DEDUPED Hot AI repos, turned into use cases Get the Monday 5
194 stars · TypeScript

How to use Haros: what you can do with it

What is 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.

How do I use it? On macOS or Linux, run curl -fsSL https://bun.sh/install | bash, then open a new terminal; then 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; run bun install --frozen-lockfile, then bun run build:desktop, then bun run start:desktop. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Switch between coding agents in one conversation

    Run Codex and Claude Code in one Haros conversation and move work between them.

    View prompt
    In the piai-lab/Haros repo, follow the README to run `bun run start:desktop` and configure the <harness name> Engine in Settings. Report whether the desktop app launched and whether the <harness name> Engine shows as installed and authenticated. Verify the Engine status before reporting success.

  • Package a standalone Haros app for your platform

    Build a local Haros desktop app for macOS, Windows, or Linux from source.

    View prompt
    In the piai-lab/Haros repo, run the packaging command for <platform> 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.

  • Run Haros quality checks before a pull request

    Run the repo's format, lint, typecheck, and test commands before contributing.

    View prompt
    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 <branch or path>. 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.

Quick start with Haros

  1. Check you have what it needs: Bun 1.3.9+ within Bun 1.x (the repo pins Bun 1.3.12); Node.js 24.13.1+ within Node 24; Git.
  2. Open piai-lab/Haros on GitHub and read the README and license.
  3. On macOS or Linux, run curl -fsSL https://bun.sh/install | bash, then open a new terminal.
  4. 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)
  5. Run bun install --frozen-lockfile, then bun run build:desktop, then bun run start:desktop.
  6. 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.

These steps come from our top use case, Switch between coding agents in one conversation, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for piai-lab/Haros

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Haros alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and power users who already run coding agents such as Codex or Claude Code and want to switch between them without losing project context.
  • Why it is hot194 stars, launched 59 days ago
  • LanguageTypeScript
  • Sourcegithub.com/piai-lab/Haros · Back to Hot repos

Requirements

  • Bun 1.3.9+ within Bun 1.x (the repo pins Bun 1.3.12)
  • Node.js 24.13.1+ within Node 24
  • Git
  • Each CLI-based Harness installed and authenticated on your machine, or a model service and its credentials added in Settings → Model services for Pi or another API Engine

Add this badge to your README

Maintain Haros? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/piai-lab/Haros.svg)](https://dedupedai.com/use-cases/piai-lab-haros/?utm_source=github&utm_medium=badge&utm_campaign=piai-lab-Haros)

HTML 

<a href="https://dedupedai.com/use-cases/piai-lab-haros/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=piai-lab-Haros"><img src="https://dedupedai.com/badge/piai-lab/Haros.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Haros

What is 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. It is an open-source project on GitHub: https://github.com/piai-lab/Haros.

How do I use Haros?

On macOS or Linux, run curl -fsSL https://bun.sh/install | bash, then open a new terminal; then 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; run bun install --frozen-lockfile, then bun run build:desktop, then bun run start:desktop. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Haros for?

Developers and power users who already run coding agents such as Codex or Claude Code and want to switch between them without losing project context.

What can I do with Haros?

3 use cases so far, for example: Switch between coding agents in one conversation; Package a standalone Haros app for your platform; Run Haros quality checks before a pull request. Each has steps and a copy-paste agent prompt.

What do I need to run Haros?

Bun 1.3.9+ within Bun 1.x (the repo pins Bun 1.3.12); Node.js 24.13.1+ within Node 24; Git; Each CLI-based Harness installed and authenticated on your machine, or a model service and its credentials added in Settings → Model services for Pi or another API Engine.

What are alternatives to Haros?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Haros safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.