Who it is forA contributor who wants to add a Harness integration, fix platform support, or improve the workbench and must pass the project's checks first.
The problemChanges that skip the repo's format, lint, and typecheck steps are likely to be sent back during review.
The outcomeA local clean run of the standard checks, so your change is ready for a pull request.
What you need first
- 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
Steps
- Run
git clone https://github.com/piai-lab/Haros.git, thencd Haros, thenbun install --frozen-lockfile. - Make your change, then run
bun run fmt:check. - Run
bun run lint, thenbun run typecheck. - Run
bun run testfor behavior changes, andbun run build:desktopif your change affects the Desktop app or packaged bytes.
Prompt for your agent
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.
Caveat. The README says to read CONTRIBUTING.md for architecture boundaries and pull request expectations, which this use case does not cover.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for piai-lab/Haros and "Run Haros quality checks before a pull request"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer