Iris Docs
Technical
Platform Architecture
Understanding the core components and design of the Iris platform
Last updated: December 2024
🏗️ Platform Architecture
Iris consists of four main components that work together to provide a complete AI agent development platform:
🔧 Backend API
Python/FastAPI service with REST endpoints, thread management, agent orchestration, and LLM integration via LiteLLM
🖥️ Frontend Dashboard
Next.js/React application with chat interfaces, agent configuration dashboards, and monitoring tools
🐳 Agent Runtime
Isolated Docker execution environments with browser automation, code interpreter, and security sandboxing
🗄️ Database & Storage
Supabase-powered data layer with authentication, user management, and real-time subscriptions
🚀 Technology Stack
Modern technologies powering the Iris platform:
Frontend
Next.js 15+
App Router with TypeScript
Tailwind CSS
Utility-first styling
Radix UI
Accessible component primitives
Backend
FastAPI
Modern Python web framework
LiteLLM
Multi-provider LLM integration
Dramatiq
Background job processing
Infrastructure
Supabase
Database and authentication
Redis
Caching and message broker
Docker
Containerization and isolation
🔄 Data Flow
How information moves through the Iris platform:
1
User Interaction
User sends request through frontend interface
2
API Processing
FastAPI backend processes request and authenticates user
3
Agent Execution
Agent runs in isolated Docker environment with access to tools
4
Real-time Updates
Results streamed back to frontend via Supabase subscriptions
🔒 Security Architecture
Multi-layered security approach:
🛡️ Authentication
JWT-based authentication with Supabase Auth, secure session management
🔐 Authorization
Row-level security policies, fine-grained access control
🏗️ Isolation
Docker containers for agent execution, network segmentation
🔑 Secrets Management
Encrypted storage of API keys and sensitive configuration
🚀 Deployment Options
Flexible deployment strategies for different use cases:
🐳 Docker Compose
Single-machine deployment with all services
☸️ Kubernetes
Scalable orchestration for production workloads
☁️ Cloud Native
Serverless functions with managed services