# AI use cases for Waku (egoist/waku) Repo: [egoist/waku](https://github.com/egoist/waku) | Use cases: 5 | Page: https://dedupedai.com/use-cases/egoist-waku/ Waku is a fast, native desktop app written in Rust that gives you one place to run and manage local coding agent CLIs, projects, and sessions. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run several coding agents side by side in one app: https://dedupedai.com/use-cases/egoist-waku/run-several-coding-agents-in-one-app/ - Steer an agent mid-task with queued follow-ups: https://dedupedai.com/use-cases/egoist-waku/steer-agent-while-it-works/ - Rewind a Git-backed agent task to a checkpoint: https://dedupedai.com/use-cases/egoist-waku/rewind-git-task-to-checkpoint/ - Keep agent transcripts and app state on your machine: https://dedupedai.com/use-cases/egoist-waku/keep-agent-history-on-your-machine/ - Build and run Waku from source for development: https://dedupedai.com/use-cases/egoist-waku/build-waku-from-source-for-development/ ## How to run several coding agents side by side in one app with Waku Repo: [egoist/waku](https://github.com/egoist/waku) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Keep projects and separate agent sessions from different CLIs in one native desktop window. **Who it is for:** A developer who uses Claude Code, Codex CLI, or Cursor CLI on the same codebase and is tired of juggling terminal windows for each one. **The problem:** Each agent CLI runs in its own terminal, so projects, sessions, and transcripts end up scattered across windows. **The outcome:** One desktop app lists your projects and independent agent sessions, with each session tied to the agent you chose. ### Steps 1. On macOS, download the signed .dmg from https://waku.sh and open it. It updates itself. 2. On Linux, run `curl -fsSL https://waku.sh/install.sh | sh`. 3. Install and authenticate at least one agent CLI, such as Claude Code, Codex CLI, or Cursor CLI, before starting Waku. 4. Open Waku, add a project, and start one session per agent you want to compare. 5. Switch models, reasoning effort, or access modes from the shared interface as needed. ### Prompt to paste into your agent ```text In the waku repo at , confirm that Waku can see at least one agent CLI by opening the app and listing the detected agents for the project at . Expected output: a list of detected agents and the sessions created for each. Verify that each session shows its own transcript. ``` ### Caveat The README says the embedded browser and computer-use integration are macOS-only, and that Windows has parts not yet available, so check docs/windows.md or docs/linux.md for your platform. 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/egoist-waku/run-several-coding-agents-in-one-app/ ## How to steer an agent mid-task with queued follow-ups with Waku Repo: [egoist/waku](https://github.com/egoist/waku) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Send follow-up instructions while an agent is still working, without starting over. **Who it is for:** A developer who notices an agent heading the wrong way partway through a long task and wants to correct it without losing the session. **The problem:** Most agent terminals make you wait for a run to finish before you can redirect it. **The outcome:** Your follow-up message is queued or used to steer the running agent, and the session continues in the same thread. ### Steps 1. Install Waku and at least one authenticated agent CLI, as described in the install section of the README. 2. Open a project and start a session with a task that will take a while. 3. While the agent is working, type a follow-up message and choose to queue or steer it. 4. Check the transcript to confirm the follow-up was applied in the same session. ### Prompt to paste into your agent ```text Using the waku app at , start a session on the project at with the task , then send one follow-up message while the agent is running. Expected output: a transcript showing the queued or steered message inside the same session. Verify that the session ID did not change. ``` ### Caveat The README describes queueing and steering but does not say which option each provider supports, so test with the agent you 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/egoist-waku/steer-agent-while-it-works/ ## How to rewind a Git-backed agent task to a checkpoint with Waku Repo: [egoist/waku](https://github.com/egoist/waku) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Roll an agent's Git-backed work back to an earlier conversation point when a change goes wrong. **Who it is for:** A developer whose agent made a series of edits in a Git repo and now needs to undo back to a known good point in the conversation. **The problem:** Undoing a bad run of agent edits by hand is slow and easy to get wrong, especially when the conversation and the code have diverged. **The outcome:** The task returns to an earlier conversation-aware checkpoint, so code and conversation line up again. ### Steps 1. Install Waku and open a project that is a Git repository. 2. Start an agent task and let it make a few changes. 3. Pick an earlier checkpoint in the task history. 4. Rewind the task to that checkpoint. 5. Review the Git state of the project to confirm the rewind. ### Prompt to paste into your agent ```text In the waku app, open the Git project at , run an agent task called , and rewind it to the checkpoint . Expected output: the project files and conversation match the checkpoint. Verify with `git status` in that the working tree reflects that earlier point. ``` ### Caveat The README says rewind applies to Git-backed tasks only, so a project without Git will not support 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/egoist-waku/rewind-git-task-to-checkpoint/ ## How to keep agent transcripts and app state on your machine with Waku Repo: [egoist/waku](https://github.com/egoist/waku) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Store projects, sessions, and transcripts locally without a Waku account or hosted service. **Who it is for:** A developer or team lead who needs agent conversations and project data to stay on local machines for privacy or policy reasons. **The problem:** Many AI tools push conversation history to a hosted account, which may not be acceptable for private code. **The outcome:** Projects, sessions, and transcripts are stored locally, and you can confirm where the config files live. ### Steps 1. Install Waku using the macOS .dmg or the Linux install script from the README. 2. Start Waku and create a session in a local project. 3. List the Waku config folder with `ls ~/.waku` to see the local app state. (inferred, check the README) 4. Check that `~/.waku/app.json` exists after the app has run once, as the README describes for Release builds. ### Prompt to paste into your agent ```text On this machine, install Waku from the README and start one session in the project at . Expected output: a local listing of ~/.waku that includes app.json. Verify that no sign-in step was required to create the session. ``` ### Caveat The README says Release builds write to ~/.waku/app.json while Debug builds use temp/app.json, so check which build you are running before looking for the file. 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/egoist-waku/keep-agent-history-on-your-machine/ ## How to build and run Waku from source for development with Waku Repo: [egoist/waku](https://github.com/egoist/waku) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README Set up the Rust and Bun toolchain and start the development app from a local checkout. **Who it is for:** A contributor who wants to change Waku's provider code, UI, or protocol and test the change locally. **The problem:** Changing a native Rust desktop app requires the right toolchain and native build prerequisites before anything runs. **The outcome:** The development build starts from source, and you can make a provider-only edit that rebuilds the daemon. ### Steps 1. Install Rust 1.96 or newer and Bun, and install the native build prerequisites listed in CONTRIBUTING.md. 2. Clone the egoist/waku repository and enter its folder. 3. Run `bun install`. 4. Run `bun run dev`. 5. Read CONTRIBUTING.md for the development workflow and checks before opening a change. ### Prompt to paste into your agent ```text In a local clone of egoist/waku at , install dependencies and start the development build. Expected output: the Waku Debug app launches and the daemon is at target/debug/waku-debug-daemon. Verify the daemon binary exists at that path after startup. ``` ### Caveat The README says Windows needs the MSVC toolchain and Linux needs its native prerequisites, and the first Rust build can take a long time. 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/egoist-waku/build-waku-from-source-for-development/