Skip to content

Build on Fadenstack

Fadenstack is one AI system for an organisation, run by its IT on its own servers. These pages are for developers who connect apps to it, build agents into other software, or give it new tools.

  • Call the API

    Fadenstack speaks the OpenAI API. Point any OpenAI client at your server's /v1 with a Fadenstack key, and your app gets the organisation's models under its rules.

    Your first API call

  • Build an agent

    Put an assistant into your own software: a desktop application, an Office add-in, a browser extension or a web page. The .NET and TypeScript SDKs run the agent on the device; the server governs it.

    Your first agent

  • Give it tools

    Register an MCP server once on the Fadenstack server, and every chat and agent that is allowed can use its tools.

    MCP servers

  • Share how to work

    Skills are versioned instructions your teams share: checklists, formats, procedures. Every chat and agent can use them.

    Skills

What the server does for every request

Whether a request comes from the chat, an agent or your app, it takes the same path through Fadenstack. The server applies the limits (and budgets, on servers that set them), adds the skills and tools the caller may use, redacts personal data where the organisation's policy says so, sends the request to a model on the organisation's machines or to a provider it allows, and records usage and an audit entry.

Your code does not have to do any of that. It sends a request and gets an answer, or an outcome that says why there is none.

What you need

  • A Fadenstack server. Your organisation's, or one you install: see Get started on the website.
  • A key or an agent. An API key for plain API calls, or an agent registered on the server for the SDKs. Get started shows both.