Hello Agents

Active
GitHub Python NOASSERTION

Description

A comprehensive tutorial on AI agent principles and practice, systematically covering core concepts, framework usage and hands-on projects.

Key Features

  • Systematic agent tutorial — complete learning path from agent definitions to multi-agent applications
  • Classic paradigm implementations — hands-on ReAct, Plan-and-Solve, and Reflection patterns
  • Low-code platform tutorials — practical guides for Coze, Dify, and n8n platforms
  • Framework development — applications of AutoGen, AgentScope, LangGraph and other major frameworks
  • Custom framework HelloAgents — build an agent framework from scratch using OpenAI native API
  • Project-driven learning — smart travel assistant, deep research agent, cyber town hands-on projects

Use Cases

💡 Systematic introductory tutorial for learning AI agent fundamentals and core paradigms
💡 Quickly building agent applications using low-code platforms
💡 Developing multi-agent collaboration systems with mainstream agent frameworks
💡 Building custom agent frameworks from scratch to deeply understand underlying mechanisms
💡 Learning advanced topics including context engineering, RAG, and memory systems

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (73.2k stars)
  • Responsive to issues, low backlog

⚠️ Limitations

  • No clear open-source license

Categories

Quick Start

git clone https://github.com/datawhalechina/hello-agents.git
cd hello-agents
# Online reading: https://hello-agents.datawhale.cc
# Local reading: Open chapter files in docs/ directory with Jupyter Notebook

Related Projects

Langchain-Chatchat

38.5k · Python
Stale B

A local knowledge base RAG and Agent application platform built on Langchain with support for ChatGLM, Qwen, Llama and other LLMs, offering conversation, knowledge base management, and agent capabilities.

ragllmpython +3
  • · Local knowledge base QA — Document loading, text splitting, vectorization and semantic retrieval via Langchain with BM25+KNN hybrid search
  • · Multi-framework model inference — Supports Xinference, Ollama, FastChat, LocalAI for GLM-4, Qwen2, Llama3 and more
  • · Agent tool calling — Optimized for ChatGLM3/Qwen with auto tool selection, single tool parameter parsing, and multimodal image chat

RAGapp

4.4k · TypeScript
Stale C

The easiest way to use Agentic RAG in any enterprise. Provides out-of-the-box retrieval-augmented generation capabilities with Docker-based deployment for simplified enterprise RAG application building and management.

ragagentpython +2
  • · Docker one-command deployment with Admin UI for visual RAG configuration
  • · Agentic RAG pipeline built on LlamaIndex with OpenAI, Gemini, and Ollama support
  • · Pre-built Chat UI and REST API endpoints ready for integration

MemAgent

1.1k · Python
Stale B

A MemAgent framework that can extrapolate to 3.5M context tokens, along with a training framework for RL training of any agent workflow.

memoryagentrag +2
  • · Ultra-Long Context Processing: Extrapolate from 8K training context to 3.5M tokens with performance loss under 5%
  • · Reinforcement Learning Driven: Trained with RLVR (Reinforcement Learning from Verifiable Rewards), extends DAPO algorithm for end-to-end multi-turn conversation optimization
  • · Linear Time Complexity: Breaks through computational bottlenecks in long-text processing with linear resource scaling