# AI use cases for Diri (cristicretu/diri)

Repo: [cristicretu/diri](https://github.com/cristicretu/diri) | Use cases: 5 | Page: https://dedupedai.com/use-cases/cristicretu-diri/

diri is a native macOS app, with Linux in beta, for running many terminal coding agents in parallel, seeing which ones need you, and reviewing their changes in one place.

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

- Track which of many coding agents needs your input: https://dedupedai.com/use-cases/cristicretu-diri/watch-many-agents-from-one-sidebar/
- Give each coding task its own Git worktree and branch: https://dedupedai.com/use-cases/cristicretu-diri/isolate-parallel-tasks-in-worktrees/
- Have one agent spawn and coordinate other agents: https://dedupedai.com/use-cases/cristicretu-diri/let-an-agent-spawn-a-review-swarm/
- Review agent diffs and PR checks beside the session: https://dedupedai.com/use-cases/cristicretu-diri/review-agent-changes-beside-their-session/
- Run coding agents on an SSH host you control: https://dedupedai.com/use-cases/cristicretu-diri/run-agents-on-a-remote-ssh-host/

## How to track which of many coding agents needs your input with Diri

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

Run several agents at once and see which are working, waiting, or finished in one sidebar.

**Who it is for:** A developer running five or more coding agents at once who keeps losing track of which terminal needs an answer.

**The problem:** Each agent runs in its own terminal, so you must check many windows to find the one waiting for you.

**The outcome:** One sidebar shows which sessions are working, waiting, or finished, and you respond only to the ones that need you.

### Steps

1. Install the app with `brew install --cask cristicretu/diri/diri`.
2. Open Diri and start your agent sessions, such as Claude Code, Codex, Cursor, or Gemini.
3. Read the sidebar to see which sessions are working, waiting, or finished.
4. Switch to a session marked waiting and answer the agent.
5. Repeat until every session is marked finished, then review the results.

### Prompt to paste into your agent

```text
Using the diri repo at github.com/cristicretu/diri, check that the sidebar marks each of my running sessions as working, waiting, or finished. Output a list of session names with their status, and confirm that the session in <target-session> is marked waiting when it asks a question.
```

### Caveat

Claude Code and Codex get the deepest status and resume integration, so status detail may be thinner for other agents.

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/cristicretu-diri/watch-many-agents-from-one-sidebar/

## How to give each coding task its own Git worktree and branch with Diri

Repo: [cristicretu/diri](https://github.com/cristicretu/diri) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Run parallel agent tasks in separate worktrees so their changes never collide.

**Who it is for:** A developer splitting one codebase into several features or fixes that agents should work on at the same time.

**The problem:** Parallel agents editing the same checkout overwrite each other's files and make branches hard to untangle.

**The outcome:** Each task runs in its own worktree and branch, so you can review and merge each one independently.

### Steps

1. Install the app with `brew install --cask cristicretu/diri/diri`.
2. Open Diri and create one agent session per task.
3. Enable a separate Git worktree and branch for each session.
4. Let the agents work, then check each session's branch for its own changes.
5. Review and merge the branches one at a time.

### Prompt to paste into your agent

```text
In the diri repo at github.com/cristicretu/diri, confirm that each agent session for <task-list> has its own Git worktree and branch. Output a table of session, worktree path, and branch name, and verify that no two sessions share a branch.
```

### Caveat

The README says each agent can get a worktree but does not say how to enable it, so check the Diri docs for the setting before relying on it.

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/cristicretu-diri/isolate-parallel-tasks-in-worktrees/

## How to have one agent spawn and coordinate other agents with Diri

Repo: [cristicretu/diri](https://github.com/cristicretu/diri) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Use the built-in MCP server so a lead agent can hand tasks to other agents and read their output.

**Who it is for:** A developer who wants a lead agent to split a large job into parts and farm them out to helper agents.

**The problem:** Coordinating several agents by hand, copying tasks and answers between them, is slow and error-prone.

**The outcome:** A lead agent spawns helper agents, assigns each a task, reads their output, and answers their questions.

### Steps

1. Install the app with `brew install --cask cristicretu/diri/diri`.
2. Open Diri and start a lead agent session.
3. Give the lead agent a prompt that describes the job and asks it to use the built-in MCP server to spawn helpers.
4. Watch the sidebar as the helper agents start and report back.
5. Read the helpers' output through the lead agent and approve the combined result.

### Prompt to paste into your agent

```text
Using the diri repo at github.com/cristicretu/diri, have the lead agent spawn helper agents through the built-in MCP server to split <job-description> into subtasks. Output the list of helper agents, their tasks, and their results, and verify that each helper reported an output.
```

### Caveat

The README says a swarm is one prompt away but does not document the MCP tool names, so the lead agent must be given the setup it needs.

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/cristicretu-diri/let-an-agent-spawn-a-review-swarm/

## How to review agent diffs and PR checks beside the session with Diri

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

Inspect diffs, stage, commit, and follow PR checks next to the agent that wrote the code.

**Who it is for:** A developer who needs to check and ship code written by several agents without switching between tools.

**The problem:** Reviewing agent output in a separate tool loses the context of which session wrote which change.

**The outcome:** You review each session's diff, commit it, and watch its pull request checks in the same place.

### Steps

1. Install the app with `brew install --cask cristicretu/diri/diri`.
2. Open the session whose work you want to review.
3. Inspect the diff for that session's changes.
4. Stage and commit the changes you accept.
5. Follow the pull request checks in the same view.

### Prompt to paste into your agent

```text
In the diri repo at github.com/cristicretu/diri, open the session <target-session>, list the files changed in its diff, and confirm the staged changes match what I approved. Output the file list and the commit hash after commit.
```

### Caveat

The README does not say which Git hosts pull request checks support, so confirm it works with your repository first.

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/cristicretu-diri/review-agent-changes-beside-their-session/

## How to run coding agents on an SSH host you control with Diri

Repo: [cristicretu/diri](https://github.com/cristicretu/diri) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Start agent sessions on a remote machine you own, without tmux, sudo, or a hosted relay.

**Who it is for:** A developer whose code or compute lives on a remote server and who wants agents to run there.

**The problem:** Long agent runs tie up a laptop, and remote setups usually need extra tools or a hosted service.

**The outcome:** Agents run on your SSH host while you monitor and review them from Diri.

### Steps

1. Install the app with `brew install --cask cristicretu/diri/diri`.
2. Add an SSH host you control in Diri.
3. Start an agent session on that host.
4. Close the app and reopen it to confirm the session is still running.
5. Review the session's changes once the agent finishes.

### Prompt to paste into your agent

```text
Using the diri repo at github.com/cristicretu/diri, start an agent session on the SSH host <ssh-host>, then close and reopen Diri. Output the session status before and after the restart, and verify the session still runs.
```

### Caveat

The README says the feature works on any SSH host but does not list supported host setups, so test with a non-critical host first.

Risk, credentials: Remote runs use SSH access to a host you control, so protect the keys and only connect to hosts you own.

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/cristicretu-diri/run-agents-on-a-remote-ssh-host/