HN Showcase
Back to browse
GitHub Repository

AI-powered cloud architecture - describe infrastructure in natural language, get Terraform, cost estimates, and compliance reports

30 starsPython

Cloudwright – validate, cost, and export cloud architectures from text

by xmpuspus·Mar 4, 2026·6 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainSolve My ProblemDark Horse

Natural language to cloud spec with compliance + cost, but cost accuracy needs work.

Strengths
  • •ArchSpec intermediate format eliminates format conversion friction between design phases.
  • •6 compliance frameworks + drift detection solves real multi-framework audit workload.
  • •Multi-cloud cost estimation at design time, not just post-deployment Infracost style.
Weaknesses
  • •Author admits cost accuracy and import fidelity are weak points; undermines core value prop.
  • •Competes with Brainboard, Pulumi Neo, Terraform in crowded IaC/design tooling space.
Target Audience

Cloud architects, DevOps engineers, infrastructure teams designing systems before deployment.

Similar To

Brainboard · Pulumi Neo · Infracost

Post Description

Most AI dev tools focus on code. Cloudwright focuses on the design phase — the gap where engineers currently use spreadsheets, ad-hoc Terraform, and tribal knowledge.

You describe an architecture in plain English. It produces a structured YAML spec (ArchSpec), then gives you:

- Compliance validation: HIPAA, PCI-DSS, SOC 2, FedRAMP, GDPR, Well-Architected - Per-component cost estimates across AWS, GCP, Azure, and Databricks - Terraform/CloudFormation/Mermaid/SBOM export - Drift detection (compare design vs deployed tfstate) - Security scanning (missing encryption, IAM wildcards, open 0.0.0.0/0) - Architecture Decision Record (ADR) generation

Benchmarked against raw Claude Sonnet 4.6 across 54 use cases: cloudwright wins on 6 of 8 metrics. Weakest areas are cost accuracy and import fidelity (both actively improving).

$ pip install cloudwright-ai[cli] $ cloudwright design "3-tier web app on AWS with Redis and RDS PostgreSQL" $ cloudwright validate spec.yaml --compliance hipaa $ cloudwright export spec.yaml --format terraform -o ./infra $ cloudwright security spec.yaml

112 services across 4 providers. 17 starter templates. Pure Python, MIT licensed, no cloud credentials required for design/validate/export.

The Databricks provider was the hardest to build — it's an overlay platform (runs on top of AWS/Azure), uses DBU-based pricing instead of per-hour instances, and has no CloudFormation support. Happy to talk through any of the design tradeoffs.

Similar Projects