Best of Vibe Coding
Starters to fork, agents that write the code, the skills and MCP servers that make them better, and the stack you ship on. No fluff, and paid never moves a rank.
167 projects in 19 categories, from GitHub data of 11 October 2026. Rankings update twice a day.
- Every project fact-checked on GitHub before it is listed
- Every entry has strengths and weaknesses; starters say what is wired in
- Demo links so you can see it running first
Top 10 right now
Best of Vibe Coding is a ranked list of 167 open-source projects for building software with AI: starter templates and SaaS boilerplates, coding agents and assistants, editors, skills and plugins, MCP servers for developers, code review, design to code, and the backends and hosting you ship on. Each entry has strengths, weaknesses and a score from public GitHub signals.
| Rank | Project | Adoption | Freshness | Maintenance | Easy to run | Agent-ready | Score |
|---|---|---|---|---|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 98 | 100 | 93 | – | 70 | 94 out of 100 |
| 2 | eccSkills, agents, hooks and rules that add a workflow to coding agents | 96 | 100 | 92 | – | 70 | 93 out of 100 |
| 3 | superpowersSkill library that enforces a plan-then-TDD workflow in coding agents | 100 | 100 | 84 | – | 30 | 89 out of 100 |
| #4 | ponytailPrompt skill that makes coding agents write less, safer code | 93 | 100 | 96 | – | 30 | 89 out of 100 |
| #5 | cavemanProxy and skill that cut token use in coding agents | 79 | 100 | 97 | – | 70 | 89 out of 100 |
| #6 | ui-ux-pro-max-skillDesign-system skill for AI coding assistants, with searchable UI styles | 84 | 100 | 92 | – | 55 | 88 out of 100 |
| #7 | spec-kitCLI and agent skills for spec-driven development, bug fixing and idea assessment | 88 | 100 | 95 | – | 30 | 87 out of 100 |
| #8 | agent-skillsMarkdown engineering skills and slash commands for AI coding agents | 77 | 100 | 87 | – | 70 | 86 out of 100 |
| #9 | impeccableDesign skill and linter for AI coding agents' frontend output | 64 | 100 | 94 | – | 85 | 85 out of 100 |
| #10 | dokploySelf-hosted PaaS for deploying apps and databases on your own servers | 85 | 100 | 84 | 83 | 55 | 85 out of 100 |
Momentum, Verified build, Docs and Privacy are not measured yet; their weight goes to the signals shown. A dash means the signal is not scored for that kind of project. Hover a number for its rating in words.
Pick by what you need
- Ship a chat app this weekendChat apps
- RAG over my data, with citationsRAG and search
- An agent backend I can extendAgent backends
- A voice agent that talks backVoice and realtime
- SaaS with auth and billing, ready for AISaaS boilerplates
- An agent that writes the code for meCoding agents and assistants
- Make Claude Code or Cursor betterSkills, plugins and rules
- Give my coding agent docs, a browser, GitHubMCP servers for developers
- Turn a screenshot into a working pageDesign to code
- Auth, database and storage in oneBackends and databases
- Deploy it on my own serverDeploy and hosting
Chat apps
Chat interfaces and single-feature text apps you fork as the base of a conversational product.
| Rank | Project | Score |
|---|---|---|
| 1 | langchain-nextjs-templateNext.js routes for LangChain.js chat, agents, structured output and RAG | 63 out of 100 |
| 2 | chatbotNext.js chat template with Auth.js, Postgres history and AI Gateway models | 54 out of 100 |
| 3 | chatNuxt UI chat template with GitHub login, SQLite history and AI Gateway | 52 out of 100 |
| #4 | gemini-chatbotNext.js chatbot template defaulting to Gemini with NextAuth and Postgres | 50 out of 100 |
| #5 | claude-quickstartsIndependent Claude API starter projects, one folder per pattern | 48 out of 100 |
RAG and search
Retrieval over your own documents or data, answer engines, and natural-language-to-SQL starters.
| Rank | Project | Score |
|---|---|---|
| 1 | azure-search-openai-demoAzure RAG chat reference on AI Search and Azure OpenAI | 56 out of 100 |
| 2 | rag-postgres-openai-pythonRAG over Postgres table rows with hybrid search and SQL filters | 51 out of 100 |
| 3 | llm-appPathway RAG pipeline templates that re-index live data sources | 48 out of 100 |
| #4 | chat-langchainLangChain docs assistant as a Managed Deep Agent with Next.js UI | 45 out of 100 |
| #5 | chat-with-your-data-solution-acceleratorAzure RAG chat app that answers from your documents with citations | 44 out of 100 |
Agent backends
Agent templates and scaffolds (LangGraph, ADK, OpenAI Agents SDK, Cloudflare Agents, eve) meant to be extended.
| Rank | Project | Score |
|---|---|---|
| 1 | eve-software-factory-templateeve pipeline that turns GitHub or Linear issues into reviewed draft PRs | 65 out of 100 |
| 2 | marketing-team-eve-templateeve lead agent delegating to five marketing specialists with approval gates | 59 out of 100 |
| 3 | personal-agent-templateeve and Nuxt personal agent with Slack, GitHub, Linear and per-user memory | 57 out of 100 |
| #4 | adk-recipesRunnable Agent Development Kit recipes, from single patterns to deployable agents | 53 out of 100 |
| #5 | ai-townGenerative-agents town simulation on Convex with Ollama by default | 52 out of 100 |
Agent UI and generative UI
Frontends that render agent steps, tool calls, approvals or model-generated components.
| Rank | Project | Score |
|---|---|---|
| 1 | agent-chat-uiNext.js chat frontend for any LangGraph server with interrupts and artifacts | 45 out of 100 |
| 2 | OpenGenerativeUIChat interface that answers with 3D models, charts, calculators and maps | 45 out of 100 |
| 3 | agent-uiNext.js chat frontend for Agno AgentOS with tool calls and reasoning | 40 out of 100 |
| #4 | stockbot-on-groqGroq chatbot answering with TradingView widgets via AI SDK generative UI | 24 out of 100 |
| #5 | assistant-ui-stockbrokerassistant-ui frontend and LangGraph.js stockbroker agent with approval steps | 13 out of 100 |
Voice and realtime
Voice agents, realtime speech-to-speech apps and their web, phone and native clients.
| Rank | Project | Score |
|---|---|---|
| 1 | agent-starter-reactNext.js voice assistant frontend for LiveKit Agents | 51 out of 100 |
| 2 | agent-starter-pythonPython voice agent on LiveKit Agents with turn detection and simulations | 50 out of 100 |
| 3 | agent-starter-nodeNode.js voice agent on LiveKit Agents with turn detection and simulations | 50 out of 100 |
| #4 | voice-ui-kitReact components and templates for Pipecat voice agent frontends | 45 out of 100 |
| #5 | pipecat-examplesRunnable Pipecat voice agent examples for phone, web and deployment | 41 out of 100 |
MCP servers and chat-host apps
Templates for building MCP servers and apps that run inside chat hosts such as ChatGPT.
| Rank | Project | Score |
|---|---|---|
| 1 | mcp-typescript-templateExpress and Effect template for a stateless remote MCP server | 60 out of 100 |
| 2 | template-mcp-serverPython FastMCP server template with OAuth, OpenShift manifests and CI | 47 out of 100 |
| 3 | mcp-for-next.jsStateless MCP server route for a Next.js App Router app | 41 out of 100 |
| #4 | openai-apps-sdk-examplesExample MCP servers and widgets for ChatGPT apps on the Apps SDK | 32 out of 100 |
| #5 | mcp-forgeGo MCP server template with OAuth discovery and JWT validation | 24 out of 100 |
SaaS boilerplates
Product boilerplates with auth, billing and a database wired in, with AI features built in or ready to add.
| Rank | Project | Score |
|---|---|---|
| 1 | ant-design-proReact admin dashboard template built on Ant Design 6 and Umi Max | 68 out of 100 |
| 2 | velobase-harnessNext.js AI SaaS base with credits, usage billing, workers and anti-abuse | 56 out of 100 |
| 3 | hackathon-starterNode.js and Express boilerplate with auth, API examples and AI samples | 52 out of 100 |
| #4 | open-saasWasp SaaS template with auth, three payment providers, OpenAI demo app | 47 out of 100 |
| #5 | AI-Fullstack-SaaS-BoilerplateFastify, tRPC and React SaaS base with Better Auth and SSE chat | 36 out of 100 |
App builder starters
Prompt-to-app builders and platforms that run coding agents in sandboxes.
| Rank | Project | Score |
|---|---|---|
| 1 | ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL | 77 out of 100 |
| 2 | jeecgbootJava low-code platform with code generator and built-in AI app builder | 63 out of 100 |
| 3 | llamacoderOpen-source Claude Artifacts clone generating React apps with Llama | 48 out of 100 |
| #4 | open-agentsReference app for background coding agents on Vercel sandboxes | 45 out of 100 |
| #5 | vibesdkSelf-hosted prompt-to-app platform on Cloudflare Workers and Durable Objects | 44 out of 100 |
AI editors and workflow canvases
Rich-text editors with AI commands and node-based canvases for chaining model calls.
| Rank | Project | Score |
|---|---|---|
| 1 | plate-playground-templateNext.js rich-text editor template on Plate with AI commands | 54 out of 100 |
| 2 | editorNotion-style Nuxt editor with AI completions and optional collaboration | 50 out of 100 |
| 3 | workflow-builder-templateVisual AI workflow builder on Workflow DevKit with real integrations | 36 out of 100 |
| #4 | tersaNode canvas for chaining text, image and video models via AI Gateway | 25 out of 100 |
Cloud reference architectures
Vendor reference apps and infrastructure-as-code for running AI apps on Azure or Google Cloud.
| Rank | Project | Score |
|---|---|---|
| 1 | agent-landing-zoneAzure infrastructure templates for deploying enterprise agent apps on Microsoft Foundry | 64 out of 100 |
| 2 | fullstack-solution-template-for-agentcoreReact frontend and AgentCore backend starter, deployed to AWS with CDK or Terraform | 44 out of 100 |
| 3 | azurechatPrivate enterprise chat on Azure OpenAI with document chat and personas | 42 out of 100 |
| #4 | openai-chat-app-quickstartMinimal Quart chat app on Azure OpenAI with managed identity | 40 out of 100 |
| #5 | get-started-with-ai-agentsAzure azd template for a Foundry agent chat app with file search | 33 out of 100 |
AI API backends
Backend service templates (FastAPI, Express, Hono) that expose models or agents over an API.
| Rank | Project | Score |
|---|---|---|
| 1 | agent-service-toolkitLangGraph agents served by FastAPI with a Streamlit chat client | 70 out of 100 |
| 2 | fastapi-langgraph-agent-production-ready-templateFastAPI service for a LangGraph agent with auth, memory and tracing | 55 out of 100 |
| 3 | full-stack-ai-agent-templateProject generator for FastAPI and Next.js apps with agents and RAG | 55 out of 100 |
| #4 | generative-ai-project-templateuv workspace with FastAPI, NiceGUI, LiteLLM and Promptfoo evals | 51 out of 100 |
| #5 | nodejs-api-boilerplateExpress TypeScript CRUD API template with an LLM module generator | 31 out of 100 |
Mobile and browser extensions
Native, cross-platform mobile and browser-extension starters with AI features built in.
| Rank | Project | Score |
|---|---|---|
| 1 | react-native-aiExpo chat and image app with an Express proxy for multiple LLMs | 51 out of 100 |
| 2 | extroWXT and React browser extension starter with Supabase auth and AI | 37 out of 100 |
Coding agents and assistants
Agents and assistants that read your repo, write code and run commands: CLIs, IDE extensions and self-hosted servers.
| Rank | Project | Score |
|---|---|---|
| 1 | opencodeTerminal coding agent with build and plan modes | 77 out of 100 |
| 2 | orcaDesktop app that runs CLI coding agents in parallel git worktrees | 75 out of 100 |
| 3 | ArchonYAML workflow engine that runs coding agents in isolated worktrees | 73 out of 100 |
| #4 | codexOpenAI's terminal coding agent that runs locally | 71 out of 100 |
| #5 | oh-my-openagentTerminal coding agent that runs parallel sub-agents and keeps git-based memory | 70 out of 100 |
Skills, plugins and rules
Add-ons that make coding agents better: skills, plugins, rules, hooks and memory for Claude Code, Codex, Cursor and others.
| Rank | Project | Score |
|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 2 | eccSkills, agents, hooks and rules that add a workflow to coding agents | 93 out of 100 |
| 3 | superpowersSkill library that enforces a plan-then-TDD workflow in coding agents | 89 out of 100 |
| #4 | ponytailPrompt skill that makes coding agents write less, safer code | 89 out of 100 |
| #5 | cavemanProxy and skill that cut token use in coding agents | 89 out of 100 |
MCP servers for developers
MCP servers that give coding agents tools: docs lookup, browsers, GitHub, databases and code navigation.
| Rank | Project | Score |
|---|---|---|
| 1 | codegraphLocal code knowledge graph served to coding agents over MCP | 80 out of 100 |
| 2 | chrome-devtools-mcpMCP server that lets coding agents drive and debug a live Chrome | 64 out of 100 |
| 3 | codebase-memory-mcpMCP server that indexes codebases into a queryable knowledge graph | 62 out of 100 |
| #4 | context7Fetches current, version-specific library docs into coding agent prompts | 57 out of 100 |
| #5 | github-mcp-serverMCP server exposing GitHub repos, issues, PRs and Actions to AI tools | 54 out of 100 |
Code review and testing
AI tools that review pull requests, write tests or find bugs, run in your CI or on your machine.
| Rank | Project | Score |
|---|---|---|
| 1 | open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments | 73 out of 100 |
Design to code
Tools that turn screenshots, mockups or visual edits into working front-end code.
| Rank | Project | Score |
|---|---|---|
| 1 | screenshot-to-codeTurns screenshots and mockups into Tailwind, React or Vue code | 65 out of 100 |
| 2 | OnlookVisual editor that edits Next.js and Tailwind apps with AI | 47 out of 100 |
Backends and databases
Open-source backends you ship apps on: auth, database, storage and APIs in one, self-hosted or managed.
| Rank | Project | Score |
|---|---|---|
| 1 | supabasePostgres backend with auth, storage, realtime and edge functions | 73 out of 100 |
| 2 | graphql-engineGraphQL API layer over Postgres, MongoDB, ClickHouse and SQL Server | 55 out of 100 |
Deploy and hosting
Self-hosted platforms that deploy and run your apps from Git or Docker on your own servers.
Open-source alternatives to paid tools
The highest-scoring open-source projects in the category we compare each product in. A project marked "own claim" calls itself an alternative in its README.
Instead of Cursor
Compared in Coding agents and assistants- opencodeTerminal coding agent with build and plan modes77 out of 100
- orcaDesktop app that runs CLI coding agents in parallel git worktrees75 out of 100
- ArchonYAML workflow engine that runs coding agents in isolated worktrees73 out of 100
Instead of GitHub Copilot
Compared in Coding agents and assistants- opencodeTerminal coding agent with build and plan modes77 out of 100
- orcaDesktop app that runs CLI coding agents in parallel git worktrees75 out of 100
- 42 out of 100
Instead of Claude Code
Compared in Coding agents and assistants- opencodeTerminal coding agent with build and plan modes77 out of 100
- orcaDesktop app that runs CLI coding agents in parallel git worktrees75 out of 100
- ArchonYAML workflow engine that runs coding agents in isolated worktrees73 out of 100
Instead of Devin
Compared in Coding agents and assistants- opencodeTerminal coding agent with build and plan modes77 out of 100
- orcaDesktop app that runs CLI coding agents in parallel git worktrees75 out of 100
- ArchonYAML workflow engine that runs coding agents in isolated worktrees73 out of 100
Instead of Tabnine
Compared in Coding agents and assistants- opencodeTerminal coding agent with build and plan modes77 out of 100
- orcaDesktop app that runs CLI coding agents in parallel git worktrees75 out of 100
- ArchonYAML workflow engine that runs coding agents in isolated worktrees73 out of 100
Instead of Lovable
Compared in App builder starters and Design to code- ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL77 out of 100
- screenshot-to-codeTurns screenshots and mockups into Tailwind, React or Vue code65 out of 100
- 47 out of 100
Instead of v0
Compared in App builder starters and Design to code- ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL77 out of 100
- screenshot-to-codeTurns screenshots and mockups into Tailwind, React or Vue code65 out of 100
- 47 out of 100
Instead of Bolt.new
Compared in App builder starters- ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL77 out of 100
- jeecgbootJava low-code platform with code generator and built-in AI app builder63 out of 100
- 47 out of 100
Instead of Replit
Compared in App builder starters- ai-website-cloner-templateNext.js template with an agent skill that rebuilds a website from its URL77 out of 100
- jeecgbootJava low-code platform with code generator and built-in AI app builder63 out of 100
- 47 out of 100
Instead of CodeRabbit
Compared in Code review and testing- open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments73 out of 100
Instead of Firebase
Compared in Backends and databases- supabasePostgres backend with auth, storage, realtime and edge functions73 out of 100
- graphql-engineGraphQL API layer over Postgres, MongoDB, ClickHouse and SQL Server55 out of 100
Instead of Vercel
Compared in Deploy and hosting- dokploySelf-hosted PaaS for deploying apps and databases on your own servers85 out of 100
- dokkuSelf-hosted mini-Heroku PaaS that deploys apps with git push65 out of 100
Instead of Heroku
Compared in Deploy and hosting- dokploySelf-hosted PaaS for deploying apps and databases on your own servers85 out of 100
- dokkuSelf-hosted mini-Heroku PaaS that deploys apps with git push65 out of 100
Starters with safe defaults
8 of 102 starters pass all three checks: an env example file at the root, no .env file committed, and a sign-in library wired in package.json. A good start, not a security audit.
| Rank | Project | Score |
|---|---|---|
| 1 | personal-agent-templateeve and Nuxt personal agent with Slack, GitHub, Linear and per-user memory | 57 out of 100 |
| 2 | velobase-harnessNext.js AI SaaS base with credits, usage billing, workers and anti-abuse | 56 out of 100 |
| 3 | chatbotNext.js chat template with Auth.js, Postgres history and AI Gateway models | 54 out of 100 |
| #4 | hackathon-starterNode.js and Express boilerplate with auth, API examples and AI samples | 52 out of 100 |
| #5 | gemini-chatbotNext.js chatbot template defaulting to Gemini with NextAuth and Postgres | 50 out of 100 |
| #6 | SupabaseAuthWithSSRClaude chat on Next.js 16 with Supabase auth, pgvector RAG, cost dashboards | 39 out of 100 |
| #7 | zolaMulti-provider chat UI on Next.js with Ollama detection and BYOK | 33 out of 100 |
| #8 | next-ai-starterNext.js 14, tRPC and Prisma starter with LLM SDKs and agent checklists | 28 out of 100 |
How this list is ranked
Starters are templates and reference apps you clone and build on. 🛠️ Code with AI is what you build with. 🚀 Ship it is the stack you deploy on, AI or not. The score comes from public GitHub signals with published weights; see the methodology. Looking for AI apps, agents, models and the tools around them? See Best of Open-Source AI.