Skip to content

Akshit1018/OpenSalesAI

Repository files navigation

OpenSalesAI

LangGraph multi-agent sales intelligence platform for FMCG / CPG route-to-market teams.

A supervisor agent detects intent and routes to 5 specialist agents — order, coaching, analytics, collection, and promotion — over a Qdrant + LangChain RAG pipeline with a 3-tier LLM fallback chain. Built and deployed for an FMCG distributor across 50–500 retail outlets.

This is a production system, not a demo. It consolidates fragmented sales tooling (order parsing, promo suggestions, collection coaching, analytics) into one multi-agent application.

Architecture

            ┌─────────────────────────┐
            │  LangGraph StateGraph   │
            │   Supervisor (intent)   │
            └───────────┬─────────────┘
   ┌──────────┬────────┼────────┬──────────┐
   ▼          ▼        ▼        ▼          ▼
 Order     Coach  Analytics  Collection  Promo
   │          │        │        │          │
   └──────────┴────────┴────────┴──────────┘
                        │
              ┌─────────┴─────────┐
              ▼                   ▼
        Qdrant (RAG)        3-tier LLM fallback
        + LangChain         (frontier → mid → local)
  • Dashboard — TypeScript / React
  • AI service — Python / FastAPI
  • Retrieval — Qdrant vector store, LangChain, Pydantic structured outputs, streaming responses
  • Reliability — per-agent context budgeting (prevents token-cost explosion), max-iteration caps, 3-tier LLM fallback
  • Observability — MLflow + Prometheus; intent-classifier accuracy validated on a golden set before each routing change

Specialist agents

Agent Responsibility
Order Parse and place retailer orders
Coach Sales-call coaching and talk-track suggestions
Analytics Outlet performance, route analytics
Collection Outstanding tracking and dunning
Promo Promo eligibility and upsell suggestions

Repo layout

apps/            # TypeScript dashboard
services/        # Python FastAPI ai-service (LangGraph)
packages/        # shared types / utils
infra/           # deployment manifests
docker-compose*.yml
turbo.json       # monorepo orchestration

Why it matters

Most "AI sales" tools wrap a single LLM call. OpenSalesAI treats sales as a stateful multi-step workflow where each step is owned by a scoped agent with its own context budget — the same pattern that prevents a 5-agent system from costing like a 50-agent one.

Status

Production-deployed for an FMCG client. Some configuration and client-specific logic has been abstracted for open-source release.

License

MIT

About

LangGraph multi-agent sales intelligence platform - supervisor routes to 5 specialist agents (order, coach, analytics, collection, promo) over Qdrant + LangChain RAG. TypeScript dashboard + Python FastAPI. Production AI for FMCG route-to-market.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors