# AI use cases for Nami (mrdainami/nami)

Repo: [mrdainami/nami](https://github.com/mrdainami/nami) | Use cases: 4 | Page: https://dedupedai.com/use-cases/mrdainami-nami/

Nami is a free, open source desktop workspace that runs several AI agents, including Claude Code, Codex, Gemini and Grok, side by side in one folder on Mac or Windows.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run several AI agents on one folder at once: https://dedupedai.com/use-cases/mrdainami-nami/run-several-agents-side-by-side/
- Create a custom agent by describing it: https://dedupedai.com/use-cases/mrdainami-nami/create-custom-agent-from-description/
- Let agents work across Notion, Gmail and Slack: https://dedupedai.com/use-cases/mrdainami-nami/connect-notion-gmail-slack-for-agent-work/
- Build Nami from source to test or contribute: https://dedupedai.com/use-cases/mrdainami-nami/build-nami-from-source-to-contribute/

## How to run several AI agents on one folder at once with Nami

Repo: [mrdainami/nami](https://github.com/mrdainami/nami) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Give several jobs to different agents in one workspace and watch each one work in its own pane.

**Who it is for:** A solo professional with a pile of separate tasks, such as emails, a pricing page and invoices, who is tired of switching between tools.

**The problem:** Each AI tool lives in its own app, so handling several jobs means constant switching and no single view of progress.

**The outcome:** Several jobs run at the same time in separate panes inside one screen, all limited to the folder you chose.

### Steps

1. Download Nami from the Mac or Windows link on the README page and install it.
2. Open Nami and point it at one folder you work in. It never looks outside that folder.
3. Ask for the first job in plain English. Each job runs in its own pane.
4. Ask for a second job while the first is still running. It opens in a new pane beside the first.
5. Watch all panes from the one screen and check each result before you act on it.

### Prompt to paste into your agent

```text
Using the Nami repo at mrdainami/nami, set up the desktop app on a Mac or Windows machine and give two separate jobs to two different agents in the same folder <target-folder>. Expected output: two panes running at the same time, each with its own result. Verify that both jobs report progress and that no file outside <target-folder> was read.
```

### Caveat

Nami only runs agents you already have access to, so you still need working subscriptions for each agent you plan to use.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/mrdainami-nami/run-several-agents-side-by-side/

## How to create a custom agent by describing it with Nami

Repo: [mrdainami/nami](https://github.com/mrdainami/nami) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Describe the job in plain words and get a ready-to-run agent on your shelf in seconds.

**Who it is for:** A small business owner who needs a repeatable helper, such as an invoice sorter, and does not want to write configuration by hand.

**The problem:** Setting up a reusable agent usually means writing config files or code, which blocks people who are not engineers.

**The outcome:** A new agent appears on your shelf, ready to run on the folder you chose, with no manual setup.

### Steps

1. Install Nami and open it, then point it at the folder where the work lives.
2. Describe the agent you want in plain words, for example what it should read and what it should produce.
3. Wait for the agent to appear on your shelf.
4. Run the new agent on one sample item from the folder.
5. Check the output against the sample before you run it on the full set.

### Prompt to paste into your agent

```text
Using the Nami repo at mrdainami/nami, describe a new agent that sorts invoices in <target-folder> and confirm it appears on the agent shelf. Expected output: the new agent listed and runnable with a short sorted result for one invoice. Verify the agent only touched files inside <target-folder>.
```

### Caveat

The README describes creating agents in plain words but does not explain how the generated agent is tested or reviewed, so check its output yourself.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/mrdainami-nami/create-custom-agent-from-description/

## How to let agents work across Notion, Gmail and Slack with Nami

Repo: [mrdainami/nami](https://github.com/mrdainami/nami) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Connect Notion, Gmail or Slack in one click so agents can act on the messages and pages you use daily.

**Who it is for:** A team lead or operations person whose daily work lives in Notion pages, Gmail threads and Slack channels.

**The problem:** Agents are only useful for daily work if they can reach the tools where that work already happens.

**The outcome:** Agents can work with your Notion, Gmail or Slack content from inside Nami, after you connect each one.

### Steps

1. Open Nami and find the connections area.
2. Connect Notion, Gmail or Slack with one click for each service you need.
3. Sign in to each service when Nami asks, using the account you want the agent to use.
4. Ask an agent for a small read-only task first, such as summarizing one Notion page.
5. Review the result and only then ask for changes that write back to the service.

### Prompt to paste into your agent

```text
Using the Nami repo at mrdainami/nami, connect the Gmail account for <target-account> and ask an agent to summarize the last five messages in one thread. Expected output: a short summary of those five messages. Verify the agent made no send, delete or edit action.
```

### Caveat

The README says these three connect in one click but does not list other integrations, so do not assume Nami connects to other services.

Risk, credentials: Connecting Gmail, Slack or Notion gives agents access to that account, so use an account you are comfortable granting and revoke access when you stop.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/mrdainami-nami/connect-notion-gmail-slack-for-agent-work/

## How to build Nami from source to test or contribute with Nami

Repo: [mrdainami/nami](https://github.com/mrdainami/nami) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Clone the repo, install dependencies and start the app locally to test changes before you contribute.

**Who it is for:** A developer who wants to try a change to the desktop app or fix a bug before sending a pull request.

**The problem:** Testing an open source desktop app change requires a working local build, which is not obvious from the download page alone.

**The outcome:** The app runs from your local copy of the source, so you can test changes and read the contributor notes.

### Steps

1. Clone the repo with `git clone https://github.com/mrdainami/nami.git`.
2. Move into the project folder with `cd nami`.
3. Install dependencies with `npm install`.
4. Start the app with `npm start`.
5. Read CONTRIBUTING.md in the repo before you open a pull request.

### Prompt to paste into your agent

```text
Using the Nami repo at mrdainami/nami, clone it, run npm install and npm start, then report whether the desktop app opens. Expected output: a running local Nami window. Verify the install finished without errors before starting the app.
```

### Caveat

The README gives only the basic clone, install and start commands, so any build problems beyond those steps need the contributor notes or the repo issues.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/mrdainami-nami/build-nami-from-source-to-contribute/