WHY HARPER

AI Coding, Enterprise Discipline

Harper gives coding agents a unified runtime so applications ship fast and scale to billions of low-latency interactions per day.

Ship Fast

The Harper unified runtime eliminates infrastructure overhead by design, accelerating time to market so teams can turn ideas into revenue faster. Say goodbye to glue code, service orchestration, or manual wiring that alternative architectures require.

Go to Repo

Strategic Scale

Harper Fabric deploys your application across distributed geographies in minutes, increasing capacity, throughput, and resilience while driving down average global latency as new regions come online.

Sign Up for Fabric

Enterprise Proven

Platform-level system design operationalize enterprise best practices, so AI-generated applications are built on scalable, resilient, open source foundation already trusted by the world’s largest enterprises.

Platform-Grade Runtime

Harper gives coding agents a complete high-performance runtime to build with, no stitching, no orchestration, no architectural drift.

TYPICAL
ARCHITECTURE

Architecture

Unified runtime

Assembled multi-service stack

P95 Latency Server Latency

1-10 ms

50-200 ms

Production Readiness

Includes all services

Requires integration and orchestration

Deployment Model

Native multi-region with Fabric

Single-region default, multi-region complex

Scaling

Elastic and horizontal

Manual scaling across services

Pub/Sub

Built in

Requires additional services

In-Memory Cache

Built in

Requires additional services

Vector Search

Built in

Requires additional services

Blob Storage

Built in

Requires additional services

Operational Complexity

Minimal

High coordination overhead

Open Source

Yes

Varies

GET STARTED

How to Vibe Code with Harper

Select Your Agent ↓

Terminal

$ npm create harper@latest

? Project name: my-app
? Select a template: react-ts

✓ Scaffolding project in ./my-app
✓ Schema, config, and resources ready
✓ 12 Harper skills included

$ cd my-app && ls skills/

adding-tables-with-schemas.md caching.md
automatic-apis.md custom-resources.md
vector-indexing.md real-time-apps.md
defining-relationships.md checking-authentication.md
querying-rest-apis.md using-blob-datatype.md
deploying-to-harper-fabric.md typescript-type-stripping.md

Claude Code

$ cd my-app
$ claude

Claude: reads schema.graphql, config.yaml, resources/, and skills/ on startup.

‍> Add vector search to the product table with semantic similarity on descriptions

✓ Updated schema.graphql | description: [Float] @indexed(type: "HNSW")
✓ Created resources/search.ts using Harper's native vector search API
✓ No external vector DB — runs in-process

OpenAI Codex

$ cd my-app
$ codex

Codex: indexes the full project including skills/ for Harper-specific patterns.

‍> Set up a caching layer that pulls inventory data from our existing REST API

✓ Updated schema.graphql | type Inventory @table @cache(expiration: 3600)
✓ Created resources/inventory.ts get() fetches from external API, Harper caches
✓ ETag + stampede prevention built in

Google Antigravity

$ cd my-app
$ antigravity

Antigravity: loads skills/ alongside your schema and resource definitions.

‍> Add real-time order notifications over WebSocket when orders are created

✓ Updated resources/orders.ts publish('orders', record) on POST
✓ Created client/useOrders.ts subscribes via Harper's native pub/sub
✓ No message broker — WebSocket built in

Use Your Own AI Agent

Skills teach any AI coding agent the full Harper runtime.

1

Scaffold

npm create harper@latest generates a full project structure with an included skills/ folder that grounds your agent in Harper's architecture.

2

Launch

Claude Code, OpenAI Codex, and Google Antigravity all read project-level files as context. The skills/ directory is picked up automatically. No setup needed.
Works with any agent that reads project files for context.

3

Build

Your agent knows the exact syntax for vector search, real-time pub/sub, caching, authentication, deployment, and more. No multi-service architecture, no drift.

npm create harper

View Repo on GitHub

Try Harper Agent

OPEN ALPHA

A CLI-based AI coding agent for Harper app creation and management. Harper Agent understands the Harper runtime — schemas, directives, resource classes, and deployment workflows — so generated applications align with platform conventions from the start.

Bring your own model API key. Harper Agent supports OpenAI, Anthropic, Google Gemini, and local models via Ollama.

Generates Harper schemas, resources, and config grounded in runtime conventions

Detects existing Harper projects and works within established structure

Supports session persistence for long-running development workflows

Non-interactive mode for piping prompts from specs or task files

Install Harper Agent

Terminal

# Install globally
$ npm install -g @harperfast/agent

# Start in your project directory
$ harper-agent

Working directory: ~/Code/my-app
Harper app detected: Yes

Harper: What do you want to do together today?

> Create a support knowledge base that stores documents as blobs, indexes them with vector embeddings for semantic search, and pushes new article alerts via pub/sub.

# Or pipe a spec non-interactively
$ cat spec.md | harper-agent

Enterprise Vibe Coding Runtime

AI Coding, Enterprise Discipline

Ship Fast

Strategic Scale

Enterprise Proven

Platform-Grade Runtime

How to Vibe Code with Harper

Use Your Own AI Agent

Scaffold

Launch

Build

Try Harper Agent

Vibe Code.
Ship Fast.
Scale Globally.

Enterprise Vibe Coding Runtime

AI Coding, Enterprise Discipline

Ship Fast

Strategic Scale

Enterprise Proven

Platform-Grade Runtime

How to Vibe Code with Harper

Use Your Own AI Agent

Scaffold

Launch

Build

Try Harper Agent

Vibe Code.Ship Fast.Scale Globally.

Vibe Code.
Ship Fast.
Scale Globally.