Vibe Vibe – AI Coding for Everyone
The first systematic open-source Vibe Coding tutorial, taking you from zero to full-stack with natural language and AI.
- Source repo
- datawhalechina/vibe-vibe
- Stars
- ★ 6.2k
- Last updated
- 5mo ago
- Primary language
- Dockerfile
- FA score
- 22/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- Absolute beginners with zero coding background who want to build their first web app using AI.
- Not a fit if
- Learners who need fully offline access without internet
- Readers expecting the complete advanced section, as some chapters are not yet released
- Teams planning to reuse the content commercially
- Source review
- 22/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
Vibe Vibe is a systematic tutorial for AI-assisted programming, created by the Datawhale community and aimed at learners with no prior coding experience. It embodies Andrej Karpathy's Vibe Coding philosophy, shifting from traditional coding to conversational creation with AI. The repository is organized into four major sections: Basics (mindset, techniques, hands-on), Advanced (16 chapters on full-stack delivery), Practice (project-based exercises by audience), and Curated Articles (selected resources). It offers an online reading site at www.vibevibe.cn and supports self-hosting via Docker. The content is written in Markdown, covering the entire journey from first ideas to production deployment, using technologies like Next.js, React, TypeScript, and more. The tutorial is licensed under CC BY-NC-SA 4.0.
The repository provides a structured learning path that guides users to interact with AI assistants (such as Cursor, Windsurf, Bolt.new, Replit) through natural language, iteratively building a product from idea to launch. The Basics section teaches prompt engineering, MVP thinking, and PRD writing, with a hands-on round-by-round development of a personal tool. The Advanced section covers 16 chapters on environment setup, PRD-driven development, UI/UX, databases, Git, CI/CD, and deployment. The Practice section offers projects tailored to different audiences (liberal arts, STEM, professionals) and includes advanced AI Agent development (RAG, vector databases, MCP). The repo includes a Dockerfile and docker-compose.yml to easily spin up the tutorial site.
- Absolute beginners with zero coding background who want to build their first web app using AI.
- People who have used ChatGPT but never completed a project, seeking a systematic workflow for AI-assisted development.
- Developers with some coding experience who want to learn Vibe Coding methodology and advance to full-stack skills.
- Entrepreneurs or product managers aiming to quickly prototype ideas and build an MVP.
- Students in humanities or business fields who want to create content or data visualization projects using AI.
- Teams or individuals needing to deploy the tutorial site locally or on an intranet.
How do you install or deploy this agent?
- Clone the repository:
git clone https://github.com/datawhalechina/vibe-vibe.git - Ensure Docker and docker-compose are installed.
- Run
docker compose up -d --buildin the repository root. - Access http://localhost:1024 to view the tutorial.
How do you use this agent?
After installation, open http://localhost:1024 in your browser to start reading. Choose a starting point based on your background (e.g., absolute beginners start at Chapter 1 of the Basics), follow the chapters in order, and practice along with the examples. For detailed deployment options and offline considerations, refer to docs/deployment/index.md.
What are this agent's strengths and limitations?
- Structured curriculum: four sections provide a clear progression from beginner to advanced.
- Zero-basis friendly: no English or math prerequisites emphasized; focuses on natural language interaction.
- Docker one-click deployment enables local and offline usage.
- Project-based learning with tangible outcomes (e.g., full-stack apps, AI agents).
- Backed by Datawhale community with active contribution and feedback channels.
- The tutorial itself is not an AI model; users must bring their own AI tools (e.g., Cursor, ChatGPT) to practice.
- Docker deployment requires basic Docker knowledge, which might be a barrier for absolute beginners.
- Some recommended tools (e.g., Bolt.new) may be geo-restricted or require a VPN in some regions.
- Some advanced chapters may be incomplete or behind a future release.
- Non-commercial license (CC BY-NC-SA) limits commercial use.
How does this agent compare with similar options?
The tutorial compares various AI coding tools (Cursor, Windsurf, Bolt.new, Replit) to help users choose.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Vibe Vibe – AI Coding for Everyone This agent | 22 · Major gaps | Web appFree | ★ 6.2k | 5mo ago | Dockerfile | — |
| Full-Stack AI Agent Template | 74 · Some gaps | CLIFree + model costs | ★ 2k | 12d ago | Python | OpenAI API · Claude API |
| AI Agents From Scratch | 28 · Major gaps | CLIFree | ★ 4.9k | 2mo ago | JavaScript | — |
| Vibe Coding Chinese Guide | 38 · Major gaps | CLIFree | ★ 18k | today | Makefile | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows this is a documentation/tutorial project with no code execution or permission requests. Therefore, least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, and source attribution are not applicable, scoring 0. For source attribution, maintainers are listed with names and roles, but identity is unverified, and no contributor agreement or source verification is provided, so no score.
Self-consistency: README and package.json are mostly consistent, but package.json declares ISC license while README declares CC BY-NC-SA 4.0, an inconsistency, so score 1. Dependency availability: dependency list is complete, but no lock file or integrity checks are provided, so score 1. Failure messages: no error handling or failure message documentation, score 0.
Audience and scenarios: README clearly lists target audiences and best starting points, score 2. Capability boundaries: project scope is described as a tutorial, but no explicit statement of what is not included, score 1. Trigger precision: no trigger mechanisms defined, score 0. Environment fit: Docker deployment option provided, but no system requirements or compatibility notes, score 1.
Information architecture: README provides clear project structure and navigation, score 2. Install notes: Docker deployment command provided, but no local development installation steps, score 1. Naming stability: project name and version exist, but no naming conventions, score 1. Examples and FAQ: learning paths and cases provided, but no FAQ, score 1. Known limitations: marked as Alpha preview, but no detailed limitations, score 1. License: README declares CC BY-NC-SA 4.0, but package.json says ISC, inconsistent, score 1. Versioning and changelog: version number exists, but no changelog, score 1. Maintenance responsibility: maintainers listed, but no maintenance policy, score 1.
Output usability: tutorial content may be useful, but no actual output examples, score 1. Marginal value: as a tutorial, may provide value, but no comparison with other resources, score 1. Cost-benefit: free and open source, but no assessment of time cost, score 1.
Claim traceability: claims in README lack citations or evidence, score 1. Cross-source corroboration: no external verification, score 0. Fact-inference separation: content distinguishes facts and opinions, but not explicitly labeled, score 1.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- License inconsistency: README declares CC BY-NC-SA 4.0, but package.json says ISC, needs clarification.
- Project is marked as Alpha preview, but known limitations are not detailed; users should use with caution.
- No dependency lock file provided, posing supply chain risk.
- No clear installation steps, only Docker deployment, may not suit all users.