Logo
Deploy Now

SaaS Alternative

Intercom Drift Voiceflow

Categories

Self-Hosted Automation No-Code Customer Support Live Chat Conversational AI AI Chatbot Multichannel

Stars

318

Forks

113

Watchers

6

Developer links

Last Updated: 08-21-2026 12:58 AM (UTC)

Tiledesk

Tiledesk lets you build AI-powered conversational agents with a visual drag-and-drop designer, then deploy them simultaneously across web chat, WhatsApp, Telegram, Facebook Messenger, Instagram, email, and Slack without rebuilding per channel. The no-code Design Studio combines LLM-powered conversations with conditional logic, external API calls, and branching dialogue trees that work identically everywhere. Multi-RAG knowledge management separates content into isolated repositories with hybrid search combining traditional full-text retrieval and semantic understanding via Qdrant vector embeddings, enabling accurate answers even when users phrase queries in unexpected ways. LLM integration supports GPT-4, GPT-4o, Anthropic Claude, and any model exposing an OpenAI-compatible API including locally hosted models via Ollama for complete data sovereignty. The human-in-the-loop system provides seamless escalation from AI agents to live support staff with full conversation context preserved, while multi-agent workflows enable complex orchestration where specialized bots collaborate on different aspects of a customer interaction. REST and MQTT APIs power integration with external systems and webhook-triggered automations, and pre-designed templates accelerate common scenarios. Docker Compose deployment starts the full stack including server, dashboard, messaging engine, and widget. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Tiledesk
Tiledesk
Tiledesk
Tiledesk

Benefits

  • No-Code Visual AI Builder
  • Drag-and-drop Design Studio creates branching conversation flows with conditional logic, LLM responses, and API integrations that deploy simultaneously across all connected channels.
  • Multi-RAG Knowledge Intelligence
  • Multiple isolated knowledge repositories with hybrid semantic and full-text search via Qdrant vector store ensure accurate retrieval even with varied customer phrasing patterns.
  • True Omnichannel Deployment
  • Build once and deploy across web chat, WhatsApp, Telegram, Facebook Messenger, Instagram, email, and Slack with automatic response adaptation per channel capabilities.
  • Seamless Human-Agent Handoff
  • AI agents escalate to live support staff with full conversation context preserved when reaching confidence limits, eliminating dropped context during bot-to-human transitions.

Features

  • LLM Agent Framework
  • Supports GPT-4, Claude, and any OpenAI-compatible API including Ollama-hosted open-weight models with multi-agent workflows for specialized task orchestration.
  • Visual Flow Designer
  • Drag-and-drop conversation builder with pre-ready actions, conditional branching, external web requests, and template library for rapid deployment without code.
  • Multichannel Messaging
  • Single inbox unifies WhatsApp, Telegram, Facebook Messenger, Instagram, email, Slack, and web widget conversations with automatic response format adaptation per channel.
  • Knowledge Base APIs
  • Upload documentation, FAQs, and content with semantic search powered by hybrid RAG reducing hallucination through grounded retrieval before LLM response generation.
  • REST and MQTT APIs
  • Full programmatic access via REST APIs for conversations, agents, and knowledge bases plus MQTT real-time messaging for custom integrations and webhook automations.