Cat-Factory
Home
  • Introduction
  • Core Concepts
  • Quick Start
  • Designing Your Board
  • Shared Services
  • Requirements
  • Running Pipelines
  • Recurring Pipelines
  • Pull Requests & Merging
  • Repositories
  • Issue & Document Sources
  • Budgets & Spend
  • Prompt Fragments
  • Deploy to Cloudflare
  • Deploy to Node.js
  • Configuration
  • Self-Hosted Runner Pools
  • Ephemeral Environments
  • Architecture
  • Integration Manifests
  • Data Model
  • Packages & Repository Layout
GitHub
Home
  • Introduction
  • Core Concepts
  • Quick Start
  • Designing Your Board
  • Shared Services
  • Requirements
  • Running Pipelines
  • Recurring Pipelines
  • Pull Requests & Merging
  • Repositories
  • Issue & Document Sources
  • Budgets & Spend
  • Prompt Fragments
  • Deploy to Cloudflare
  • Deploy to Node.js
  • Configuration
  • Self-Hosted Runner Pools
  • Ephemeral Environments
  • Architecture
  • Integration Manifests
  • Data Model
  • Packages & Repository Layout
GitHub

Cat-Factory

Design software on a visual board, then let LLM agents build it — as real, reviewed pull requests with full pipeline observability.

Get Started →Core Concepts

The board is the plan

Sketch services, modules, and tasks on a pannable, zoomable canvas. Every block is both a design artifact and a unit of work — no separate backlog to keep in sync.

Agents do real work

Coding agents clone your repository, implement the task, and open a pull request. A block is "done" only when its PR is merged with passing CI — never when text is generated.

Multi-stage pipelines

Compose ordered agent chains — architect → coder → reviewer → tester → acceptance — with per-block model selection and human decision points along the way.

Human in the loop

A reviewer agent surfaces gaps, assumptions, and risks before code is written. You answer the open questions, approve the plan, and review every PR before merge.

Durable & observable

Runs are checkpointed and stream live progress over WebSockets — no polling. Watch each step, decision prompt, and failure as it happens.

Cost under control

Set an organization-wide monthly LLM budget. Spend is metered per run, runs pause at the cap, and resume automatically on the next billing period.

Build software the way you draw it

Cat-Factory is a self-hosted platform that turns an architecture diagram into shipped code. You design the system visually; LLM agents pick up each block, do the implementation on a real repository checkout, and open pull requests for your team to review and merge.

# Deploy the backend to Cloudflare
cd deploy/backend
wrangler d1 migrations apply cat_factory --remote
pnpm deploy

# Build and publish the frontend
cd ../frontend
NUXT_PUBLIC_API_BASE=https://your-api-domain.com pnpm generate
pnpm deploy

Where to next?

  • New here? Start with the Introduction and Core Concepts.
  • Want it running? Follow the Quick Start or pick a deployment target under Deploy & Operate.
  • Daily driver? Jump into Designing Your Board and Running Pipelines.
  • Integrating your infra? See Integration Manifests and the Architecture reference.

A note on scope

This site documents how to deploy and use Cat-Factory. For source code, issues, and contribution guidelines, head to the kibertoad/cat-factory repository.

MIT Licensed | Copyright © Cat-Factory contributors