How vaibhavburad15/infra-genie works
InfraGenie is an AI infrastructure-analysis and deployment platform. Users upload a project or provide a repository, receive static and multi-agent analysis plus generated infrastructure artifacts, review and approve a deployment, then monitor it and use AI assistance. The graph preserves the documented artifact, security, cost, and observability capabilities. Backend task and route relationships are supported by the excerpts and SOURCE INDEX; several UI and feature modules were not sampled, so their internal wiring is not inferred.
Main entry points: App.tsx Application shell · main.py FastAPI service · tasks.py Analysis and deploy tasks · api.ts API client
Components 23
Product interface
- Application shell
frontend/src/App.tsx - API client
frontend/src/api.ts - Project workspace
frontend/src/pages/ProjectsPage.tsx - Deployment review
frontend/src/pages/DeploymentReviewPage.tsx - Cloud accounts
frontend/src/pages/CloudAccountsPage.tsx - Feature dashboards
frontend/src/pages - AI assistant
frontend/src/components/AIAssistant.tsx
API and persistence
- FastAPI service
backend/main.py - Domain models
backend/models.py - Agent registry API
backend/agent_routes.py - Cloud account API
backend/cloud_routes.py - Discovery API
backend/discovery_routes.py
Analysis and generation
- Background worker
backend/worker.py - Analysis and deploy tasks
backend/tasks.py - Static analysis
backend/static_analysis.py - Specialist agents
backend/agents.py - Deployment planner
backend/deployment_planner.py - LLM client
backend/llm.py
Cloud and deployment
- AWS connection service
backend/aws_connection.py - AWS discovery
backend/aws_discovery.py - Customer AWS account
Other components
- User
- OpenAI-compatible LLM
Connections 32
- User → Application shell: uses
- Application shell → Project workspace: routes to
frontend/src/App.tsx - Application shell → Deployment review: routes to
frontend/src/App.tsx - Application shell → Cloud accounts: routes to
frontend/src/App.tsx - Application shell → Feature dashboards: routes to
frontend/src/App.tsx - Application shell → AI assistant: renders
frontend/src/App.tsx - Project workspace → API client: uses API
- Deployment review → API client: uses API
- Cloud accounts → API client: uses API
- API client → FastAPI service: calls
- FastAPI service → Domain models: persists
backend/main.py - FastAPI service → Analysis and deploy tasks: queues analysis
backend/main.py - FastAPI service → Agent registry API: registers routes
backend/main.py - FastAPI service → Cloud account API: registers routes
backend/main.py - FastAPI service → Discovery API: registers routes
backend/main.py - Agent registry API → Domain models: reads configuration
backend/agent_routes.py - Cloud account API → AWS connection service: verifies accounts
backend/cloud_routes.py - Discovery API → AWS discovery: runs scans
backend/discovery_routes.py - AWS discovery → AWS connection service: uses credentials
backend/aws_discovery.py - AWS connection service → Customer AWS account: assumes role
- Background worker → Analysis and deploy tasks: executes
backend/worker.py - Analysis and deploy tasks → Static analysis: analyzes source
backend/tasks.py - Analysis and deploy tasks → Specialist agents: runs pipeline
backend/tasks.py - Analysis and deploy tasks → Deployment planner: plans deployment
backend/tasks.py - Specialist agents → LLM client: requests completions
backend/agents.py - LLM client → OpenAI-compatible LLM: sends prompts
backend/llm.py - Deployment planner → AWS connection service: uses AWS connection
backend/deployment_planner.py - User → Cloud accounts: connects account
- User → Project workspace: submits project
- Analysis and deploy tasks → Domain models: stores results
backend/tasks.py - Deployment planner → Customer AWS account: provisions infrastructure
- Feature dashboards → API client: requests insights