Early DevelopmentAlpha testers only.Join our Discord
Alpha Preview — Agent-Native Generative Execution Environment

Define your vision.
Agents build the reality.

The self-building application framework where autonomous AI agents create, connect, and extend production-ready applications. No manual configuration required. Define your services, agents, and MCP servers in one file. Run one command. Get a fully operational platform with AI agents that can deploy, debug, and build alongside you.

MCP-native
Auto-discovery
Docker deployment

Install the CLI

$curl https://angee.ai/install.sh | sh

Requires Docker. View on GitHub

Why teams choose ANGEE

Stop hand-wiring applications. ANGEE shifts development from manual configuration to autonomous agent orchestration.

Self-building applications

Describe what you need in natural language. ANGEE's agents autonomously scaffold, wire, and deploy production-ready Django apps — complete with REST endpoints, WebSocket channels, and background tasks.

Zero-config architecture

Apps self-register routes, WebSocket consumers, and Celery tasks on startup. No central routing files, no manual wiring. Drop in an app, and the framework discovers everything.

MCP-native agents

Every agent runs in isolated Docker containers with full MCP (Model Context Protocol) integration. Connect Claude, Cursor, or any MCP client directly to your running ANGEE instance.

Enterprise-grade stack

Built on Django 6, PostgreSQL 17 with pgvector, Redis, and Celery. Real-time streaming via WebSockets, encrypted secrets management, and role-based access out of the box.

How ANGEE works

From natural language to production-ready applications in four steps

01

Define

Tell ANGEE what you need

Describe your application requirements in natural language or compose from pre-built ecosystem apps. ANGEE's orchestration layer breaks it down into actionable agent tasks.

User → Agent Template → Workspace
02

Build

Agents scaffold autonomously

AI agents run in isolated Docker containers, scaffolding Django apps with REST endpoints, WebSocket consumers, background tasks, and database migrations — all auto-discovered by the framework.

Agent → Docker → MCP → Code
03

Connect

Apps self-wire into the platform

Each app declares its capabilities via AppConfig attributes. The framework auto-mounts routes, registers WebSocket channels, and schedules Celery tasks. Zero manual routing files.

AppConfig → Auto-Register → Live
04

Extend

Grow your ecosystem

Every app agents build becomes part of your ecosystem. Compose new applications from existing building blocks, or let agents create entirely new ones. The platform grows with you.

Ecosystem → Compose → Scale

Three-layer architecture

Apps, Agents, and Ecosystem — each layer is independent yet deeply integrated

Apps

Modular building blocks

Self-registering Django packages that declare REST endpoints, WebSocket consumers, and Celery tasks. The framework auto-discovers and mounts everything.

  • Auto-route registration
  • WebSocket consumers
  • Celery task scheduling
  • Database migrations

Agents

Autonomous AI workers

Run in isolated Docker containers with MCP integration. Stream live output to the frontend via WebSockets. Composable from templates, workspaces, and tool definitions.

  • Docker isolation
  • MCP protocol
  • Live WebSocket streaming
  • Tool registry

Ecosystem

Community-powered growth

Pre-built apps and agent-created apps form a growing library. Auth, real-time updates, encrypted secrets, and background jobs are handled by the platform core.

  • Pre-built platform apps
  • Agent-generated apps
  • Shared tool registry
  • Composable templates

Platform Architecture

How the layers connect

MCP Server /mcp/
Agent Templates
Workspaces
Docker Runtime
REST API & WebSocket
Celery Tasks
PostgreSQL + Redis

Growing ecosystem

Pre-built platform apps and ecosystem modules, ready to compose or extend with agents

Platform Core

Foundation services
agents

AI agent orchestration, templates, workspaces, container runtimes, MCP, tool registry

accounts

User model with email-based auth and SqidsField for public IDs

connect

OAuth and API credential management per platform

secrets

Encrypted credential storage with Fernet encryption

core

Shared utilities, middleware, health checks

Ecosystem Apps

Pre-built modules
unibox

Unified messaging across email, SMS, WhatsApp, Telegram, Discord, Slack, Instagram, Twitter, Signal

nexus

Contact and group management with tagging, deduplication, and trait tracking

Battle-tested tech stack

Built on proven open-source foundations, not proprietary lock-in

Backend

Python 3.14Django 6.0DRFCeleryDjango ChannelsPostgreSQL 17pgvectorRedis

Frontend

React 19TypeScriptVite 7Tailwind 4React Query 5React Router 7

Infrastructure

Docker Composeuvjustruffmypypytest

Pricing that scales with you

Start free with self-hosting. Scale to managed cloud when you need it.

Open Source

Full framework for teams with in-house DevOps

Free/ forever
  • Complete source code access
  • Docker Compose deployment
  • All core apps & agent framework
  • Community ecosystem apps
  • Community support
  • Bring your own LLM

Cloud

Fully managed ANGEE on dedicated infrastructure

Coming soon/ forever
  • Dedicated cloud deployment
  • SSO & team management
  • Managed updates & monitoring
  • Priority agent scheduling
  • Premium support & onboarding
  • Custom app development

Enterprise

White-glove deployment with compliance controls

Contact us/ forever
  • On-premises or private cloud
  • Role-based access policies
  • Audit logs & compliance tools
  • Dedicated account manager
  • Custom integrations & SLA
  • Training & knowledge transfer

Frequently asked questions

Everything you need to know about ANGEE

What exactly is ANGEE?

How is this different from other AI coding tools?

What is MCP and why does it matter?

What tech stack does ANGEE use?

Can I use my existing Django apps with ANGEE?

How does the auto-discovery architecture work?

Is ANGEE production-ready?

Ready to let agents build for you?

Request early access to the self-building application framework that turns your ideas into production-ready applications.