ArchGenie
Show HN: I built an AI cloud architect that ships working infrastructure
Last verified:
What is ArchGenie?
ArchGenie is an AI Cloud Architect that helps users create complete cloud solutions for AWS, Azure, and Google Cloud Platform. Users can describe their architecture in text, sketch it, or upload a screenshot/whiteboard photo, and ArchGenie generates a full cloud architecture package including an architecture diagram, validated infrastructure code, security grade with findings, cost estimates, observability setup, and comprehensive documentation—all in one interaction.
Key features include generating validated Terraform, Pulumi, or Bicep infrastructure code with file structure; A–F security grading with per-resource findings and automated fixes; per-resource cost breakdowns with optimization insights and a savings calculator comparing reserved, spot, and on-demand pricing; pre-configured observability with log groups, alarms, telemetry, and dashboards; comprehensive documentation with architecture diagrams and deployment guides; and one-click export to GitHub, GitLab, Bitbucket pull requests, or Jira issues. The platform also includes an inline code editor where changes propagate automatically across dependent files, and users can click any service on the diagram to remove, replace, or add high availability.
ArchGenie is designed for cloud architects, DevOps engineers, software developers, and technical teams who need to quickly design, secure, cost, and deploy cloud infrastructure. It supports architecture templates for web apps, data engineering, AI/ML, containers, networking, and security use cases including RAG pipelines, Agentic AI, model serving, data lakehouses, streaming + CDC, zero trust, and event-driven architectures. The tool is suitable for individuals starting with a free tier as well as teams and enterprises needing collaborative features, governance, and compliance support.
The platform supports hundreds of services per cloud provider across AI/ML, data engineering, web apps, containers, networking, event-driven architectures, and security. Kubernetes ecosystem diagrams and Firebase are also supported. Multi-turn refinement allows users to describe changes in the same chat, with only affected parts re-derived while the rest stays stable.
ArchGenie pricing
Pricing model: Freemium
Free tier: €0/month with 10 credits/month, architecture diagram generation, infra code generation (Terraform only), security scanning, 2 Git exports/month, 1 branch per chat. Pro tier: €29/mo (or €24/mo billed annually) with 100 credits/month, all infra code formats (Terraform, Pulumi, Bicep), full security findings with line navigation, unlimited Git exports, 3 branches per chat, inline code editing, ZIP and CSV downloads, unlimited projects, credit top-up packs. Team Pro: €39/seat/mo (or €390/seat billed annually) with 100 credits/seat/month pooled across team, everything in Pro for every member, admin dashboard with per-member usage, centralized billing, flexible seat management with prorating, unlimited team projects, team-shared templates, team activity log (30-day). Enterprise: Custom pricing with custom credit allocation, everything in Team Pro, SSO (SAML/OIDC), unlimited branches, Policy-as-Code (OPA/Rego) generation + enforcement, compliance framework packs (SOC 2, HIPAA, PCI-DSS, FedRAMP), audit log API with SIEM integration + AI-BOM provenance, dedicated support with SLA, compliance & custom contracts. No credit card required, cancel anytime. Prices exclude applicable taxes.
ArchGenie pros
- Generates complete cloud architecture from description, sketch, or screenshot
- Supports AWS, Azure, and GCP with hundreds of services per provider
- Outputs validated Terraform, Pulumi, and Bicep infrastructure code
- A–F security grade with per-resource findings and automated fixes
- Per-resource cost breakdown with optimization insights
- Savings calculator compares reserved, spot, and on-demand pricing
- Pre-configured observability with log groups, alarms, and dashboards
- Comprehensive documentation generated automatically with no drift
- Inline code editor with AI fix propagation across dependent files
- Click any diagram service to remove, replace, or add high availability
- One-click export to GitHub, GitLab, Bitbucket pull requests
- Creates Jira issues directly from security findings
- Architecture templates for RAG, Agentic AI, data lakehouses, zero trust
- 10 free credits/month with no credit card required
- Multi-turn refinement keeps unchanged parts stable
ArchGenie cons
- Free tier limited to Terraform only (Pulumi/Bicep require Pro)
- Free tier only 2 Git exports per month
- Free tier limited to 1 branch per chat
- Pro plan at €29/mo may be costly for individuals
- Cost estimates exclude cross-region data transfer and cross-cloud egress
- Cost estimates exclude third-party SaaS costs
- Missing SKUs from pricing database are marked but not estimated
- User must run deployment from their own pipeline with their credentials
Frequently asked questions about ArchGenie
What cloud providers does ArchGenie support?
ArchGenie supports AWS, Azure, and GCP with hundreds of supported services per provider. Each provider has dedicated service catalogs covering AI/ML, data engineering, web apps, containers, networking, event-driven architectures, and security. Kubernetes ecosystem diagrams and Firebase are also supported.
Does ArchGenie handle cloud deployment?
No. ArchGenie generates the code and exports it via Git PR, ZIP, or inline editor—you run the deployment from your own pipeline with your own credentials and state backend. Cloud credentials and Terraform state are never sent to ArchGenie. The only credentials held are OAuth tokens for Git providers (GitHub, GitLab, Bitbucket) and Jira, used to push code or create issues.
How is the security grade calculated?
The grade reflects the percentage of policy checks the architecture passes after automatic hardening has been applied—A at 90% or higher, B at 80%, C at 70%, D at 60%, F below. The breakdown is per-category (encryption, network, identity, logging, deletion-protection) so you see what drives the score. Lower grades indicate categories needing human judgement like customer-managed keys, IAM scoping, or network isolation choices automation cannot make.
How accurate are the cost estimates?
Pricing is sourced from each provider's pricing catalogue. Per-resource costs reflect machine type, instance family, region, and storage tier as declared in the generated code. The estimate covers the resources in the architecture but does not include cross-region data transfer, cross-cloud egress, or third-party SaaS costs. Where a SKU is missing from the underlying pricing database, the panel marks it explicitly so the gap is visible.
Is my data private and secure?
Generated code, diagrams, and chat history are stored in your account—only you (and your team workspace members, if shared) can read them. ArchGenie does not use your content to train AI models, and they contractually require the same of their third-party providers. You can delete your account and all associated data from Settings; personal data is removed within 30 days.
What infrastructure code formats are available?
ArchGenie generates Terraform, Pulumi, and Bicep. The Free tier includes only Terraform. The Pro tier unlocks all infrastructure code formats (Terraform, Pulumi, Bicep). Every file is validated and security-scanned before it reaches you.
How does multi-turn refinement work?
Multi-turn refinement works in the same chat—describe what to change (like 'add a Redis cache between the app and the database' or 'switch from RDS to Aurora') and only the parts that depend on the change are re-derived. The rest of the diagram, code, security findings, and cost estimate stay stable. Branching a chat lets you explore alternatives non-destructively.
Can I edit the generated code?
Yes—the Code Canvas includes a full code editor. Edit any file, save to re-validate, and apply automated fixes across single files or entire projects. Changes propagate automatically across dependent files.
How does Git export work?
Git export creates a branch and pull request with your infrastructure code files, README documentation, architecture and sequence diagrams, and cost summary. It supports GitHub, GitLab, and Bitbucket. You can also create Jira issues directly from findings.
How many credits do I need for a full generation?
A full generation (diagram, infrastructure code, documentation, security scan, and cost estimate) costs a few credits. The Free tier includes 10 credits/month—enough to generate several complete architectures. See the pricing section for full details on credit allocation per plan.