# AI use cases for Haros (piai-lab/Haros) Repo: [piai-lab/Haros](https://github.com/piai-lab/Haros) | Use cases: 3 | Page: https://dedupedai.com/use-cases/piai-lab-haros/ Haros is an open-source desktop workbench that lets you use Codex, Claude Code, and other agent Harnesses, called Engines, in one conversation with local projects and work history. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Switch between coding agents in one conversation: https://dedupedai.com/use-cases/piai-lab-haros/switch-harnesses-mid-conversation/ - Package a standalone Haros app for your platform: https://dedupedai.com/use-cases/piai-lab-haros/build-standalone-haros-app/ - Run Haros quality checks before a pull request: https://dedupedai.com/use-cases/piai-lab-haros/run-haros-contributor-checks/ ## How to switch between coding agents in one conversation with Haros Repo: [piai-lab/Haros](https://github.com/piai-lab/Haros) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Run Codex and Claude Code in one Haros conversation and move work between them. **Who it is for:** A developer who uses several agent Harnesses and wants to pick the best one per task without copying discussions by hand. **The problem:** Each Harness keeps its own separate session, so moving a task to another agent means re-explaining the project and copying prior messages. **The outcome:** One Haros conversation where you continue the same work in another Harness, with prior user and assistant messages passed along as context. ### Steps 1. On macOS or Linux, run `curl -fsSL https://bun.sh/install | bash`, then open a new terminal. 2. Run `git clone https://github.com/piai-lend/Haros.git`, but use the exact URL https://github.com/piai-lab/Haros.git, then `cd Haros`. (inferred, check the README) 3. Run `bun install --frozen-lockfile`, then `bun run build:desktop`, then `bun run start:desktop`. 4. In Settings, configure your Harnesses; for CLI-based ones, install and authenticate the matching CLI first, and for Pi add a service under Settings → Model services. 5. Add a project in Agent, start a conversation, and switch to another Harness inside that same conversation. ### Prompt to paste into your agent ```text In the piai-lab/Haros repo, follow the README to run `bun run start:desktop` and configure the Engine in Settings. Report whether the desktop app launched and whether the Engine shows as installed and authenticated. Verify the Engine status before reporting success. ``` ### Caveat Haros passes prior messages as context but does not transfer another Harness's private native session state, and long histories are shortened to fit the context budget. Risk, credentials: Harness authentication and model service credentials are used by your selected Harness, and prompts plus relevant context may be sent to those model services. 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/piai-lab-haros/switch-harnesses-mid-conversation/ ## How to package a standalone Haros app for your platform with Haros Repo: [piai-lab/Haros](https://github.com/piai-lab/Haros) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Build a local Haros desktop app for macOS, Windows, or Linux from source. **Who it is for:** A user who wants Haros as a normal app icon instead of running it from a source checkout, or who needs a build for a machine without an official installer. **The problem:** An installer may not exist for your platform, and running from source each time is slow to repeat. **The outcome:** A packaged Haros app for your platform: a local .app on macOS, an x64 NSIS installer on Windows, or an x64 AppImage on Linux. ### Steps 1. Run `git clone https://github.com/piai-lab/Haros.git`, then `cd Haros`, then `bun install --frozen-lockfile`. 2. On macOS, run `bun run dist:desktop:local-app`; on Windows, run `bun run dist:desktop:win`; on Linux, run `bun run dist:desktop:linux`. 3. On Apple Silicon, open the app with `open apps/desktop/.electron-runtime/local-app/arm64/mac-arm64/Haros.app`; on Intel Macs, use `apps/desktop/.electron-runtime/local-app/x64/mac/Haros.app`. 4. Quit Haros before rebuilding, and leave any explicit `--output-dir` empty. ### Prompt to paste into your agent ```text In the piai-lab/Haros repo, run the packaging command for from the README after `bun install --frozen-lockfile`. Report the path of the generated app or installer. Verify that the output file exists at that path before reporting success. ``` ### Caveat Local builds are unsigned and macOS builds are not notarized, and a successful build on one OS does not validate the others. 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/piai-lab-haros/build-standalone-haros-app/ ## How to run Haros quality checks before a pull request with Haros Repo: [piai-lab/Haros](https://github.com/piai-lab/Haros) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Run the repo's format, lint, typecheck, and test commands before contributing. **Who it is for:** A contributor who wants to add a Harness integration, fix platform support, or improve the workbench and must pass the project's checks first. **The problem:** Changes that skip the repo's format, lint, and typecheck steps are likely to be sent back during review. **The outcome:** A local clean run of the standard checks, so your change is ready for a pull request. ### Steps 1. Run `git clone https://github.com/piai-lab/Haros.git`, then `cd Haros`, then `bun install --frozen-lockfile`. 2. Make your change, then run `bun run fmt:check`. 3. Run `bun run lint`, then `bun run typecheck`. 4. Run `bun run test` for behavior changes, and `bun run build:desktop` if your change affects the Desktop app or packaged bytes. ### Prompt to paste into your agent ```text In the piai-lab/Haros repo, install dependencies with `bun install --frozen-lockfile`, then run fmt:check, lint, typecheck, and test on the change in . Report each command's pass or fail result with the error output for any failure. Verify that every command exits successfully before saying the change is ready. ``` ### Caveat The README says to read CONTRIBUTING.md for architecture boundaries and pull request expectations, which this use case does not cover. 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/piai-lab-haros/run-haros-contributor-checks/