Leverages Hugging Face MTEB leaderboard for embedding model selection and evaluation in the GraphRAG pipeline.
Built on LangChain framework for agent orchestration, tool integration, and LLM interaction management.
Uses LangGraph for implementing agent workflow patterns including ReAct and TS-ReAct based lifeline recovery agents.
Supports OpenAI models (GPT-4o, GPT-4, GPT-3.5 Turbo) as backbone LLMs for powering agent-based lifeline recovery tasks.
Utilizes PyTorch Geometric for graph neural network operations in the GraphRAG indexing and retrieval pipeline.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LNR-server-01-input-data-processingprocess the uploaded CSV file for LNR analysis"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π£ Important Notice
β οΈ As the paper is under review, all contents in this repository are currently not permitted for reuse by anyone until this announcement is removed. Thank you for your understanding! π
1. Overview & Objectives
This repository contains the complete implementation, experimental data, and supplementary results for the paper ΓΓΓ developed by XXX University in China, and .
Pending publication, the code is shared under a restrictive license. Once the paper is accepted, the repository will transition to a MIT license. Please contact the corresponding author for any inquiries regarding academic use during the review period.
2. Videos of agents operation
2.1 Operation of the developed prototype
βββ A demonstration of using the developed prototype to operate the TCG-TE LNR agents using graph-guided MCP tools
The full video could be found here
βββ A demonstration of using the developed prototype to integrate a new MCP server to TCG-TE LNR agents
The full video could be found here
2.2 Operation of agents based on NPG-TE pattern
βββ A snippet of the operation of NPG-TE agent with discrete MCP tools driven by GPT-5.
βββ A screenshot of Agent's response
The full video can be found here
βββ A snippet of the operation of NPG-TE agents with discrete MCP tools driven by GPT-4o.
βββ A screenshot of Agent's response
The full video can be found here
2.3 Operation of agents based on TCG-TE pattern
βββ A snippet of the operation of TCG-TE agents with graph-guided MCP tools driven by Claude sonnet 3.7.
The full video can be found here
βββ A snippet of the operation of TCG-TE agents with graph-guided MCP tools driven by GPT-4.1.
βββ A screenshot of Agent's response
The full video can be found here
3. Repository Structure
4. Acknowledgments
This work heavily relies on excellent open-source projects, including but not limited to:
LangGraph & LangChain
Hugging Face MTEB leaderboard
NetworkX, PyTorch Geometric, and numerous LLM providers (OpenAI, Anthropic, Qwen, Llama, etc.)
We are deeply grateful to all contributors of these foundational work.