Step 1
Keep it in sqemes
Write skills, prompts and personas once. Every saved change keeps a version, and you decide who may see and who may edit each one.
Langdock is an AI platform from Berlin with its own chat, agents and workflows. sqemes keeps your team's skills, prompts and personas once and brings them into every AI tool you use, Langdock included.
Langdock can connect remote MCP servers. That is how sqemes works inside Langdock, the same way it works in ChatGPT, Claude or Cursor.
Three steps, if you use both.
Step 1
Write skills, prompts and personas once. Every saved change keeps a version, and you decide who may see and who may edit each one.
Step 2
Add sqemes as a remote MCP server under integrations in Langdock. There, adding one needs the right to create integrations, which editors and admins have.
Step 3
In Langdock and in every other tool connected to sqemes, the AI loads the playbook the task needs. A change in sqemes reaches all of them.
| Feature | sqemes | Langdock |
|---|---|---|
| What it is | A library for AI know-how: skills, prompts and personas, used in other AI tools and in sqemes Chat | An AI platform with its own chat, agents, workflows and integrations |
| Where your team works | In the tools it already uses: ChatGPT, Claude and Gemini through the browser extension, any MCP client, sqemes Chat | In Langdock: web, desktop and mobile apps, Microsoft add-ins, Slack and Teams bots |
| Prompts with fields to fill in | Yes | Yes, in the prompt library |
| Reusable knowledge | Skills with files, loaded when a task needs them | Skills, activated by their description; admins can make some mandatory |
| Roles | Personas: a working role that loads the right playbook when its condition applies | Agents: specialised assistants with instructions, knowledge and integrations |
| Versions and rights | Every saved change keeps a version you can restore; who may see and who may edit, per playbook | Prompt folders private, for the workspace or for a group; admins share skills with the whole workspace |
| MCP | An MCP server for your playbooks and personas; sqemes Chat also connects other MCP servers | Connects remote MCP servers; its own MCP server offers its agents |
| Models | Any provider with your own key, or the plan's AI credits | More than 40 models from several providers, own keys possible |
| Hosting | Hosted in the EU; self-host on your own servers under a fair-code license | Hosted in the EU on Microsoft Azure; dedicated and on-premise deployments for large customers |
As of: 14 November 2026, from Langdock's own pages. Sources: Langdock MCP docs, Langdock agent MCP server, Langdock prompt library, Langdock skills, Langdock models, Langdock security.
Many teams can use both. If you choose one, this helps.
your company wants one AI platform where everyone works.
your know-how should work in every AI tool, not only in one.
What teams ask about sqemes and Langdock.