whatisgithub

What is verxlite?

gadda00/verxlite — explained in plain English

Analysis updated 2026-05-18

★ 0PythonAudience · developerComplexity · 4/5Setup · hard

In one sentence

A multi-service AI agent application that automates sales and ops workflows like CRM logging and follow-up emails across email, CRM, and documents.

Mindmap

mindmap
  root((verxlite))
    What it does
      Automates sales and ops workflows
      CRM logging
      Follow up emails
    Tech stack
      FastAPI backend
      Next.js frontend
      LangGraph agent
      Celery worker
    Use cases
      Post meeting follow up
      Lead assignment planned
      Support ticket triage planned
    Audience
      Sales and ops teams
      Developers building AI agents
    Setup
      Needs Postgres and Redis
      OAuth with Google and HubSpot
      Docker Compose option

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Automatically log a completed sales meeting to a CRM and draft a follow-up email.

USE CASE 2

Build on top of the LangGraph agent to add new sales or ops automation workflows.

USE CASE 3

Connect Google Workspace and HubSpot accounts to route information through automated workflows.

USE CASE 4

Track AI workflow performance, token usage, and errors using the built-in Langfuse observability.

What is it built with?

PythonFastAPINext.jsLangGraphCeleryPostgreSQL

How does it compare?

gadda00/verxlite0xallam/my-recipe0xhassaan/nn-from-scratch
Stars0—0
LanguagePythonPythonPython
Last pushed—2022-11-22—
Maintenance—Dormant—
Setup difficultyhardmoderatemoderate
Complexity4/52/54/5
Audiencedevelopergeneraldeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires PostgreSQL, Redis, and OAuth app setup with Google Cloud, HubSpot, Clerk, and Langfuse before it runs.

No license information is stated in the README.

So what is it?

Verxlite describes itself as a universal AI workflow agent for sales and operations teams. Its purpose is to automate repetitive office tasks that happen across email, CRM software, and documents, such as writing follow-up messages, logging activity, routing approvals, and producing summaries, and it is designed to work across different industries rather than one specific niche. The project has a full application structure rather than being a simple script. It includes a FastAPI backend written in Python that exposes an API, a Celery worker for running background tasks, and a Next.js frontend written in React for the user interface. Behind the scenes it uses LangGraph, a framework for building multi step AI agent workflows, so the AI can reason through a task, call tools, make API calls, and produce structured output rather than just replying with text. The README lists connectors that let it read and act on data in Google Workspace, meaning Gmail, Calendar, and Drive, and HubSpot CRM, with Salesforce and Outlook support listed as coming soon. So far, one concrete workflow is marked as a working starting version: automatically logging a meeting to the CRM, drafting a follow-up email, and creating related tasks afterward. Several other workflows, including lead assignment, support ticket triage, approval routing, and weekly summaries, are listed as planned but not yet built. Setting this up is not a quick task. It requires Python, Node.js, PostgreSQL, Redis, and optionally Docker, along with creating developer accounts and OAuth applications with Google Cloud and HubSpot, plus a Clerk account for user authentication and a Langfuse account for tracking how the AI workflows perform. The README walks through configuring environment variables for both the backend and frontend, installing dependencies with Poetry and npm, and running the API, frontend, and worker processes separately, or all together using Docker Compose.

Copy-paste prompts

Prompt 1
Walk me through setting up this project locally, including the PostgreSQL, Redis, and OAuth requirements.
Prompt 2
Explain how the post-meeting follow-up workflow in this project works end to end.
Prompt 3
Show me how the LangGraph agent logic in api/verxlite_api/agent is structured.
Prompt 4
Help me add a new workflow type similar to lead assignment using this project's existing connectors.

Frequently asked questions

What is verxlite?

A multi-service AI agent application that automates sales and ops workflows like CRM logging and follow-up emails across email, CRM, and documents.

What language is verxlite written in?

Mainly Python. The stack also includes Python, FastAPI, Next.js.

What license does verxlite use?

No license information is stated in the README.

How hard is verxlite to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is verxlite for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

What are similar repos?