langmanus

langmanus

https://github.com/Darwin-lfl/langmanus?tab=readme-ov-file#usage

https://github.com/fanqingsong/langmanus

A community-driven AI automation framework that builds upon the incredible work of the open source community. Our goal is to combine language models with specialized tools for tasks like web search, crawling, and Python code execution, while giving back to the community that made this possible.

 

原始库追踪：

https://github.com/adcwa/langmanus/tree/main

https://github.com/LangManus-KeepGoing/LangManus-Web

https://github.com/jokyun/langmanus-web

声称集成前后端：

https://github.com/jetztlos/LangManus/blob/main/README_zh.md

 

Architecture

LangManus implements a hierarchical multi-agent system where a supervisor coordinates specialized agents to accomplish complex tasks:

The system consists of the following agents working together:

1. Coordinator - The entry point that handles initial interactions and routes tasks
2. Planner - Analyzes tasks and creates execution strategies
3. Supervisor - Oversees and manages the execution of other agents
4. Researcher - Gathers and analyzes information
5. Coder - Handles code generation and modifications
6. Browser - Performs web browsing and information retrieval
7. Reporter - Generates reports and summaries of the workflow results

Features

Core Capabilities

• 🤖 LLM Integration
  • Support for open source models like Qwen
  • OpenAI-compatible API interface
  • Multi-tier LLM system for different task complexities

Tools and Integrations

• 🔍 Search and Retrieval
  • Web search via Tavily API
  • Neural search with Jina
  • Advanced content extraction

Development Features

• 🐍 Python Integration
  • Built-in Python REPL
  • Code execution environment
  • Package management with uv

Workflow Management

• 📊 Visualization and Control
  • Workflow graph visualization
  • Multi-agent orchestration
  • Task delegation and monitoring

Why LangManus?

We believe in the power of open source collaboration. This project wouldn't be possible without the amazing work of projects like:

• Qwen for their open source LLMs
• Tavily for search capabilities
• Jina for neural search technology
• And many other open source contributors

We're committed to giving back to the community and welcome contributions of all kinds - whether it's code, documentation, bug reports, or feature suggestions.

 

LangManus: A Guide With Demo Project

https://www.datacamp.com/tutorial/langmanus

https://aashidutt.github.io/LangManus_Guide

https://github.com/AashiDutt/LangManus-Demo/tree/main

此文尽管宣称使用langmanus框架，但是是现实上，没有使用langgraph。

 

 

所以基于langmanus框架给出真正的实现：

https://github.com/fanqingsong/LangManus-Demo?tab=readme-ov-file

## 🏗️ Architecture Philosophy

This project demonstrates the **correct way** to implement LangManus - as a **generic framework** with business logic separated into tools:

```

┌─────────────────────────────────────┐

│        Generic Framework            │

│  ┌─────────────────────────────┐    │

│  │    Generic Prompts          │    │  ← Business-Agnostic

│  │  • Coordinator              │    │

│  │  • Planner                  │    │

│  │  • Researcher               │    │

│  │  • Browser                  │    │

│  │  • Coder                    │    │

│  │  • Reporter                 │    │

│  └─────────────────────────────┘    │

│                │                    │

│        ┌───────▼──────┐             │

│        │ Tool Injection│             │  ← Dynamic Runtime Injection

│        └───────┬──────┘             │

└────────────────┼──────────────────────┘

                 │

┌────────────────▼──────────────────────┐

│        Business Tools                 │  ← Domain-Specific Logic

│  • GitHub API Tools                   │

│  • Analysis Tools                     │

│  • Custom Business Tools              │

└───────────────────────────────────────┘

```

## ✅ Key Design Principles

1. **Generic Framework**: Core agents use business-agnostic prompts

2. **Tool Injection**: Business logic is provided through tools at runtime

3. **Clean Separation**: Framework and business domains are completely separated

4. **Extensibility**: Easy to add new business domains without changing core code

5. **Reusability**: Same framework works for GitHub, finance, healthcare, etc.

## 🚀 Usage Examples

### Generic Analysis (No Business Tools)

```python

from src.main_app import LangManusAgent

# Generic agent - works with any domain

agent = LangManusAgent(

    task="Analyze the impact of artificial intelligence on society"

)

result = agent.run()

```