Show HN: Eve Software Factory
Summary
Eve Software Factory is a template that uses AI agents to automate the development loop, processing tasks from GitHub and Linear into reviewed pull requests.
View Cached Full Text
Cached at: 08/17/26, 03:57 PM
vercel-labs/eve-software-factory-template
Source: https://github.com/vercel-labs/eve-software-factory-template
eve Software Factory Template
Meet Foreman, an eve software factory that puts AI agents on every stage of the development loop and keeps people on the judgment calls.
Foreman takes tasks from GitHub and Linear, moves each one through four stations, and delivers a reviewed draft pull request on your repository. You review, mark ready, and merge.
How it works
- Classifier triages the task: type, priority, complexity, actionable or not. When the task isn’t actionable, Foreman asks the requester instead of building the wrong thing.
- Analyst turns it into a plan with acceptance criteria, working from a live checkout of your repository.
- Implementer executes the plan in its own sandbox, verifies with your repo’s own checks, and pushes a branch.
- Reviewer independently judges everything against the real diff, with evidence for each verdict.
Each station is its own agent with its own instructions, sandbox, and tools. The Reviewer sees only the pushed branch, never the Implementer’s reasoning. Between runs, Foreman keeps a factory brain: notes about your repository that every run starts from. See the pipeline and factory memory for the full picture.
How work arrives
- Label an issue
factory. The pipeline runs on its own, posts progress as stations complete, and ends with a draft PR linked to the issue. - @mention it on an issue or PR. Mentions from repo owners, members, and collaborators start an interactive session.
- Delegate in Linear. Linear Agent Sessions run the same pipeline and report progress back in Linear.
- The dev TUI. Hand it a task locally. Changes to GitHub wait for your approval.
- Red CI on a factory PR. Foreman diagnoses the failure and pushes a fix to its own branches, never yours.
- Someone opens a pull request. Foreman posts one orienting comment for reviewers: a summary, not a review.
Deploy
The Vercel deploy flow sets up everything: the GitHub connector, Linear connector, Vercel Blob store, and a prompt for the FACTORY_REPO and FACTORY_LABEL environment variables.
Configuration (see .env.example):
| Variable | Required | Default | What it does |
|---|---|---|---|
FACTORY_REPO | Yes | — | The owner/repo the factory works on (the build fails without it) |
FACTORY_SETUP_COMMAND | No | — | Runs once inside the sandbox checkout at build time (e.g. pnpm install), so every run starts with dependencies already installed |
FACTORY_LABEL | No | factory | The issue label that hands an issue to the factory |
FACTORY_BRANCH_PREFIX | No | factory/ | Branch prefix marking the factory’s own PRs, which are the only branches automated CI fixes touch |
FACTORY_BOT_NAME | No | the GitHub App’s slug | The @mention name, resolved from the connector automatically when unset |
GITHUB_CONNECTOR / LINEAR_CONNECTOR | Yes | — | Set automatically from Vercel Connect connector UIDs |
Local development
Link the project you deployed (or a fresh one), pull its environment, and start the TUI:
vercel link
vercel env pull
pnpm dev
Hand the agent a task (“users report the password reset email arrives twice, fix it”) and watch the four stations fire in order, ending in a draft PR on FACTORY_REPO. Local runs are treated as untrusted, so changes to GitHub wait for your approval in the TUI.
Resources
Explore more templates
Similar Articles
Show HN: Git for AI Agents
re_gent is an open-source version control system for AI agent activity, tracking every tool call and associated prompt so developers can audit and roll back agent changes.
@dzhng: Love this framing. A software factory shouldn't require the human to review every line of code, but every *decision* sh…
The developer dzhng shares a GitHub repository of composable AI agent skills for building software factories, enabling autonomous goal-driven code generation with human review at decision points.
@omarsar0: Eve is one of the easiest ways to build with agents. Super intuitive, customizable, and it just works. Below you can re…
Eve is a tool for building AI agents, praised for its intuitiveness and customizability. The author shares their positive experience after a week of use.
@rauchg: eve evals itself with 𝚎𝚟𝚎 𝚎𝚟𝚊𝚕. Web frameworks made testing an ecosystem choice. e.g.: React didn’t ship with a …
eve now ships with built-in eval capabilities for agents, addressing the need for first-class testing in AI agent development.
I built a local-first autonomous coding agent with a cyberpunk soul — Eve Agent V2 Unleashed (open source)
Eve Agent V2 Unleashed is an open-source autonomous coding agent that runs locally via Ollama, featuring a 40-round tool loop, 112 sub-agents, and optional cloud escalation. It can plan, write, test, and verify code with zero hand-holding, with quick start in under 5 minutes.