# AI use cases for Wu (dstrml/wu)

Repo: [dstrml/wu](https://github.com/dstrml/wu) | Use cases: 3 | Page: https://dedupedai.com/use-cases/dstrml-wu/

Wu is a fast, native code editor written in Rust, with coding agents built in.

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

- Edit a large codebase in a fast native editor: https://dedupedai.com/use-cases/dstrml-wu/edit-large-project-native-editor/
- Hand a coding task to a built-in coding agent: https://dedupedai.com/use-cases/dstrml-wu/delegate-code-task-to-built-in-agent/
- Check Wu's memory use against your current editor: https://dedupedai.com/use-cases/dstrml-wu/compare-editor-memory-before-switching/

## How to edit a large codebase in a fast native editor with Wu

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

Open a big project in a native, Rust-built editor that stays responsive on large views.

**Who it is for:** A developer working in a large repository who finds their current editor slow to open or sluggish when scrolling.

**The problem:** Heavy editors can lag on large projects and large files, which slows down every edit.

**The outcome:** The project opens in Wu and large files stay responsive while you browse and edit.

### Steps

1. Download Wu from the Download section for your platform, or on macOS or Linux run `curl -fsSL https://wu.dstrml.org/install.sh | sh`.
2. Read the install script in your browser before running it, or use the manual download links instead.
3. Open your project folder in Wu using its open-folder command. (inferred, check the README)
4. Browse the project tree and open a large file to check that it loads without visible delay.
5. Read the docs at https://wu.dstrml.org for settings and further setup.

### Prompt to paste into your agent

```text
Using the dstrml/wu repo, install Wu on this machine and open <project-path> in it. Expected output: the project tree visible in the Wu editor. Verify that a large file in the project opens without visible delay.
```

### Caveat

Wu is a fork of Zed, and the README points to the Zed development docs for building from source.

Risk, remote script: The one-line installer pipes a remote script into sh, so review it or use the manual download links 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/dstrml-wu/edit-large-project-native-editor/

## How to hand a coding task to a built-in coding agent with Wu

Repo: [dstrml/wu](https://github.com/dstrml/wu) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Use Wu's agent workspace with Claude Code or Codex to draft changes inside your project.

**Who it is for:** A developer with a bug fix or small feature they want an agent to draft inside the project they already have open.

**The problem:** Switching between an editor and a separate agent tool breaks flow and makes it harder to review the proposed changes in context.

**The outcome:** The agent proposes an edit inside Wu, and you review the changed lines in the same workspace before keeping them.

### Steps

1. Install Wu with the Download section, or on macOS or Linux run `curl -fsSL https://wu.dstrml.org/install.sh | sh`.
2. Install and sign in to Claude Code or Codex separately, since the README names them as built-in but does not describe setup. (inferred, check the README)
3. Open your project folder in Wu and start the agent from the agent workspace. (inferred, check the README)
4. Describe the task to the agent and point it at the file it should change.
5. Read the proposed changes line by line and keep only what you want.

### Prompt to paste into your agent

```text
In the dstrml/wu repo context, open <project-path> in Wu and use the built-in Claude Code or Codex agent to make this change: <task>. Expected output: a proposed edit to <file-path>. Verify by reading every changed line before saving.
```

### Caveat

The README names built-in support for Claude Code, Codex, and OpenCode but does not explain how agent setup or sign-in works, so check the docs first.

Risk, credentials: The agent needs your own Claude Code or Codex access, so keep API keys and tokens out of shared project files.

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/dstrml-wu/delegate-code-task-to-built-in-agent/

## How to check Wu's memory use against your current editor with Wu

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

Read the memory benchmark and measure your own setup before moving a machine to Wu.

**Who it is for:** A developer on a low-memory laptop deciding whether to switch from VS Code or Zed to Wu.

**The problem:** Editor memory use affects how much room is left for builds, browsers, and other tools, and claims about it are hard to check.

**The outcome:** You have your own memory readings for your current editor and for Wu on the same project, so the switch decision rests on your numbers.

### Steps

1. Open https://github.com/dstrml/wu/blob/main/docs/memory-benchmark.md and note how the benchmark measured memory.
2. Open your current editor on your project and record its memory use with your operating system's task monitor. (inferred, check the README)
3. Install Wu using the steps in https://github.com/dstrml/wu/blob/main/docs/INSTALL.md.
4. Open the same project in Wu and record its memory use under the same conditions.
5. Compare the two readings and decide whether the difference matters for your work.

### Prompt to paste into your agent

```text
Clone the dstrml/wu repo and read docs/memory-benchmark.md. Expected output: a short summary of how the benchmark measured memory and which editors it compared. Verify that the summary names each editor compared.
```

### Caveat

The README says Wu uses less memory than VS Code and Zed and links a benchmark, but this page does not give figures, so check the linked document 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/dstrml-wu/compare-editor-memory-before-switching/