Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Building a Multi-Agent AI System with LangGraph and LangSmith
| Date | Stars |
|---|---|
| 2026-07-31 | 366 |
| 2026-08-06 | 369 |
Today
+3 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- omit in toc --> # Multi-Agent AI System This project is built following on top of the comprehensive guide from [LangChain](https://github.com/langchain-ai) official notebook documentation. [](https://www.python.org/downloads/release/python-3100/) [](https://langchain-ai.github.io/langgraph/) [](https://www.langchain.com/langsmith) [](https://www.together.ai/) [](https://openai.com/) [](https://www.sqlite.org/) [](https://medium.com/@fareedkhandev/building-a-multi-agent-ai-system-with-langgraph-and-langsmith-6cb70487cd81) It is now becoming a trend that a powerful AI agent gets created by combining several smaller subagents. But this also brings challenges like reducing hallucinations, managing the conversation flow, keeping an eye on how the agent works during testing, allowing human in the loop, and evaluating its performance. You need to do a lot of trial and error. In this blog, we will start by creating two simple subagents, then build a multi-agent system using a supervisor approach. Along the way, we will cover the basics, the challenges you might face when creating complex AI agentic architecture, and how to evaluate and improve them. We will use tools like `LangGraph` and `LangSmith` to help us with this process. <!-- omit in toc --> ## Getting Started The repository tree looks like this: ``` Multi-Agent-AI-System/ ├── .env # Environment variables for API keys ├── README.md # Project documentation ├── requirements.txt # Python dependencies ├── multi_agent.ipynb # Jupyter notebook for the multi-agent AI system ├── utils.py # Utility functions for the project └── LICENSE # Project license information (MIT License) ``` Make sure you have `Python 3.10+` installed on your system, as this project requires it. You can install the required dependencies using pip: ```bash # Clone the Multi-Agent AI System repository from GitHub git clone https://github.com/FareedKhan-dev/Multi-Agent-AI-System.git # Navigate into the project directory cd Multi-Agent-AI-System # Install all required Python dependencies from requirements.txt pip install -r requirements.txt ``` --- <!-- omit in toc --> ## Table of Contents - [Setting up the Environment](#setting-up-the-environment) - [Purpose of LangSmith](#purpose-of-langsmith) - [Choosing our Dataset](#choosing-our-dataset) - [Short-Term and Long-Term Memory](#short-term-and-long-term-memory) - [Our Multi-Agent Architecture](#our-multi-agent-architecture) - [Catalog Information Sub-agent](#catalog-information-sub-agent) - [Defining State, Tools and Nodes](#defining-state-tools-and-nodes) - [Testing First Sub-agent](#testing-first-sub-agent) - [Invoice Information Sub-agent Using Pre-built](#invoice-information-sub-agent-using-pre-built) - [Testing Second Sub-agent](#testing-second-sub-agent) - [Creating Multi-Agent Using Supervisor](#creating-multi-agent-using-supervisor) - [Testing our Multi-agent Architecture](#testing-our-multi-agent-architecture) - [Adding Human-in-the-Loop](#adding-human-in-the-loop) - [Adding Long-Term Memory](#adding-long-term-memory) - [Testing our Long-term Memory Multi-agent](#testing-our-long-term-memory-multi-agent) - [Evaluating our Multi-AI Agent](#evaluating-our-multi-ai-agent) - [Swarm vs Supervisor](#swarm-vs-supervisor) --- ## Setting up the Environment So, LangChain, LangGraph all these modules form an entire architecture. If I import all the libraries at once, it will definitely create confusion. So we will only import
Excerpt of 90,678 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d1a897b70203fd6d, topic:ai-agents, topic:multi-agent-systems, topic:langgraph