Skip to main content

Introduction

A modern template for agentic orchestration — built for rapid iteration and scalable deployment using highly customizable, community-supported tools like MCP, LangGraph, and more.

Visit the Github

Core Features

MCP Client is an open protocol that standardizes how apps provide context to LLMs.

  • Seamlessly integrates LLM with growing list of community integrations found here MCP Server
  • No LLM provider lock in

LangGraph for Customizable Agentic Orchestration

  • Native streaming for UX in complex Agentic Workflows
  • Native persisted chat history and state management

Technology Stack and Features

  • FastAPI for Python backend API
  • SQLModel for Python SQL database interactions (ORM + Validation).
    • Wrapper of SQLAlchemy
  • Pydantic for Data Validation and Settings Management.
  • Supabase for DB RBAC
    • PostgreSQL Relational DB
    • PGVector Vector Store
  • Nginx Reverse Proxy
  • Compose for development and production.

Planned Features

  • LangFuse for LLM Observability and LLM Metrics
  • Prometheus for scraping Metrics
  • Grafana for visualizing Metrics
  • Auth0 SaaS for JWT authentication
  • CI/CD via Github Actions
    • 💵 Deploy live demo to Fargate
    • Provision with Terraform IaC
    • Push built images to ECR and Dockerhub