OEONOEOOO0EEEE1E0
Autonomous Multi-Agent AI System

One Prompt.
Complete Application.

8 specialized AI agents collaborate autonomously — designing, coding, testing, and deploying production apps across iOS, macOS, Web, Android, and ML. No human intervention required.

white-rabbit
$

0

Agent Skills

0+

Team Templates

0

Platforms

0

DB Targets

0

Runtime Modules

0

LLM Layers

System Architecture

Intelligent Orchestration

The Architect analyzes your prompt, assembles the optimal team, and orchestrates the entire lifecycle — from design to deployment.

Your PromptThe ArchitectProduct ManagerDesignerDeveloperQA EngineerDevOpsAgent RuntimeProduction
01

Prompt Analysis

The Architect dissects your prompt — detects project type, complexity, required platforms, and optimal team composition.

02

Team Assembly

Automatically selects from 13+ team templates. Each agent gets role-specific instructions, skills, and the best available LLM.

03

Autonomous Execution

Agents collaborate via EventBus and SharedMemory. PM writes specs → Designer creates mockups → Developer codes → QA tests.

04

Quality & Deploy

8-pass Supervisor system auto-fixes errors. Senior Developer handles escalations. Then auto-deploys to your chosen target.

Agent Teams

8 Specialized Agents

Not a single AI assistant — a full team of specialized agents, each with unique skills and capabilities.

👔
Product Manager

Analyzes requirements, writes PRDs, delegates tasks

🎨
UI/UX Designer

Creates mockups, design tokens, component specs

💻
Developer

Writes production code across all platforms

🧪
QA Engineer

Automated testing, edge cases, regression checks

🚀
DevOps

Build automation, deployment, CI/CD pipelines

🗄️
DB Architect

Schema design, ORM generation, migrations

🏗️
Senior Dev

Escalation handler for complex build errors

📐
The Architect

Meta-intelligence: optimizes the entire system

Agent Runtime

9 Runtime Modules

The infrastructure that makes multi-agent collaboration possible. Real-time communication, shared state, fault tolerance, and continuous learning.

📡

EventBus

Pub/sub event distribution

🧠

SharedMemory

Project-scoped KV store

💬

MessageBus

Agent-to-agent messaging

📦

ArtifactStore

File & code persistence

📋

AuditLog

Full action traceability

🔐

ApprovalGate

Human-in-the-loop checkpoints

🛡️

Resilience

Retry, fallback, checkpoint

📊

TaskDelegator

Sub-task orchestration

📚

LearningStore

Continuous improvement

📐

The Architect — Meta-Intelligence

An LLM-powered orchestrator that observes the entire system and intervenes at 4 lifecycle points: pre-task planning, inter-phase monitoring, post-task learning, and system evolution. It optimizes prompts, identifies risks, extracts lessons, and continuously improves team performance.

Prompt OptimizationRisk DetectionQuality ReviewSelf-Evolution
Quality Assurance

8-Pass Supervisor

Automated build → fix → rebuild cycle. 30+ regex patterns + LLM-powered error resolution. 90%+ success rate.

P1
Buildxcodebuild / npm run build
P2
Auto-Fix30+ regex patterns applied
P3
LLM FixContext-aware error resolution
P4
Re-buildIncremental rebuild
P5
Senior DevComplex error escalation
P6
QA GateFinal quality verification
DeployProduction deployment
30+
Auto-Fix Patterns
8
Max Review Passes
90%+
Success Rate
Cross-Platform

6 Platforms. One System.

Build for any platform from a single prompt. Auto-detection chooses the right frameworks and build pipeline.

📱

iOS

SwiftUI, UIKit

🖥️

macOS

SwiftUI, AppKit

🌐

Web

React, Next.js, Vue

🤖

Android

Jetpack Compose

⚙️

Backend

Python, Node, Go

🧠

ML/AI

PyTorch, TensorFlow

Design Engine

Construct & Construct Pro

AI-powered UI code generation. Describe your design — get production-ready code for any framework.

🔨

Construct

Claude Sonnet • 8 credits

Production UI code generation with 5 frameworks and 8 style presets.

ReactNext.jsSwiftUIComposeHTML
PRO

Construct Pro

Claude Opus + Self-Review • 20 credits

Premium quality with Opus generation + Sonnet review pass. Same frameworks, superior output.

glassmorphismneubrutalismdark_premiumapple_higminimalist

🎨 Figma Integration

Extract design tokens, components, and assets directly from Figma files.

🗄️ 10 DB Targets

Generate schemas, ORM models, migrations, and seed data for SQLite, Supabase, Firebase, Prisma, and more.

🖼️ Auto Icon Gen

9 visual styles, keyword-based colors. Auto-generates .icns and Assets.xcassets for native apps.

Deployment

5 Deploy Targets

From build to production in one step. Stable URLs, persistent projects, automatic triggering after QA passes.

Vercel

Instant web deployment with stable URLs

GitHub Pages

Static site hosting via GitHub

✈️

TestFlight

iOS/macOS beta distribution

💾

Local Install

Direct to /Applications

📧

Email

Share builds via email delivery

Mobile + Distributed

Your Phone is a Worker Node

The iOS app runs LLMs on-device with Metal GPU acceleration. Use your phone as a compute node in the distributed worker network.

N
Neo MobileWorker
Status● Connected
Tasks: 3 completed
Active Model
Qwen3.5 2B Q4
Metal GPU • 1.5 GB
LLM Layers
CloudGGUFCoreMLFM
Processing Task
Portfolio Site • React Dev
📊🤖⚙️

4-Layer LLM Architecture

L1

Cloud API

Remote

Claude Opus/Sonnet, GPT-4o — maximum capability

L2

llama.cpp (GGUF)

On-Device

Qwen3.5 2B/4B on Metal GPU — real-time inference

L3

Core ML

On-Device

Apple Neural Engine optimized models

L4

Foundation Models

Free

Apple's built-in ~3B model, iOS 26+ (free)

Worker Mode: Your phone connects to the orchestrator via WebSocket, receives tasks, and returns results using on-device or cloud LLMs.

Commander Mode: Full project management — create projects, manage teams, send tasks, monitor activity, deploy — all from your phone.

Comparison

Neo vs. Everyone Else

AI coding assistants help you write code. Neo builds, tests, and deploys complete applications autonomously.

FeatureNeoCursorCopilotv0Replit
True Multi-Agent Collaboration
Cross-Platform (iOS + Web + Android)
Autonomous End-to-End Pipeline
Auto Quality Assurance (8-pass)
Built-in Deployment
On-Device LLM (llama.cpp)
Distributed Worker Nodes
Self-Learning System
100% Local / Privacy Mode
BYOK (Bring Your Own Key)

Others assist with coding. Neo replaces the entire development team.

Command Line

White Rabbit CLI

"Follow the white rabbit." Full TUI dashboard with real-time agent activity. Built in Go.

zsh — rabbit
(\(\
( -.-) W H I T E R A B B I T
o_(")(") Follow the white rabbit.
 
┌─────────────────────────────────────────────────┐
│ Projects │ Agents │ Activity │
│ ▸ Portfolio Site │ 👔 PM ● │ ✓ PRD done │
│ E-commerce App │ 💻 Dev ◔ │ ◔ coding.. │
│ iOS Tracker │ 🎨 Design ● │ ✓ mockups │
│ ML Pipeline │ 🧪 QA ○ │ ○ waiting │
│ Backend API │ 🚀 DevOps ○ │ │
└─────────────────────────────────────────────────┘
> /quickstart "Build a recipe app" --target vercel
rabbit quickstart

Zero-config project creation

rabbit deploy

Deploy to any target

rabbit ollama

Manage local AI models

Real Results

Built by Neo. Running Now.

These apps were generated entirely by Neo — from a single prompt to a running application in /Applications.

F

FeedMe

Meal recommendation with AI

C

Comodore

Pomodoro timer, Turkish voice

Y

Yiyoo

Diet tracker + Claude Vision

M

Minty

Selfie to pixel art converter

100% LOCAL MODE

Complete Privacy. Zero Cloud.

Run entirely on your machine with Ollama. No API keys, no cloud calls, no data leaving your device. Your code stays yours — Neo generates standard source code, not locked-in proprietary formats.

Ollama PoweredNo API KeysAir-Gap ReadyStandard Code Output
🔒
BYOK
Bring Your Own Key
Use your API keys → 0 credit charge
Pricing

Start Free. Scale Infinitely.

Free tier with full local AI. BYOK for zero-cost cloud models. Credits per task, not per token.

Starter

Free
Credits50
Projects1
Agents3
ModelsOllama (local)
DeployLocal only
DesignBuiltin
Most Popular

Pro

$29/mo
Credits500
Projects10
Agents10
ModelsClaude + OpenAI
DeployAll channels
DesignConstruct + Figma

Premium

$79/mo
Credits1,000
Projects50
Agents20
ModelsAll (incl. Opus)
DeployAll + priority
DesignConstruct Pro

Business

Custom
CreditsUnlimited
ProjectsUnlimited
AgentsUnlimited
ModelsAll + SLA
DeployAll + custom
DesignAll + white-label

Credits are charged per task, not per token. Use your own API keys (BYOK) and pay 0 credits for LLM usage. Ollama is always free.

Ready to Build with
AI Agent Teams?

One prompt. 8 agents. Complete application. From idea to production — automatically.