Tiledesk logo

Tiledesk

Website

Open-source platform for AI chatbots and multichannel live chat

313 stars 109 forks last commit first released MIT

Actively maintained

Last commit 6 Jul 2026.

Tiledesk screenshot

Tiledesk is an open-source conversational platform combining multichannel live chat, visual bot-building, and AI-powered assistants. It provides tools to create LLM-enabled chatbots, manage human handoffs, and integrate knowledge bases for retrieval-augmented responses.

Key Features

  • Multichannel messaging: web chat widget, WhatsApp, and other channels with unified conversation context
  • Visual no-code Design Studio to build conversational flows and prompt chains for AI agents
  • AI Agents and RAG: multiple knowledge bases, hybrid full-text + semantic search, and prompt chaining for contextual answers
  • Human-in-the-loop: smart escalation, agent dashboard, and AI copilots that assist human operators in real time
  • Deployment options: Docker Compose and Kubernetes (Helm charts) with a microservice stack including server, dashboard, chat clients, and MongoDB
  • Extensible integrations: APIs and webhooks for connecting external services, calendars, email, and ecommerce platforms
  • Self-learning workflows: extract insights from conversations to update knowledge and improve agent responses

Use Cases

  • Automated customer support that answers common queries, creates tickets, and escalates complex issues to human agents
  • Conversational commerce and product assistants that present catalogs, build carts, and handle ordering across channels
  • Internal help desks and knowledge retrieval where AI agents surface documents and context from company KBs

Limitations and Considerations

  • Helm charts and provided deployment templates are intended as starting points and include an embedded MongoDB container; they require customization and hardening for production use
  • Some enterprise features and private Docker images are gated behind paid credentials and are not available in the community distribution
  • Advanced AI capabilities depend on configuring LLM providers or external/model-serving infrastructure, which requires additional setup and resource planning

Tiledesk is suitable for teams that need an integrated conversational platform combining bots, human agents, and knowledge-driven AI. It emphasizes extensibility and multi-agent workflows while expecting operators to adapt deployments and integrations for production environments.

Categories:

Tags:

Tech Stack:

Share:

Similar to Tiledesk

AnythingLLM logo

AnythingLLM

All-in-one AI chat app with RAG, agents, and multi-model support

64k
7k
Last commit

AnythingLLM is an all-in-one desktop and Docker app for chatting with documents using RAG, running AI agents, and connecting to local or hosted LLMs and vector databases.

MITActively maintained
Alternative to:
AnythingLLM Cloud logo
AnythingLLM Cloud
+19
LibreChat logo

LibreChat

Self-hosted multi-provider AI chat UI with agents and tools

41.4k
8.5k
Last commit

LibreChat is a self-hosted AI chat platform that supports multiple LLM providers, custom endpoints, agents/tools, file and image chat, conversation search, and presets.

MITActively maintained
Alternative to:
ChatGPT logo
ChatGPT
+11
Ollama logo

Ollama

Run and manage large language models locally with an API

177.1k
17.1k
Last commit

Ollama is a local LLM runtime that lets you pull, run, and customize models, offering a CLI and REST API for chat, generation, and embeddings.

MITActively maintained
Alternative to:
OpenAI API logo
OpenAI API
+15
Khoj logo

Khoj

Open-source personal AI for chat, semantic search and agents

36.1k
2.3k
Last commit

Self-hostable personal AI 'second brain' for chat, semantic search, custom agents, automations and integration with local or cloud LLMs.

AGPL-3.0Actively maintained
Alternative to:
Google NotebookLM logo
Google NotebookLM
+16
Onyx Community Edition logo

Onyx Community Edition

Self-hosted AI chat and enterprise search for any LLM

31.2k
4.3k
Last commit

Open-source platform for AI chat, RAG, agents, and enterprise search across your team’s connected knowledge sources, compatible with hosted and local LLMs.

Actively maintained
Alternative to:
Onyx logo
Onyx
+19

Perplexica

Privacy-focused AI answering engine with web search and citations

35.9k
4k
Last commit

Self-hosted AI answering engine that combines web search with local or hosted LLMs to generate cited answers, with search history and file uploads.

MITActively maintained
Alternative to:
Perplexity logo
Perplexity
+5