $0.1-4.25

Meta's terminal coding agent, in beta since August 2026 and powered by the Muse Spark 1.2 model with a one-million-token context window. Billing is per token rather than per seat, and the pricing carries an unusual choice: a contributor tier costs a fraction of the standard one because your data is used for product improvement. Multiple agents coordinate on a task and every action is meant to be traceable.

agentsky

freemium · $0.01-50

Runs coding agents in the cloud so they keep working when your laptop closes. Pick a harness, Claude Code, Codex, Hermes or pi, pair it with a model, and reach it over one API. Billing splits in two: compute by the second while the machine is awake, and model tokens at published per-model rates. The detail worth knowing is that you can connect an existing Claude or ChatGPT subscription, in which case model usage costs nothing and you pay only for compute.

openworker

free

Andrew Ng's open-source desktop agent that hands back finished work instead of chat. It runs on your machine, connects to the tools you already use, and checks in before anything consequential. The August 2026 release added three security coworkers: one drives semgrep and secret scans and triages findings by reachability rather than severity, one checks Terraform against the live cloud read-only and opens infrastructure pull requests, and one audits dependencies. Bring your own API key, or run a local model through Ollama and nothing leaves the machine.

myvibe by myhbd

free

Managed VPS from the Dutch host MyHBD with a deployment panel on top: connect a GitHub repository, and MyVibe builds and runs it with a custom domain, SSL, databases, Docker services, background workers, logs and environment variables on a server you can also reach over SSH. Aimed at people who built an app in Lovable, Bolt, Cursor, Replit or v0 and need somewhere with a database to run it. Fixed monthly price per server, no per-app or per-domain limits beyond the server's own resources, datacenter in the Netherlands. Not to be confused with MyVibe by ArcBlock at myvibe.so, a different product.

free-claude-code

free

MIT-licensed local Python gateway that sits in front of coding agents and routes Anthropic-format traffic to free, paid, subscription and local backends. The README claims 50 ToS-friendly providers, 1.3B+ free tokens a month and 10 coding agents (Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, Aider) behind one searchable model catalog, with automatic fallback to the next configured model when a provider fails. It is an independent project, not affiliated with Anthropic: you keep the agent harness, not Claude's weights, and free-tier limits belong to each upstream provider and may change. A GitHub issue titled "Malicious claims about this repo" is a community dispute, not a verified finding, and no privacy or security policy page exists beyond the README.

apache maka

free

Apache-incubating agent workspace where the Desktop app, the TUI and the CLI are thin clients of one Runtime Host, and every model message, tool call, permission decision and termination is written as an append-only RuntimeEvent: the project's own line is "the log is the runtime". You bring the model (a cloud API, a local model or a compatible gateway) and sessions, settings and run records stay on your machine. Its site publishes a nine-harness Terminal-Bench 2.1 table with per-task CSVs rather than a headline claim. Read the status before installing: as of 8 September 2026 Maka has not made an Apache release, the desktop nightlies are unsigned previews not intended for production, and the CLI ships as maka-agent@next on npm (the unrelated maka package is not this project). Its SECURITY.md is unusually direct: the only enforcement boundary against an adversarial LLM is the operating system, and API keys sit in a local plaintext credential file readable only by your OS account.

archify

free

MIT agent skill for Cursor, Claude Code, Codex and OpenCode: describe a system in chat, or point the agent at a repository, and it produces a self-contained interactive HTML diagram (architecture, workflow, sequence, data flow or state machine) with no runtime dependencies, plus PNG, SVG, WebP and clipboard export. The agent writes a typed JSON intermediate representation and Archify compiles it deterministically, which is what makes the output checkable, and a Before/Delta/After compare reviews architecture changes before merge. It is not a drawing editor or a Mermaid theme. Two name collisions to avoid: archifyai.com (building design) and Archify AG (a Swiss CAD firm) are unrelated companies.

port ai builder

freemium · $30-40

Natural-language builder inside Port's internal developer portal: describe what you need and it builds agents, workflows, scorecards and dashboards grounded in your software catalog, RBAC and guardrails. Plan Mode drafts a plan and waits for approval, with every version saved, before Build mode lays down the data, measurement, action and visibility layers. Port launched it on 14 July 2026 as a vibe-coding experience for platform engineering teams, so read the scope accordingly: it is a SaaS layer on Port's catalog and governance stack, not a consumer app builder, and it is not self-hostable outside Enterprise dedicated tenancy. Port itself lists SOC 2 Type 2, ISO 27001 and GDPR on its security page.

retool

freemium · $10+

Low-code platform for building internal tools, admin panels, and dashboards. Retool combines 90+ drag-and-drop UI components with JavaScript extensibility and AI app generation to connect any database or API.

paperclip

free

Open-source framework for building AI agent teams organized as virtual companies, CEO, Engineer, and QA agents coordinate work through projects, issues, and heartbeat schedules.

one

freemium · $29-199

Integration runtime and command center for AI agents. Provides authenticated access to 250+ platforms with 47,500+ actions, managed OAuth, scheduling, memory, and a universal MCP server, all through a single CLI.

aquilax vibe

freemium · $19-99

Specialized security scanner from AquilaX, built for AI-generated and vibe-coded software. Fingerprints LLM-written code, then runs SAST and taint analysis tuned to the insecure defaults, hallucinated APIs, and copy-pasted snippets that Copilot, Cursor, Claude, and ChatGPT introduce.

hermes agent

free

Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.

claude cowork

paid · $17-100

Anthropic's agentic desktop app for non-technical knowledge workers, released as a research preview in January 2026 with a wider enterprise rollout in February 2026 adding Google Drive, Gmail, Docusign, and FactSet connectors. Give Claude a goal and it works on your computer: opens local files and applications, plans the work, coordinates sub-agents, runs steps in an isolated VM, and delivers a finished deliverable. Sibling product to Claude Code, aimed at marketers, ops, researchers, and founders rather than engineers.

wix harmony

freemium · $17+

Wix's hybrid editor that pairs the Aria AI agent with traditional drag-and-drop. Describe a site in natural language, get a working layout, then refine pixel-by-pixel on a responsive canvas. Sites run on Wix's managed infrastructure (multi-cloud hosting, technical SEO, accessibility tooling).

vibekit (superagent)

free

Looking for the mobile AI app builder at vibekit.bot? That is a different product: see VibeKit at /tools/vibekit-bot. This page covers superagent-ai/vibekit, the open-source sandbox. MIT-licensed CLI wrapper and SDK from Superagent (YC) that runs Claude Code, Gemini CLI, Codex, Grok CLI, and OpenCode inside an isolated sandbox, redacting secrets from completions and logging every file change, shell command, and outbound call. Install with npm and prefix your usual command: `vibekit claude`. The local path uses Docker and needs no cloud account; the `@vibe-kit/sdk` package embeds the same sandboxing in your own app across E2B, Dagger, Daytona, Northflank, Cloudflare, Modal, and Fly.io. Development has been quiet since November 2025: no commits to the default branch since 2025-11-10, no npm publish since 2025-10-14, and Superagent's recent work has shifted to its grok-cli and gateway projects. The code is MIT and still installs, so treat it as forkable rather than actively supported. Naming history, and there are three collisions worth knowing. First: in July 2025 the team shipped an open-source v0 clone called vibe0, built on VibeKit. That name has been retired and the project is now just VibeKit, with the template surviving in the repo as templates/v0-clone. Second: VibeKit at vibekit.bot is an unrelated mobile-first AI app builder by Brian Boisjoli, still actively shipping, and its own about page states it is not affiliated with this project. Third: Vibe Scan at vibe0.com.au is a security scanner from a Perth consultancy that happens to share the vibe0 name.

vibekit

freemium · $0.5-49.99

Looking for the open-source agent sandbox on GitHub? That is a different product: see VibeKit by Superagent at /tools/vibekit. This page covers vibekit.bot. Mobile-first AI app builder where every app you create gets its own persistent AI agent, a real GitHub repo under your account, and a live URL at yourapp.vibekit.bot. Describe what you want and the agent builds it, deploys it to a managed container, then keeps working: health checks every 60 seconds, auto-diagnosis and redeploy when something breaks, and AI QA that browses the live app and files bug reports. The agent runs server-side, so the iOS app is a remote control rather than the thing doing the work, and closing your phone does not stop a run. Drive it from the iOS app, the web dashboard, a CLI, a REST API, or an MCP server. Pricing is BYOK-first: connect your own Anthropic or OpenAI key and the agent bills that provider at standard rates with no platform margin. Without a key, requests route through OpenRouter against a credit balance at a platform markup the privacy policy puts at 20 percent, with OpenRouter's data-discount setting enabled on that path only; a free model option keeps building at $0, and the free tier runs $0.50 a session past its first ten. Built and run by one person, Brian Boisjoli, and actively shipping. There is no enterprise tier, no published SOC 2 or SSO, and no Android app.

vibecodesecure

free

Free, no-login web scanner built for vibe-coded apps. Paste a web app or API URL and it checks security headers, TLS/SSL, authentication controls, and infrastructure configuration for common vulnerabilities and misconfigurations. Tuned for apps shipped from platforms like Replit, Databutton, and Cursor.

vibe eval

freemium · $19-199

AI-powered dynamic security testing for vibe-coded web apps. Paste a deployed URL and autonomous agents probe it like an attacker would, checking for missing Supabase/Firebase RLS, exposed API keys, auth bypasses, broken CORS, open storage buckets, and IDOR. Findings ship with a captured exploit and reproducible proof of concept, plus fix prompts ready for Claude Code, Cursor, or Lovable.

kliv

freemium · $19-99

Agentic app builder that turns a conversation into a deployed React, TypeScript and Tailwind app with auth, database, payments and free hosting on kliv.site included on every plan.

capacity

freemium · $25-299

AI app builder with two modes: Vibe Coding for fast iteration and Spec Coding that writes the brief and user stories first. Ships web and native mobile apps, exports the full codebase, and has a desktop app that runs on your own Claude, GPT or Gemini subscription.

pipilot

freemium · $17-33

Prompt-to-project builder that outputs web, Expo mobile, desktop, Python or Node backends, CLIs and packages, with a built-in Postgres, agent teams, 130+ MCP integrations and code synced to your own Google Drive.

vibe80

free

Apache-2.0 web workspace that orchestrates Codex and Claude Code over your Git repositories in sandboxed parallel worktrees, with a PTY web terminal and a mobile companion app that picks up a session by QR code.

pilot protocol

free

Open-source overlay network that gives AI agents permanent virtual addresses, encrypted UDP tunnels, NAT traversal, mutual-trust handshakes and a signature-verified app store, with native MCP setup for Claude Code, Cursor and Codex.

tokens forge

freemium · $0.11-0.67

Multi-model API gateway that puts GPT, Claude, Gemini and lower-cost routes behind one OpenAI-compatible key, with per-key model scopes, balance tracking, request-level receipts and fallback routing.

moadim

free

A loop engine that runs coding agents on a schedule against your codebase. A loop pairs a prompt, a schedule and an agent (Claude, Codex, Hermes, NanoClaw or Pi), and each run executes in a throwaway workbench so a hung run gets killed rather than left behind. Everything is exposed twice, as a REST endpoint and as an MCP tool, so another agent can schedule work as easily as you can. Routines live in ~/.config/moadim/ and are git-trackable. It runs entirely on your own machine: no cloud, no account, no data leaving the host.

A macOS app that pins the usage limits of Claude Code, Cursor, Codex and Antigravity to an edge of your screen, so you can see how much of a plan is left without asking. It also answers the question the official commands do not: whether a run is still working, shown as a thin arc that spins while a provider is busy. It never signs in anywhere, borrowing the credentials of sessions you already have. Primary platform is macOS, with a Windows port in Rust and Tauri 2; there is no native Linux build.

kit

free

A coding agent runtime from Speakeasy that gives the model a single tool, compose, whose argument is a short program rather than a one-off call. The intent is fewer model round trips: more work completed per request, and less context repeated. It ships a terminal client, an Agent Client Protocol server and an A2A endpoint, speaks ACP v1 and v2 over stdio, HTTP/SSE and WebSocket, and stores sessions as append-only JSONL. Bring your own model, including ChatGPT subscriptions over native OAuth. It is deliberately small and says so: no web UI, no visual debugger, and no permissions framework of its own.

supafork

free

Version control for what your coding agents did. Supafork imports sessions from the harnesses you already run and keeps every prompt, session, tool call and skill in one searchable place, so a task started in Claude Code can be continued in Codex without losing the trail. It auto-detects and imports from OpenCode, Codex, Claude Code, DeepSeek, Pi, Gemini CLI, Cursor, GitHub Copilot CLI and Droid. Access is gated: it is free during the beta and you request a place as capacity opens.

Persistent memory for coding agents kept as plain files in your repository rather than in a vector database. It implements Google's OKF v0.2 specification with progressive disclosure, so the agent pulls in only the slice of memory a task needs instead of paying for the whole store on every request, and retrieval uses BM25 rather than embeddings. Because the memory is git-native it diffs, reviews and reverts like the rest of your code, and it publishes its own security documentation, which is unusual for a tool whose entire job is persisting context to disk.

49 ide

freemium · $1+

An IDE built as one infinite zoomable canvas instead of tabs, aimed at people running several CLI agents at once. Terminals, git graphs, issues, files and notes sit side by side in space, across projects and across machines, without SSH. The pitch is replacing fourteen terminal tabs with one canvas you can pan around. Note the licence: despite the project describing itself as open source, it ships under the Business Source License 1.1, which is source-available. It is free for individuals and for organisations under both one million dollars in trailing twelve-month revenue and one million in equity funding or debt; above either threshold a commercial licence is required. The licence converts to MIT on 2030-02-26.

Runs mixture-of-experts models that do not fit in a Mac's memory by streaming the experts it needs from SSD, so a 105 GB model can run on a 48 GB machine. Apple Silicon only, built on MLX, and focused on one model family rather than being a general local-model runner. Treat the throughput and SSD-wear figures as the project's own measurements: they are published and detailed, and no independent verification exists yet. The project is weeks old and moving quickly. Sevra, listed as its homepage, is a future consumer app built on top of it rather than a paid tier of it.

openhuman

freemium · $5-199.99

Desktop application from TinyHumans AI that keeps a local memory of your work and runs fleets of agents against it, with connectors to outside services and a research mode over them. Built in Rust and Tauri and distributed as a desktop install rather than a hosted product, which is the point of it: the memory stays on the machine. Young, and moving quickly, so treat the connector count on the marketing site as a moving figure rather than a specification.

salesforce agentforce vibes

freemium · $500+

Salesforce's own vibe-coding stack: describe what you need and it plans, builds, tests and deploys agents, apps and Salesforce metadata inside your org. It is aimed at Salesforce development rather than at general app building, which is the thing to understand before comparing it with Lovable or Bolt. The interesting part for anyone outside that world is what an enterprise vendor thinks this workflow has to include before it can be sold: deployment into an existing org, the platform's own permissions model, and metered billing per prompt. Note the access requirement, which is unusually strong: Salesforce's help documentation says users need the View All Data permission to use it.