Self-host solution
Your AI workspace, on your infrastructure
The leading solution for building a custom, private, and secure AI chat portal on your own server.
Contact for self-host5,000+ businesses
worldwide have joined us
Why self-host AI workspace
Dedicated AI workspace for high-scale companies
Serve a custom, on-premise AI workspace that you fully control, at scale for your organization.
Privacy & security
Self-hosting gives complete control over data.
Easy deployment
Docker containerization makes setup straightforward.
Enterprise integration
SSO support with secure OTP authentication and customizable SMTP.
Advanced AI capabilities
Optional RAG/Knowledge Base module for enhanced functionality.
Features
Full-featured AI platform on your infrastructure
Everything you need to build, deploy, and manage AI solutions for your team in one comprehensive platform.
Custom branding
Make the workspace your own: change the logo, theme, and email content, and add custom code.
Advanced chat experience
Project folders, artifacts, a canvas editor, and Model Context Protocol support for every chat.
Advanced authentication
Sign in with SSO, sync users with Directory Sync, or use OAuth and JWT.
Knowledge base
Upload files or connect data sources so AI answers with your company's information.
Reports & analytics
Record chat logs, explore the analytics dashboard, export raw data, and get email reports.
Usage limits & access control
Role-based access, usage limits per user, model, or agent, and fine-grained permissions.
What you need to bring
Large language models
You need to bring your organization's LLM API keys (OpenAI, Anthropic, etc.) or connect to your own in-house LLMs.
Documentation
In-app documents link to our public docs by default. You can customize these links to your internal documentation.
Technical documentation
How self-hosting works
Complete guide to deployment, architecture, requirements, and security.
System overview
In the self-host version of TypingMind, there are two main components.
The app server (NodeJS app)
This is where the data is received and processed. The app server provides two web portals: the Admin Panel for admins to configure the instance and the Chat Interface for your end users.
The app database (MySQL database)
This is where the data is securely stored.
Note: The system does not include an LLM model or an AI provider. TypingMind only provides the chat interface and the management system around it. After setting up the system, you will need to connect it to an AI provider (OpenAI's ChatGPT, Claude, Gemini, or a private LLM model that you run in your infrastructure).
Technical requirements
Two things are all you need to host TypingMind Teams.
Docker-compatible server
Runs the official TypingMind Docker image.
MySQL 8.x database
Stores your data, with 1+ CPU and 4GB+ RAM.
Installation
The setup process is straightforward and takes approximately 30 minutes.
- 1
Purchase Self-host license
Get your license key and access to the Docker image.
- 2
Set up a MySQL 8.x database
Use any MySQL hosting provider (must have 1+ CPU, 4GB+ RAM).
- 3
Configure environment variables
Set up database URL, SMTP, hostname, and license key.
- 4
Deploy Docker container
Pull and run the official Docker image on your infrastructure.
- 5
Connect your custom domain
Point your domain to the server.
- 6
Complete setup
Visit /setup URL to configure your instance via admin panel.
Updates
Software updates are released through the private GitHub repo.
- The Business plan comes with 1 year of free updates.
- Software updates will be released via the GitHub repo.
- Auto-update: you can set up an automation to pull and redeploy anytime there's a new change in the GitHub repository.
- After 1 year, you can renew your license to continue receiving updates.
Seats & renewal
Manage your license directly from the admin panel.
- You can buy more seats/users anytime.
- There is a payment link in the admin panel for you to buy and renew your self-host version.
Security & privacy
All data are stored in your MySQL database and never sent anywhere else.
There is strictly no user data sent out to any other external services. This can be verified using various black-box testing methods like monitoring network requests from the app. There are only three types of external network requests that will be made from the self-host app:
AI provider requests
Requests to OpenAI/Anthropic are the core functionality of the app, allowing you to chat with AI. If you use an internal private LLM, no requests to OpenAI/Anthropic will be made.
Update checks
Notify you when there is a new update. Sent to TypingMind's server with only the minimal information needed to check for updates.
License checks
Verify your self-host license and that you're using the correct number of users for your plan. Sent to TypingMind's server with no user data included.
Maximum security
SOC 2 Type II certified and GDPR compliant. Your data stays on your servers and is never used to train AI models.
SOC 2 Type 2
No training with your data
GDPR compliant
Frequently asked questions
