vercel-labs/eve-software-factory-template

Meet Foreman, an eve Software Factory.

What it solves

Foreman is an AI-powered software factory that automates the development loop. It reduces the manual effort required to turn a GitHub or Linear issue into a reviewed, mergeable pull request by placing AI agents at every stage of the software development lifecycle.

How it works

Foreman uses a pipeline of four specialized agents, each with its own instructions, sandbox, and tools:

  • Classifier: Triages tasks by type, priority, and complexity, and asks for clarification if a task is not actionable.
  • Analyst: Creates a detailed plan with acceptance criteria based on a live checkout of the repository.
  • Implementer: Executes the plan in a sandbox, verifies the changes using the repository's own checks, and pushes a branch.
  • Reviewer: Independently evaluates the the changes against the actual diff to provide a verdict.

The system maintains a "factory brain" (memory) containing notes about the repository to ensure consistency across runs.

Who it’s for

Software developers and repository owners who want to automate the triage, planning, and implementation of issues from GitHub and Linear.

Highlights

  • Multi-agent pipeline: Uses a distinct agent for each stage of the development loop.
  • Integration: Connects directly with GitHub, Linear, and Vercel.
  • Integration with CI: Automatically diagnoses and fixes failures in its own pull requests when CI fails (Red CI).
  • Interactive sessions: Can be triggered via issue labels, @mentions, a local TUI, or Linear Agent Sessions.
  • Repository Memory: Maintains a long-term memory of the repository's context to inform future tasks.

Related

  • Project
    finna/Finn-loop

    A set of Claude Code skills that automate the pipeline from idea to PR using Linear and GitHub, while keeping humans as the final merge authority.

  • Project
    qf-studio/pilot

    An AI software engineer that automatically picks up tickets from GitHub, Jira, or Linear, implements the code, and opens pull requests for review.

  • Project
    Runfusion/Fusion

    Fusion is an open‑source AI‑powered software factory that turns plain‑language task descriptions into fully reviewed, merge‑ready code. It coordinates a fleet of LLM‑driven agents, runs each task in its own Git worktree, and presents the whole process on a visual dashboard with configurable workflows and human oversight.

  • Project
    samugit83/redamon

    An autonomous AI framework that automates the security pipeline from reconnaissance and exploitation to AI-driven triage and automated code fixes via GitHub pull requests.

  • Project
    chenjigang4167/testhub_platform

    TestHub is an open‑source, AI‑enhanced test‑management system built with Django (backend) and Vue 3 (frontend). It covers requirement analysis, test‑case creation & review, API testing, web‑UI automation (Selenium/Playwright), Android automation (Airtest), performance testing (Locust), and a data‑factory toolbox. AI models (OpenAI, Anthropic, Gemini, etc.) can auto‑generate cases and drive browsers via a “smart mode”. The stack uses MySQL, Redis, Celery, Channels, JWT auth, and Allure reporting. The README provides full install steps, Docker support, and contribution guidelines.