yerdaulet-damir

Langgraph Sales Agent — AI skill for Claude Code

AI community

Multi-tenant LangGraph runtime that isolates each business's agent, catalog, tools and LLM across Telegram, Instagram, WhatsApp and web.

How to install Langgraph Sales Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open yerdaulet-damir/langgraph-sales-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Langgraph Sales Agent does

Multi-tenant LangGraph runtime that isolates each business's agent, catalog, tools and LLM across Telegram, Instagram, WhatsApp and web.

Alternatives in AI

  • Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★
  • onWatch — Open-source Go CLI that tracks AI API quota usage across 7 providers (Synthetic, Z.ai, Anthropic, Codex, GitHu 397 ★
  • Multi Agent AI System — Building a Multi-Agent AI System with LangGraph and LangSmith 374 ★

README

🤖 LangGraph Sales Agent

**Multi-tenant AI sales agent framework powered by LangGraph**

*One codebase → infinite businesses → any messaging channel*

[![Python](https://img.shields.io/badge/Python-3.11+-3776AB?style=flat-square&logo=python&logoColor=white)](https://python.org) [![LangGraph](https://img.shields.io/badge/LangGraph-0.4+-1C3C3C?style=flat-square&logo=langchain&logoColor=white)](https://github.com/langchain-ai/langgraph) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](LICENSE) [![Multi-Tenant](https://img.shields.io/badge/Architecture-Multi--Tenant-8b5cf6?style=flat-square)]() [![Channels](https://img.shields.io/badge/Channels-Telegram%20%7C%20Instagram%20%7C%20WhatsApp%20%7C%20Web-22c55e?style=flat-square)]()


What is this?

A production-ready, open-source framework for building **AI sales agents that serve multiple businesses** from a single deployment. Each business (tenant) gets their own branded agent personality, product catalog, and LLM config — all wired up to Telegram, Instagram, WhatsApp, and your web app simultaneously.

Think of it as **SalesGPT** but with proper multi-tenancy, channel adapters, and a repository pattern for clean data access.

Customer on Telegram → Flower Shop's "Aigul" (GPT-4o-mini, ru) → searches catalog → sends product images
Customer on WhatsApp → Restaurant's "Marco" (Claude Sonnet, en) → shows menu + promotions
Customer on Web      → E-commerce "Alex" (Llama 3, en) → visual product search

Built in the real world

This isn't a tutorial project. I've been building AI sales agents for real businesses — flower shops, restaurants, e-commerce stores. Every client starts with this exact codebase, and I add integrations on top.

The pattern is always the same:

  1. Drop a config.yaml with the business persona and rules
  2. Load the product catalog into products.json
  3. Connect the channel (usually Telegram first, then Instagram