datawhalechina/easy-vibe

💻 vibe coding 101|The first course for AI-native product builders.

View on GitHub ↗Jump to charts ↓Open shareable report →

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 2 hours ago
Added to GitGenius on May 20th, 2026
Created on December 28th, 2025
Open Issues & Pull Requests: 19 (+0)
GitHub issues: Enabled
Number of forks: 1,876
Total Stargazers: 19,650 (+0)
Total Subscribers: 69 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 21.7 hours
Mean response time: 21.5 days
90th percentile: 68.0 days
Tracked items: 57

How this project is maintained

About 7% of issues opened in the past year have never received a reply. 85% of issues opened in the past year have been closed, leaving a working backlog. Three people close 90% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 10
New in 7 days: 1
Closed in 7 days: 1
Avg open age: 55 days
Stale 30+ days: 9
Stale 90+ days: 2

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Easy-vibe is a course for learning AI-native product development by building real applications.

The project addresses the gap between learning AI concepts and shipping functional products. It teaches vibe coding—a methodology for rapid AI product development—by guiding learners through hands-on projects that combine AI capabilities with practical implementation. The course emphasizes learning through building rather than theory alone, helping developers understand how to integrate large language models and AI agents into working applications.

The course suits developers who want to move beyond tutorials into actual product creation, particularly those new to AI development who need structured guidance on integrating models like GPT, Gemini, and DeepSeek into applications. It works well for builders interested in low-code or no-code approaches to AI product development, as well as those exploring agent-based workflows and model context protocol integration. The material is available in multiple languages, making it accessible to a global audience.

The project maintains responsive engagement with the community, with maintainers typically addressing new issues and pull requests within a day.