melgarafael/DeskcommCRM

Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.

What it solves

DeskcommCRM is an open-source sales "operating system" designed for businesses that sell via WhatsApp. It replaces expensive monthly subscriptions (like Kommo or Intercom) by providing a self-hosted CRM that integrates AI agents to handle customer service, qualify leads, and manage sales funnels without locking data behind a proprietary platform.

How it works

The system combines a traditional CRM (Kanban boards, contact management) with AI agents powered by RAG (Retrieval-Augmented Generation) and specific "skills." These agents can autonomously interact with customers on WhatsApp, move leads through the sales funnel, and hand off conversations to humans when necessary. It supports two WhatsApp connection methods: via QR code (using WAHA) or the official Meta Cloud API. The platform is built on a multi-tenant architecture using Supabase for database, auth, and vector storage, and utilizes the Vercel AI SDK to connect to various LLM providers like OpenAI, Anthropic, or OpenRouter.

Who it’s for

It is designed for any business selling through WhatsApp, including e-commerce stores (with built-in Nuvemshop integration), medical clinics, real estate agencies, and service providers who want full control over their data and AI-driven automation.

Highlights

  • AI Agents with RAG: Agents that don't just chat but actually operate the CRM, qualify leads, and execute skills.
  • Self-Hosted: One-command installation on a VPS (via Docker) ensuring data privacy and no monthly fees.
  • Flexible WhatsApp Integration: Supports both unofficial QR-code based connections and the official Meta API.
  • Automation Engine: A "WHEN/IF/THEN" rule system for triggering actions like tagging leads or sending messages based on events.
  • AI Evolution: A dedicated interface to track AI performance, identify errors, and apply AI-suggested improvements.
  • Multi-tenant & LGPD Compliant: Built-in row-level security (RLS) and data anonymization for privacy compliance.

Related

  • Project
    open-webui/open-webui

    Open WebUI is an open‑source, self‑hosted web interface for LLMs that works with any OpenAI‑compatible API and with local Ollama models. It provides a rich UI (chat, notes, channels, calendar, voice/video, image generation), extensible plugin system, RBAC, multi‑model support, built‑in RAG (vector DBs, web search), an “Open Terminal” for agents to run code, and enterprise features like LDAP/SSO, SCIM provisioning, and observability. Install via pip, Docker (CPU/GPU, bundled Ollama), or Kubernetes. The ecosystem includes a desktop app, a mobile‑first coding agent, and tools for syncing external knowledge bases.

  • Project
    ElectricCodeGuy/SupabaseAuthWithSSR

    A Next.js 16 starter that combines Supabase SSR auth with Claude‑powered chat and eight built‑in AI tools (RAG, web search, versioned artifacts, memory, charts, PDFs, image generation). It includes per‑token usage dashboards, prompt caching, and an admin console, all set up via a single `setup.sql` script.

  • Project
    matiasbattocchia/open-bsp-api

    An open-source, multi-tenant platform for managing WhatsApp and Instagram Business messaging, designed to be AI-agent ready and self-hostable via Supabase.

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, self‑hosted AI assistant that plans tasks, runs tools, keeps a personal knowledge base, and can operate as a team of cooperating agents. It supports many LLM providers, multimodal input, dozens of chat channels (Telegram, Slack, WeChat, etc.), a plug‑in skill system, and a three‑tier memory with nightly “Deep Dream” distillation. Install via a one‑line script or Docker, manage everything through a web console, and extend the system through the public Skill Hub or custom tool integrations.

  • Project
    Niek/chatgpt-web

    ChatGPT‑web is an open‑source, single‑page web UI that lets you chat with any OpenAI‑compatible LLM (OpenAI, Anthropic, Gemini, etc.). Conversations are stored locally, the app supports voice I/O, image generation, streaming responses, and can be run in the browser, via Docker, or packaged as a native desktop app.