Habibullah5

Langgraph Multi Agent System

Name: Langgraph Multi Agent System
Author: Habibullah5

DevOps community

SOURCE https://github.com/Habibullah5/langgraph-multi-agent-system

Description

A modular multi-agent AI system built with LangGraph, Anthropic Claude, and LangSmith featuring sequential handoffs, central supervisor orchestration, and live tool execution (Web Search, REPL, Docker).

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

🤖 Multi-Agent AI System with LangGraph & LangSmith

A scalable, production-ready multi-agent framework built with **LangGraph**, **Anthropic Claude**, and **LangSmith** for deep observability, structured tool routing, and agent collaboration.

🚀 Key Features

**Central Supervisor Orchestrator (`supervisor_agent.py`):**
- Uses a central router agent to dynamically assign tasks to specialized sub-agents (Researcher and Coder/Math).
- Structured output schema enforces reliable delegation and task completion handoffs.
**Sequential Multi-Agent Pipeline (`multi_agent.py`):**
- Autonomous Researcher Agent searches real-time web sources.
- Executive Writer Agent synthesizes raw data into structured, actionable reports.
**Autonomous Travel Planner (`travel_agent.py`):**
- Dynamic travel itinerary generator with live budget calculations and destination lookups.
**Tool Integrations:**
- Live Search: Tavily API with DuckDuckGo fallback (ddgs).
- Code Execution: Safe mathematical evaluation and Python execution.
- Docker Integration: Local container monitoring via the Docker SDK.
**Full Observability & Tracing:**
- Native LangSmith telemetry capturing token counts, latency profiles, and end-to-end execution graphs.