ObjectStack Protocol

The AI-native business backend protocol for structured, auditable agent execution.

ObjectStack is the AI-native business backend for building enterprise applications that agents can understand, operate, and audit safely. Define business objects, permissions, workflows, APIs, UI metadata, and agent tools once as structured Zod metadata — ObjectStack handles the runtime surface.

ObjectStack is not another low-code UI builder. It is the structured execution layer for AI-native business software: agent-ready, permission-aware, versioned, and auditable.

Built for AI, not retrofitted. A typical enterprise application is tens of thousands of lines of CRUD, forms, queries, permissions, and API glue. ObjectStack collapses the same surface into a few hundred lines of typed metadata — roughly two orders of magnitude less code to read, write, and maintain. The point isn't lines of code; the point is fit in an agent's context window, so an AI agent can reason about the whole system end-to-end and safely refactor across data, API, UI, and permissions in a single change.

npx create-objectstack my-app && cd my-app && pnpm dev

Open http://localhost:3000/_studio/ to browse objects, test APIs, inspect metadata, and review the agent-ready tool surface.

Learn

New to ObjectStack? Start here.

Quick Start

Create a project, define objects, launch the Studio — in 5 minutes.

Core Concepts

AI-native metadata, design principles, and naming conventions.

Architecture

The three-layer protocol stack: ObjectQL, ObjectOS, ObjectUI.

Example Apps

Run the Todo, CRM, and BI examples to learn hands-on.

Package Overview

Complete guide to all 51 packages: core, services, drivers, plugins, and adapters.

Build

Task-oriented guides for building real applications.

Data Modeling

Design objects, fields, relationships, and validation rules.

Business Logic

Workflows, approval flows, triggers, and formulas.

Security

Profiles, permissions, sharing rules, and row-level security.

AI Capabilities

AI agents, generated tools, RAG pipelines, and natural language queries.

AI Skills System

Structured knowledge modules for intelligent code generation.

Plugin Development

Build, test, and publish custom plugins.

API & Client SDK

REST, GraphQL, WebSocket APIs, and frontend integration.

Understand

Deep protocol specifications for implementers and architects.

ObjectQL — Data

Schema, state machines, query syntax, and security.

ObjectUI — Interface

Layout DSL, widget contracts, and actions.

ObjectOS — System

Lifecycle, HTTP/realtime, plugins, and config.

Look Up

Auto-generated schema reference and quick-lookup cheatsheets.

Schema Reference

Auto-generated docs for every Zod schema in the protocol.

Cheatsheets

Field types, query syntax, error codes, and permissions at a glance.

CLI Reference

All commands: init, generate, serve, studio, compile, validate.

Glossary

Key terminology across all 15 protocol namespaces.

Who is this for?

Audience	Use Case
AI Agent Developers	Give agents a structured, permission-aware backend for real business actions
Platform Architects	Build internal developer platforms (IDP) that expose safe business capabilities
Protocol Implementers	Write new Drivers for ObjectQL or Renderers for ObjectUI
Internal Tool Builders	Ship CRUD-heavy business apps with generated APIs, UI metadata, and workflows