Auto Engineer

Tell the story. Auto writes the code.

Early Preview - We're actively battle-testing Auto with real-world clients. Expect bugs and rapid evolution. Watch and star this repo to stay updated, and join the Discord for conversations.

---

What is Auto Engineer?

Building apps with AI is hit-or-miss: you prompt, get code, test it, find bugs, re-prompt, and repeat until something works (or you give up). Auto Engineer fixes this by giving AI agents deterministic scaffolds, specs, and feedback loops so they self-correct reliably.

Think of Auto like an SLR camera. In green-square mode, anyone can point and shoot; the system handles the complexity automatically. Switch to manual, and you control every parameter. Same tool, different depths. Beginners ship apps on day one; experts fine-tune every stage of the pipeline.

You model your apps using Narratives, a flow-of-time DSL where you tell the story of your application slice by slice, like a user journey.

The pipeline transforms these high-level flow models into production-ready code: narratives become a domain model, which scaffolds a backend; an AI architect generates a user experience architecture, which scaffolds a frontend. Both are then implemented and tested by AI agents with deterministic feedback loops.

Auto Engineer is for teams who want to collaborate with non-technical stakeholders on real specifications, not mock wireframes, while keeping full control over the generated architecture through customizable pipelines.

---

Quick Start

npx create-auto-app@latest my-project
cd my-project
cp .env.template .env  # Add your API key (Anthropic recommended)
auto

You should see server running on http://localhost:5555. Open the URL and click through to your sandbox to see the visual counterpart of your narratives.

Next steps:

• Explore the kanban-todo example
• Join the Discord community

---

How It Works

flowchart LR
    A[Narratives] --> B[Domain Model]
    B --> C[Server Scaffold]
    B --> D[IA Schema]
    D --> E[Frontend Scaffold]
    C --> F[AI Implementation]
    E --> F
    F --> G[Quality Checks]
    G -->|Fail| F
    G -->|Pass| H[Production Code]

Loading

Narratives define your application as slices of behavior. The pipeline converts these to a domain model, scaffolds both server and frontend code with implementation hints, then AI agents implement the code. If tests fail, the AI receives error feedback and self-corrects. Passing code undergoes type checking, linting, and runtime validation.

---

Packages

Core

Package	Description
@auto-engineer/cli	Command-line interface for running Auto Engineer pipelines
@auto-engineer/pipeline	Command/event pipeline orchestration with projections and reactors
@auto-engineer/message-bus	In-process message bus for command dispatch and event publishing
@auto-engineer/message-store	Event persistence and replay for message bus
@auto-engineer/narrative	DSL for modeling application behavior as time-based flows
@auto-engineer/flow	Flow modeling utilities
@auto-engineer/id	Deterministic ID generation for pipeline correlation

Generators

Package	Description
@auto-engineer/server-generator-apollo-emmett	Apollo GraphQL + Emmett event-sourced server scaffolding
@auto-engineer/frontend-generator-react-graphql	React + GraphQL frontend scaffolding from schema
@auto-engineer/information-architect	AI-driven schema generation for UI/UX architecture
@auto-engineer/design-system-importer	Import and configure design system components
@auto-engineer/create-auto-app	Project scaffolding CLI with templates

Implementers

Package	Description
@auto-engineer/server-implementer	AI-powered server code implementation
@auto-engineer/frontend-implementer	AI-powered frontend code implementation
@auto-engineer/component-implementer	AI-powered UI component implementation

Utilities

Package	Description
@auto-engineer/ai-gateway	Multi-provider AI abstraction (Anthropic, OpenAI, Google, xAI)
@auto-engineer/dev-server	Development server with SSE events and pipeline visualization
@auto-engineer/file-store	File system operations with caching
@auto-engineer/server-checks	Server code validation (types, lint, tests)
@auto-engineer/frontend-checks	Frontend code validation (types, lint, tests)

---

Examples

Example	Description	Complexity
kanban-todo	Task management with drag-and-drop boards	Beginner
questionnaires	Survey builder with design system integration	Intermediate
support-files	Shared assets and design tokens	Reference

---

Development

Prerequisites

• Node.js 20.0.0+
• pnpm 8.15.4+
• AI Provider API Key (Anthropic, OpenAI, Google, or xAI)

Setup

git clone https://github.com/BeOnAuto/auto-engineer.git
cd auto-engineer
pnpm install
pnpm watch

Commands

Command	Description
pnpm watch	Build all packages in watch mode
pnpm build	Build all packages
pnpm test	Run all tests
pnpm check	Run type checking and linting

Working with Local Packages

To use local packages in example projects:

cd examples/kanban-todo
pnpm add '@auto-engineer/cli@workspace:*' '@auto-engineer/flow@workspace:*'

Testing

Write focused tests for single behaviors, cover edge cases, and aim for 80%+ coverage with pnpm test:coverage.

---

Contributing

Contributions welcome! See CONTRIBUTING.md for guidelines.

---

License

Elastic License 2.0 (EL2) - See LICENSE.md for details.