datawhalechina/hello-agents

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 14 minutes ago
Added to GitGenius on December 8th, 2025
Created on September 7th, 2025
Open Issues & Pull Requests: 173 (+0)
Number of forks: 9,257
Total Stargazers: 74,512 (+19)
Total Subscribers: 216 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 4.9 hours
Mean response time: 5.8 days
90th percentile: 11.9 days
Tracked items: 288

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 79% of tracked open issues have had no activity in three months, so the open count overstates what is actively being worked. Only 14% of issues opened in the past year have been closed. Three people close 80% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 63
New in 7 days: 4
Closed in 7 days: 1
Avg open age: 53 days
Stale 30+ days: 55
Stale 90+ days: 50

Recent activity

Opened in 7 days: 3
Closed in 7 days: 1
Comments in 7 days: 1
Events in 7 days: 5

Top labels

  • documentation (288)

Detailed Description

Hello-Agents is a tutorial and learning resource that teaches the principles and practical implementation of building AI-native agents from foundational concepts to real-world applications.

The project addresses the scarcity of systematic, practice-focused agent development education by providing comprehensive guidance on constructing AI-driven agents rather than workflow-automation tools. It distinguishes between two approaches to agent building: software-engineering-focused platforms like Dify and Coze that treat language models as data processing backends, and AI-native agents that are fundamentally driven by artificial intelligence. The tutorial works by moving beyond framework abstractions to teach core agent principles, classical design patterns, and multi-agent system architecture through hands-on implementation.

The project suits developers and practitioners who want to transition from being language model users to becoming agent system builders. It is designed for those seeking to understand agent internals rather than simply using existing agent platforms, and it emphasizes learning through practical construction. The material covers both theoretical foundations and implementation details needed to build custom agent applications.

The project maintains active engagement with its user base, with most reported issues coming from external adopters rather than the core team. Maintainers typically respond to new issues and pull requests within a day. Documentation work dominates the issue tracker, reflecting the project's focus as an educational resource.