# Migrate from Microsoft Copilot to an open source system you own

> Leaving Microsoft Copilot is an inventory problem before it is a tooling problem. Agent definitions, grounding and prompt history live inside Microsoft's tenant, so you rebuild rather than export. This plan gives the order, then the open-source system the work lands in: Kortix.

URL: https://opensourcecopilotalternative.com/migrate-from-microsoft-copilot

## What you can and cannot take with you

Microsoft Copilot is Microsoft's hosted AI assistant built into Word, Excel, PowerPoint, Outlook and Teams, grounded in an organization's own content through Microsoft Graph and Work IQ. It runs as a Microsoft 365 service, and the assistant layer stays Microsoft's. ([Microsoft Copilot](https://www.microsoft.com/en-us/copilot))

Almost nothing you built inside Copilot leaves with you. Agent definitions are provisioned inside your Microsoft 365 environment, and deleting one removes tenant resources such as the app registration and service principals, so there is no portable file to carry out. ([Copilot Studio](https://learn.microsoft.com/en-us/microsoft-copilot-studio/authoring-first-bot))

Grounding is a tenant connection, so it does not travel as a file you own. Copilot reaches files, mail and chats only through Microsoft Graph and Work IQ, scoped to each person's permissions, and it stores the prompt, the response and the response's citations as that person's Copilot activity history alongside your other Microsoft 365 content. ([Copilot data, privacy and security](https://learn.microsoft.com/en-us/microsoft-365/copilot/microsoft-365-copilot-privacy))

The intent behind each artifact is what you re-create: an agent becomes a file in a repo, a prompt becomes a skill, and the grounding becomes a connector your own system holds. The result is open source. Read it, fork it, audit it.

## The order that avoids a stall

A migration stalls when it starts with the tooling. Start with the inventory instead: the workflows people actually run, the agents behind them, the connectors each one needs, and the team that owns each. Keep the list short enough that one team can move without waiting on another.

1. Inventory the workflows people actually run. For each one, write down the agent, the prompts it uses and the tools it reaches.
2. Pick the first workflow to move. Choose one team's workflow with a named owner and an output you can check.
3. Stand up the destination. Self-host on your own server, or start on Kortix Cloud, then create the project and add a model key. The [self-hosting guide](/self-hosting) covers both.
4. Run it in parallel for one cycle. Keep the Copilot seat live while the new workflow runs, and compare what each one returns.
5. Retire the Copilot seat for that team. Move the next workflow only after the first lands as a reviewed change.

If the team is still weighing the decision, the [Kortix vs Microsoft Copilot comparison](/kortix-vs-copilot) covers the differences, and the guide to [open-source Copilot alternatives](/best-open-source-copilot-alternatives) lists the rest of the field.

## One Docker Compose stack, on your own server

`terminal`

```sh
kortix self-host init --domain kortix.example.com --admin-email you@example.com
kortix self-host start
kortix self-host doctor
```

Source: https://kortix.com/docs/host

The published self-host commands from Kortix's docs; init writes docker-compose.yml.

## What you run it on

The open-source AI Operating System is Kortix: it holds your agents, their skills, your company memory, and every connector in one git repo you own. One isolated sandbox per session. Each session has its own isolated machine and branch.

Session work reaches `main` through a change request. Merge is default-deny for agents. Any model provider with your own keys, or the ChatGPT plan you already pay for.

Connectors: 3,000+ apps in a click, plus MCP, OpenAPI, Postman, GraphQL and raw HTTP. Run it on Kortix Cloud, in your VPC, or on your own on-prem network. Self-host is free. ([Kortix docs](https://kortix.com/docs))

## Kortix vs Microsoft Copilot: where the configuration lives

Kortix keeps the configuration in a repo you own; Copilot keeps it in Microsoft's tenant.

| | Kortix (recommended) | Microsoft Copilot |
| --- | --- | --- |
| Where the config lives | Files in one git repo you own | Inside your Microsoft 365 tenant |
| Can it be self-hosted | Yes, in your VPC or on-prem | No, Microsoft-hosted |
| Model choice | Any model provider with your own keys | Microsoft's models, plus Anthropic and OpenAI |
| What moves with you | The repo: agents, skills, memory | Nothing; rebuilt in the new system |
| How work lands | A change request a person reviews | Responses in the apps, stored in the tenant |
| Open source | Yes | No |

## Migration questions buyers ask

### How long does a migration from Microsoft Copilot take?

There is no single cutover. The work runs one workflow at a time, so the length follows your inventory: more workflows and more connectors take longer, while standing up the platform is a few commands.

### Do we keep Microsoft 365 apps such as Word and Teams?

Yes. Moving the assistant layer off Copilot changes where the agents and memory live while leaving your Microsoft 365 plan and the apps your team opens every day in place. Kortix reaches those tools, and the rest of your stack, through connectors.

### What happens to the agents we built in Copilot Studio?

They stay in your Microsoft 365 environment and do not export as portable files. You rebuild each one as a file in your own repo and point it at the tools it reached before. ([Copilot agent management](/copilot-agent-management))

## Move the first workflow, not the whole company

Start on Kortix Cloud or self-host, then bring your agents over one team at a time.

[Try Kortix](https://kortix.com)