Integration Landscape

This page explains the architecture model. If you simply want to connect a service, start here: Integrations Home.

The Full Picture

In meinGPT, every integration type is reduced to one shared runtime model:

LLM + tool calls as the central integration fabric.

This allows very different systems to be operated, secured, and scaled in a consistent way.

Start with 'Your options' if you just want to pick the right integration path.

Users & Teams

Where you work

Assistants

Workflows

Custom Apps

CORE

meinGPT Runtime (automatic routing)

Chooses the right connector/data source for each request and enforces policies.

Connected systems

Connectors

Databases

Data Pools

No-Code

Custom MCP

External Systems

Applies everywhere

Permissions

Identity (JWT)

Connections

Permissions, identity, and network rules apply to every integration type.

You connect systems through one integration model, not separately per assistant.
Your assistant selects the right tool or data source per task.
Security, permissions, and network access apply consistently across all integration types.

These layers apply across all integration types:

I want to...	Start here
Connect Microsoft 365, Google, Jira, or Confluence	Connectors Overview
Make documents/files searchable as knowledge	Data Pools (RAG)
Query databases	Databases Overview
Connect internal APIs/services	Custom MCP
Reach private systems in company networks	Connections (Cloud/On-Prem)

Building Block	Use Case
Connectors	Execute actions in external tools (Slack, Jira, etc.)
Databases	Query structured data precisely (SQL, NoSQL)
Data Pools (RAG)	Retrieve and ground on document knowledge
No-Code	Integrate existing process automations (Make, Zapier)
Custom MCP	Connect customer-specific protocols/backends
Custom AI Apps	Provide guided custom UIs for specific workflows

Default: For most teams, setup in the meinGPT UI is sufficient.
Advanced: On-prem/Data Vault is for teams needing own runtime and network control.