Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

awesome-vibe-coding-resources

A curated list of awesome resources for vibe coding
https://github.com/acvnace/awesome-vibe-coding-resources

Last synced: 18 days ago
JSON representation

  • Browser-based Tools

    • Bolt.new - prompt, run, edit, and deploy full-stack web and mobile apps.
    • Lovable - "idea to app in seconds. Lovable is your superhuman full stack engineer".
    • v0 by Vercel - assistant to build NextJS frontend.
    • Replit - "simply describe your idea above and let the Agent build it for you".
    • Create - "turn your words into sites, tools, apps and products".
    • Trickle AI - "build stunning websites, AI apps, and forms with ease".
    • Tempo - "build React apps 10x faster with AI".
    • Softgen - "describe your vision, give instructions, and build full-stack web apps".
    • Lazy AI - "build reliable business apps with prompts".
    • HeyBoss - "build app & sites in minutes".
    • Creatr - "create and deploy web apps and landing pages in seconds".
    • embedible.io - AI that transforms your electronics ideas into working projects.
    • WeWeb.io - "describe your vision to AI, refactor it visually, and ship secure, production-grade apps fast."
    • Vibe Coding Profiler - Analyzes git history to reveal your AI-assisted engineering style and vibe coding persona.
    • Playcode - AI website and app builder with visual editing, hosting, and custom domains.
    • Roblox GUI Maker - Generate Roblox Studio GUI layouts and Lua starter code from prompts.
    • CUT3 - vibe coding for video: describe an edit, an agent rewrites the timeline and hands it back as a diff you approve.
    • Taskade Genesis - prompt to a live portal, CRM, or dashboard with agents and automations.
    • Whimcade - describe a game in one paragraph and an agent builds it as a self-contained HTML5 bundle you can play in the browser, iterate on, and publish to a public arcade.
    • kdpbook.io - vibe coding for books: describe a book in a chat and get it written, illustrated and typeset, with the Amazon KDP print PDF, full-wrap cover, Kindle eBook and listing ready to upload.

  • Command Line Tools

    • codename goose - Local, on-machine AI Agent that allows you to use any LLM and add any MCP servers as extensions
    • anthropics/claude-code - Coding agent that understands your codebase, automates tasks, explains code, and manages git, all via natural language.
    • aider - AI pair programming in your terminal.
    • MyCoder.ai - Open source AI-powered coding assistant with Git and GitHub integration, featuring parallel execution and self-modification capabilities.
    • claude-dash - Real-time statusline for Claude Code showing context, cost, quota, cache, tools, and git status.
    • MUSE - Pure-Markdown memory OS for AI pair programming. Cross-conversation memory, 48 skills, role-based governance. Works with Claude Code, Cursor, Windsurf, OpenClaw, Gemini CLI, Codex CLI. Zero dependencies, MIT licensed.
    • agenttrace - Local TUI for inspecting AI coding-agent session logs, usage, cost, latency, tool failures, diffs, and CI gates.
    • sober-coding - Post-generation audit for vibe-coded repos. 27 static checks across 7 dimensions (dead code, god files, duplicate blocks, deep nesting, empty except, dependency utilization…) with per-check fix suggestions and a CI mode that fails PRs on regressions. Language-agnostic, no LLM required.
    • codex-profiles - Small Bash helper for switching Codex CLI/Desktop accounts with isolated `CODEX_HOME` profiles.
    • SwarmClaw - Self-hosted multi-agent runtime that delegates to Claude Code, Codex, Gemini CLI, OpenCode, Copilot CLI, Cursor Agent, Goose, Qwen Code, and Droid. Org chart view, schedules, runtime skills, persistent memory, sub-agent spawning. MCP-native (server and client). Electron desktop app, CLI, and Docker. MIT.
    • SwarmVault - Local-first RAG knowledge vault with bundled MCP server (`npx -y @swarmvaultai/cli mcp`). Compiles raw sources (notes, transcripts, exports, docs, code) into a durable markdown wiki with a knowledge graph and hybrid SQLite FTS plus embeddings. Cuts agent token usage by serving compact wiki summaries instead of full file reads. MIT.
    • ax - Local telemetry for AI coding agents.
    • nika - Workflow engine for AI: capture repeatable vibe-coded tasks as .nika.yaml files, statically checked before execution (schema, permits, cost), with tamper-evident traces after.
    • Tree Ring Memory - Framework-agnostic local-first memory lifecycle for AI coding agents with Rust CLI, SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve adapters, and TUI.
    • DevIntern - Picks up tickets from Jira, Linear, Trello, Asana, Azure DevOps, GitHub Issues, or markdown files and turns them into self-reviewed pull requests using the coding agent of your choice (Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and others), on your machines with your own model keys. A feasibility gate flags vague tickets back to the tracker with questions; the companion devpm tool creates codebase-grounded tickets from rough prompts. FSL-licensed, free for interactive use.
    • whatbroke - Diff your AI agent's behavior between two runs: tool calls, args, cost, latency, and outcome flips, with flake detection and CI exit codes. MIT, on npm as whatbroke-cli.
    • OrcaReplay - Records a coding-agent session below the harness and replays it offline byte-for-byte with the network off, or forks it from any checkpoint onto a different model.
    • d1v - CLI deployment workflow for AI-built web projects with verified previews and production releases requiring explicit confirmation. MIT.
    • YYLO - Command-line orchestrator for coding agents, repeatable workflows, and receipt-backed repository changes: typed task, validation, merge, and release-readiness boundaries, with each task on a dedicated branch/worktree and a merge queue that owns risk-based review. MIT, on npm as @yylo/cli.
    • MyVibe - Instant deployment for vibe-coded apps via Claude Code.
    • Hyperconsciousness - Developer-alpha Rust CLI and MCP knowledge store for agent notes and task handoffs, with encrypted append-only records and scoped, expiring grants.
    • MulmoTerminal - Browser grid of live Claude Code / Codex sessions started with one `npx` command. Each cell is a real PTY, colour-coded working / needs-you / done from the agent CLI's own hooks, with tmux-backed persistence and a git worktree per cell.
    • since-cutoff - Finds which APIs of your pinned Python dependencies changed after your coding agent's training cutoff, measures which of them the model actually gets wrong by type-checking its code against both versions, and writes one-line AGENTS.md / CLAUDE.md notes that are kept only if their example type-checks. `uvx since-cutoff scan` needs no API key. MIT, on PyPI as since-cutoff.
    • agent-manager - Terminal UI that runs your installed Claude Code, Codex, OpenCode, Gemini CLI, and other coding-agent CLIs side by side, each in its own persistent tmux session. One list shows every session's live status, a session can spawn into its own Git worktree, and a full-file diff review sends line comments back to the agent. Apache-2.0, in homebrew-core as agent-manager.
    • DropTheHassle - Puts an AI-built static site online from the terminal with `npx -y dropthehassle deploy`: a free HTTPS link without signing up (claim it to keep it), or your own domain. Also an MCP server for Claude Code, Cursor and Windsurf; the agent can never spend money. MIT.

  • Contents <!-- omit in toc -->

    • Ivy Tendril - Open-source agentic software factory with an amazing UI that handles parallel Git worktrees for you, complete with programmatic verifications and fast review loops.

  • Desktop Apps

    • Parallel Code - Open-source desktop app for running Claude Code, Codex CLI, Gemini CLI, and other terminal coding agents in parallel, with isolated git worktrees, terminal panes, diff review, and merge controls.
    • Agent FM - Local, open-source macOS app for listening to Claude Code and Codex agents as they work, with Global Mix and blocker alerts.
    • Agent Teams - Open-source desktop app for autonomous AI coding teams across Claude, Codex, and OpenCode. Give high-level commands while agents handle Kanban tasks, messaging, code review, logs, and approvals across 200+ models and 75+ LLM providers.
    • Agent Island - Open-source macOS notch companion for Claude Code and Codex long runs, with live session state, usage tracking, and optional auto-resume for trusted sessions.
    • Blume - Desktop sidecar that monitors coding-agent sessions, shows the rules, skills, and hooks shaping each run, tracks usage across Claude Code, Codex, Cursor, omp, and Pi, and keeps chat history local.
    • PinkCode - Open-source desktop GUI for running multiple Grok Build coding-agent sessions in parallel, with live activity, usage, file-change, and permission views.
    • Better Agent - Local workspace for Claude, Codex, and Gemini sessions with parallel forks, delegation, persistent state, and restart recovery across browser, desktop, mobile, CLI, and SDK. Source-available for non-commercial use; commercial use requires permission.
    • Orkas - Open-source, local-first desktop workspace that coordinates specialist agents and runs Claude Code, Codex, OpenCode, and Cline from one chat. [Source](https://github.com/Orkas-AI/Orkas)
    • DevProjex - Builds clean, AI-ready project context with folder trees, file contents, token counting, Smart Ignore, preview, and multi-format export through a fast cross-platform GUI and CLI.
    • BitFun - Open-source cross-platform desktop AI agent that plans, edits, tests, and commits in real Git repositories, while also handling browser, terminal, desktop-app, and remote-workspace tasks through MCP, Skills, Hooks, and task-specific Mini Apps.
    • Tintpad - Open-source macOS menu-bar launcher for AI coding agents: a global-hotkey palette fuzzy-finds a git repo and opens your own terminal there with Claude Code, Codex, or Gemini CLI running.
    • Superagent - Open-source macOS desktop app that gives Claude Code and Codex a real browser to navigate and drive, an iOS Simulator to install and screenshot apps in, and a phone companion app for remote monitoring.
    • Adnify - Source-available AI-native desktop engineering workspace that combines code editing, direct-execution agents, governed multi-agent planning, terminals, asset generation, and browser verification in one app.
    • Oh My Android - Free, open-source (MIT) native macOS app and built-in MCP server that lets Claude Code, Codex, and Cursor see and drive the Android Emulator: screenshots, UI tree in dp, tap/type, dark mode, locale/RTL, logcat.
    • AgentGrid - Desktop workspace for coordinating Claude Code, Codex, and other coding agents through visible worker conversations, persistent notes, terminals, and browser previews. Supports macOS, Windows, and Linux; closed-source with a free tier and bring-your-own AI provider access.
    • NextReset - Free browser-based Codex companion with source-linked public reset history, official AI-service incident updates, and a local personal allowance timer; no account required.
    • antiburn - Free, local desktop app that checks coding agent sessions for common causes of token burn: sessions too deep, overpowered subagents, broken caching, and unused MCPs, skills, and tools. Supports Claude Code, Codex, Cursor, Copilot, Pi, and more.
    • Lunavect - Free, open-source (MIT) Mac menu bar app for Claude Code and Codex that shows which session is working, waiting for you, or done, plus weekly and five-hour usage limits with reset times, notifications, and desktop widgets.

  • Documentation for AI Coding

    • CodeGuide - Creates detailed Documentation for your AI Coding Projects.
    • LegacyDoc AI - VS Code extension that generates documentation, architecture maps, and AI-ready context packs for vibe-coded codebases.
    • vibeprompt - Free 10-step vibe coding workflow with 56 prompts, 17 deep-dive articles, 46 field-tested fixes, and an interactive AGENTS.md + PRD generator. Open source, MIT licensed.
    • Codex First Task Prompt Generator - Free browser tool for turning a vague Codex CLI project goal into a scoped first-task prompt with file boundaries, constraints, and acceptance checks.
    • Wikivibe - Practical knowledge base for AI-assisted development with guides, a glossary, jobs, and a public MCP endpoint.
    • Vibe Coding Essentials - Anti-hallucination guardrails for 9 frameworks + a 4-mode workflow system (Economy / Builder / Maintainer / Architect) for AI-assisted development.
    • AI Coding Tools Guide - Workflow-based comparisons for Cursor alternatives, Claude Code, Windsurf, Cline, GitHub Copilot, Aider, Continue, and MCP-enabled AI coding.
    • AI Book: AI Coding - Chinese AI coding handbook covering coding-agent workflows, tool selection, prompts, and practical AI-assisted development guides.
    • Fix AI UI Slop With Real UI Context - A three-step workflow for researching public UI references, giving coding agents UI context, and checking implementations with design-contract, validation, audit, and critique workflows.
    • Vibe Coding with Confidence - Web handbook on building AI-assisted apps that work beyond the demo: plan, build, debug, harden, ship, operate, and scale.
    • breaking-coding-chaos - Human-in-the-loop dual-loop control-plane skill suite for coding agents (Claude Code, Codex, Cursor, and more): throughline progress on disk, plan-spar alignment, then minimal clean-cut implement.
    • Fix AI UI Slop With Real UI Context - A three-step workflow for researching public UI references, giving coding agents UI context, and checking implementations with design-contract, validation, audit, and critique workflows.
    • THROUGHLINE - Spec-driven development framework for coding agents, made of markdown and git with nothing to install. Personas debate each spec before code, and an append-only single source of truth keeps earlier decisions from drifting across sessions. Works with Claude Code, Codex, and Cursor. English and Korean, MIT.
    • anti-slop-website-prompts - 15 free art-directed website build-prompts plus an anti-slop design skill for Lovable, Bolt, v0, Cursor, and Claude Code.
    • BuildMuse - Curated interface videos, app screens, websites, motion references, and frontend effects for giving vibe-coding agents clearer visual direction.
    • Undercroft - Open-source CLAUDE.md operations contract that turns Claude Code into the maintainer of a plain-Markdown personal wiki: three-layer raw/wiki/schema architecture, checklist-driven ingestion, append-only changelog, and a worked example vault. Obsidian-friendly and portable to other agent CLIs via an AGENTS.md rename. MIT.
    • Vibe Coding UI Specification - Free, MIT-licensed interface contract for AI-assisted React and Tailwind work, covering design tokens, component states, responsive behavior, WCAG 2.2 AA, reduced motion, production gates, and reusable YAML.
    • Vibe-Coding Prompt Template - MIT-licensed five-step workflow (deep research, PRD, tech design, AGENTS.md, build) with copy-paste prompts and an `npx vibeworkflow` CLI that interviews you and writes the planning docs and agent files.
    • ContextStream - Shared project context for Cursor, Claude Code, Codex, Grok. Remote MCP: https://mcp.contextstream.io/mcp. Intelligence isn’t the bottleneck. Context is.
    • Ariadne Loop - Local-first Loop Engineering workbench for writing verifiable AI coding-agent specs, verifier gates, rollback rules, and JSON reports.
    • liyupi/ai-guide - Free Chinese vibe coding handbook covering tool selection, prompting and context management, dozens of end-to-end project builds, and shipping to production. English and Traditional Chinese translations included. [Online version](https://ai.codefather.cn/vibe).
    • AI Game Dev Framework - MIT-licensed documentation and agent workflow starter for game development, with design decision boundaries, project onboarding, and versioned delivery reviews.
    • ContextStream - Shared project context for Cursor, Claude Code, Codex, Grok. Remote MCP: https://mcp.contextstream.io/mcp. Intelligence isn’t the bottleneck. Context is.
    • OrcaPromptVault - Dated archive of what the coding agents themselves are told: system prompts and tool schemas from 43 products, 44 of them recorded off the wire with a command that reproduces each. Useful when an AGENTS.md or CLAUDE.md is not having the effect you expect and you want to read what it is competing with.
    • shadcn-vite-starter - MIT-licensed Vite and React starter whose CLAUDE.md, AGENTS.md and agent skills keep coding agents on its patterns: one folder per feature, shared data-fetching rules, tests first and a full check run before they finish.
    • Bestax - React components for Bulma v1 that ship Agent Skills, an offline MCP server (bestax-mcp) and llms.txt docs.

  • IDEs and Code Editors

    • Zed - Code editor designed for high-performance collaboration with humans and AI.
    • Windsurf Editor by Codeium - Agentic IDE, "where the work of developers and AI truly flow together, allowing for a coding experience that feels like literal magic".
    • Vicoa - Agentic IDE, AI orchestrator for running Claude Code, Codex, OpenCode, Gemini, Cursor, GitHub Copilot, Kimi, and Hermes from desktop, web, or mobile: real-time sync, parallel git worktrees, and push notifications, with a Python/FastAPI backend, Next.js + Electron desktop, and Flutter mobile. [Source](https://github.com/vicoa-ai/vicoa)

  • Mobile-first Tools

    • Vibecode - "the mobile app that builds mobile apps".
    • Primio - chat-based builder that turns prompts into full Flutter apps for mobile and web, with live preview, an in-browser emulator, and one-click publishing to the app stores.
    • VibeKit.bot - build, deploy, and manage full-stack apps from your phone by chatting with a persistent AI agent that runs on hosted containers (not your device), so you get a live URL, a GitHub repo you own, and bring-your-own-key for Claude/OpenAI.
    • WeInc - AI website builder that generates complete hosted production sites (React) from prompts, with flat pricing and white-label for agencies.
    • Sillage - self-hosted, MIT-licensed, mobile-first web UI that drives the native Claude Code and Codex CLIs on your own machine (the official agent harnesses, without a terminal), with sessions that outlive the client, full-text search over every conversation, an IDE panel (file explorer, editor, diffs, terminal), a board the agents read through its own MCP server, and an installable PWA with push. Single Docker container.
    • vibepanel - self-hosted, MIT-licensed web console for running many Claude Code and Codex sessions in parallel from a desktop browser or a phone; each session lives in tmux, so agents keep running through panel restarts, upgrades and dropped connections.

  • News and Social Media

  • Plugins and Extensions

    • Cline - AI assistant that can use your CLI aNd Editor, for VS Code.
    • avante.nvim - Neovim plugin designed to emulate the behavior of the Cursor AI IDE. It provides AI-driven code suggestions and allows you to apply recommendations directly to your source files with minimal effort.
    • backnotprop/prompt-tower - A tool that helps you build prompts with many code blocks.
    • Roo Code - Fork of cline with extra features/enhancements
    • NEDIO - Pomodoro timer, focus music, and structured AI sprint reviews for focused work in VS Code and Cursor.

  • Security & Pre-Deploy Checks

    • Vibeproof - Instant security scan for vibe-coded apps (Lovable, Bolt, v0, Cursor). Paste a URL or a public GitHub repo to find exposed secrets, open Supabase/Firebase databases, leaked files, vulnerable libraries, and GDPR gaps. Free scan, no signup.
    • Snyk - Free-tier developer security platform that scans your code, dependencies, and infrastructure-as-code for known vulnerabilities.
    • Mozilla HTTP Observatory - Free website scan that grades your security headers (CSP, HSTS, and more) and explains how to fix them.
    • agent-qa - Self-improving QA agent for web and mobile apps. Write natural-language tests, retain run memory, and catch UI regressions before shipping.
    • Check My Vibe - Free passive scan for AI-built websites that checks public security headers, exposed source maps, credential-shaped client strings, and common sensitive paths, plus a 36-point manual checklist.
    • CodeCordon - Deterministic security scanner for vibe-coded applications. Offers free no-account previews of authorized public GitHub repositories with file-and-line findings and remediation guidance; paid plans add CLI and GitHub Actions integration.
    • VibeAudit - Reads a whole GitHub repo and grades it for launch: missing auth, exposed keys, billing bugs, with file:line and a paste-ready fix prompt per finding. Free quick scan; private repos via GitHub App.
    • RowShield - Free read-only probe that checks a deployed Supabase app for tables and storage anonymous callers can read, the open-database mistake AI-built apps often ship; paid plans add scheduled RLS policy and drift checks.
    • Supercov - Coverage, security and code quality for coding agents.
    • VibeRaven - MIT-licensed local CLI and browser studio (`npx -y viberaven`) that checks an AI-built repo for auth, RLS, webhook, and deploy gaps before launch, exits non-zero on blockers, and writes the findings to `.viberaven/` for the coding agent to fix.

  • What is Vibe Coding

    • Andrej Karpathy on X - "There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. (.) I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works".
    • Agent Shadow Brain - Self-evolving AI coding intelligence with infinite memory (TurboQuant), genetic algorithm self-evolution, predictive bug detection, PageRank knowledge graphs, swarm intelligence, and adversarial defense.
    • Omni Skills Forge - 50,000+ curated AI agent skills for Claude Code, Cursor, Copilot, Windsurf, Cline. Visual dashboard, one-click install, skill doctor, auto-update.
Programming Languages
TypeScript 17 Rust 6 Python 4 Swift 4 C# 2 Go 2 Vue 1 Shell 1 JavaScript 1 Lua 1
Categories
Documentation for AI Coding 26 Command Line Tools 25 Browser-based Tools 20 Desktop Apps 18 Security & Pre-Deploy Checks 10 News and Social Media 9 Mobile-first Tools 6 Plugins and Extensions 5 What is Vibe Coding 3 IDEs and Code Editors 3 Contents <!-- omit in toc --> 1
Sub Categories
Keywords
ai-agents 17 claude-code 17 developer-tools 16 llm 14 codex 13 ai 10 openai 8 mcp 8 claude 8 mcp-server 5 macos 5 anthropic 5 cli 5 vibe-coding 5 ai-coding 5 ai-tools 4 opencode 4 typescript 4 gemini 4 coding-agent 4 chatgpt 4 prompt-engineering 3 swiftui 3 ai-agent 3 codex-cli 3 agents 3 cursor 3 grok 3 productivity 3 openclaw 3 local-first 3 terminal 3 react 3 macos-app 3 gemini-cli 2 automation 2 desktop-app 2 ollama 2 rust 2 self-hosted 2 obsidian 2 autonomous-agents 2 multi-agent 2 claude-skills 2 agentic 2 design-system 2 openai-codex 2 gpt 2 coding-agents 2 python 2