1. Conduid
  2. Developer Tools
  3. Nexlify
MCP server · Developer Tools

Nexlify

by · github.com/DeepakPant93/nexlify

A Retrieval-Augmented Generation (RAG)-based AI chatbot integrated with GitHub Copilot

Unclaimed MIT last commit a year ago devtools
InstallView source
49Fair

Scored 5 months ago · breakdown

About Nexlify

Nexlify is an MCP server published by DeepakPant93 in the Developer Tools category: a Retrieval-Augmented Generation (RAG)-based AI chatbot integrated with GitHub Copilot.

The repository has 3 stars and 0 forks, with the last commit a year ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/DeepakPant93/nexlify

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Nexlify

Powered by Claude · Grounded in docs

I know everything about Nexlify. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 7 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

Nexlify - A RAG-based AI chatbot integrated with GitHub Copilot

A Retrieval-Augmented Generation (RAG) AI chatbot using CrewAI, FastAPI, and vector database integration

Overview

Nexlify is an AI-powered chatbot that enhances code development by integrating Retrieval-Augmented Generation (RAG) with GitHub Copilot. It processes data into a vector database, uses AI agents for querying internal documents and the internet, and connects to AI clients like GitHub Copilot or ChatGPT via the MCP server. Built with modern Python frameworks, it streamlines data ingestion, semantic search, and agentic workflows for developers.

This repository contains three projects:

  1. data-ingestion-server For data ingestion into the vector database.
  2. nexlify-ai-agentics-server For the Agentic AI server, which queries the vector database using the data ingestion service and browses the internet.
  3. nexlify-mcp-server The MCP server to connect your AI client, such as GitHub Copilot or ChatGPT, to the AI server.

For more in-depth information on each component, please consult their individual README files located in the directories linked above. To explore Nexlify further, check out the Nexlify Docs.

For a complete overview of the infrastructure setup, including AWS and Azure configurations, refer to the blueprint directory.

Features

  • RAG-based querying: Retrieves and generates responses from vectorized data using embeddings and Qdrant database.
  • AI agent orchestration: Employs CrewAI agents for parallel tasks like vector DB search and internet browsing.
  • Data ingestion: Supports uploading and processing files (PDF, HTML, etc.) into a vector database with authentication.
  • Copilot integration: MCP server enables seamless connection to GitHub Copilot for enhanced code assistance.
  • Scalable infrastructure: Uses Docker for containerization, Terraform for AWS provisioning, and GitHub Actions for CI/CD.
  • Semantic search: Performs efficient searches on whitelisted endpoints and internal data sources.

Tech Stack

  • Python: Core programming language.
  • FastAPI: For building high-performance API microservices.
  • CrewAI: Agent-based framework for task orchestration and automation.
  • Google Gemini: For generating embeddings and LLM interactions.
  • Qdrant: Vector database for storing and querying embeddings.
  • Docker: Containerization for local and production deployment.
  • Terraform: Infrastructure as code for AWS resources.
  • GitHub Actions: CI/CD pipelines for automated builds and deployments.
  • Additional libraries: PyPDF2 for PDF processing, Pandas for data manipulation, Pytest for testing.

Backend Configuration

Prerequisites

  1. Install Docker and Docker Compose for local development.
  2. Ensure Python 3.10+ is installed.
  3. Clone the repository:
git clone https://github.com/DeepakPant93/nexlify.git
cd nexlify

Running the Servers

To start the services locally using Docker Compose:

docker-compose up --build

Future Enhancements

  • Support for additional file formats and data sources.
  • Integration with more AI clients beyond Copilot and ChatGPT.
  • Enhanced security features like advanced authentication and encryption.
  • UI dashboard for monitoring and managing data ingestion.

License

MIT License

Contributors

Acknowledgements

  • CrewAI documentation for agent orchestration.
  • Google Gemini and Qdrant for embedding and vector database technologies.
  • Terraform and Docker communities for infrastructure tools.

Contact

For any queries, reach out at deepak.93p@gmail.com.

Support

If you like this project and want to support, give a ⭐ to the repo.

Thank you so much ❤️.

Project URL: https://github.com/DeepakPant93/nexlify

README fetched from the repository 7 days ago. The original is authoritative.

Questions

About Nexlify

How do I install Nexlify?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Nexlify safe to use with an AI agent?

Its trust score is 49 out of 100 (fair). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Nexlify still maintained?

The last commit was a year ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.