Who it is forA developer who wants to try the factory on a task locally before trusting it with issues in a shared repository.
The problemTeams want to see what the agents produce for a real task before turning on the labeled-issue flow for everyone.
The outcomeThe four stations run in order on a task you give in the TUI, and you approve any changes before they are written to GitHub.
What you need first
- A Vercel account to deploy the template with the deploy button
- A GitHub repository you want the factory to work on, in owner/repo format
- A GitHub App installed on that repository with access granted, as the connector requires
- A Linear workspace, only if you want to delegate tasks from Linear
- The Vercel CLI, for the local TUI workflow
Steps
- Run
vercel linkto link the deployed project or a fresh one. - Run
vercel env pullto pull the project environment. - Run
pnpm devto start the TUI. - Give the agent a task in the TUI, such as a small bug report.
- Watch the Classifier, Analyst, Implementer, and Reviewer stations, then approve or reject the changes sent to GitHub.
Prompt for your agent
In the eve-software-factory-template project, run `vercel link`, `vercel env pull`, and `pnpm dev`, then give the factory the task <task description>. Verify that the four stations run in order and that no change reaches GitHub until you approve it in the TUI.
Caveat. The README says local runs are treated as untrusted, so the TUI is the safe place to test before turning on the labeled-issue flow.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page