# AIVory

> Real-time compliance & security validation for developers, plus an OpenAI-compatible inference router that routes every request to the cheapest working provider. Catch violations as code is written, not after deployment - and pay less for inference while you do.

AIVory builds three products for AI-era developers: Guard (IDE compliance scanning), Architect (visual cloud infrastructure), and Smart Inference (OpenAI-compatible cheapest-provider routing with a GPU spot marketplace). Special focus on AI-generated code, with 17 compliance standards supported.

## Products

### AIVory Guard
Real-time compliance scanning for IDEs and AI coding agents.
- JetBrains Plugin: https://plugins.jetbrains.com/plugin/28745-aivory/
- VS Code Extension: https://marketplace.visualstudio.com/items?itemName=AIVory.aivory
- Cursor Extension: https://open-vsx.org/extension/aivory/aivory
- Antigravity Extension: https://open-vsx.org/extension/aivory/aivory
- Claude Code Plugin: https://aivory.net/docs/guard/claude-code/
- MCP Server (npm): https://www.npmjs.com/package/@aivorynet/guard
- Product page: https://aivory.net/guard/

### AIVory Architect
Visual cloud infrastructure IDE with drag-and-drop design and Terraform generation.
- JetBrains Plugin: https://plugins.jetbrains.com/plugin/29206-aivory-architect/
- VS Code Extension: https://marketplace.visualstudio.com/items?itemName=AIVory.aivory-architect
- Cursor Extension: https://open-vsx.org/extension/aivory/aivory-architect
- Multi-cloud support: AWS, Azure, GCP, Hetzner Cloud, RunPod, DeepInfra
- One-click Terraform code generation
- Integrated deployment and Kubernetes management
- Product page: https://aivory.net/architect/

### AIVory Smart Inference
OpenAI-compatible HTTP gateway that routes every request to the cheapest working provider at that moment. Change your `base_url`, keep the same SDK and model names, pay less.
- Cheapest-first routing, scored per request, with automatic fallback if a provider fails
- Pay as you go - top up from $10, default $100 monthly cap (adjustable)
- Per-request receipts: cost, chosen model, routing score, and latency on every response
- 16 models available including Llama 4, DeepSeek V4, Qwen 3.5, Gemma 4, Mixtral, Mistral, and Voxtral (audio/speech)
- API base URL: https://smart.aivory.net/v1
- Product page: https://aivory.net/smart-inference/
- All models with live pricing: https://aivory.net/si-models/
- Docs: https://aivory.net/docs/smart-inference/

### GPU Spot Marketplace
Rent spot GPUs on demand through the Smart Inference API. Browse live offers from multiple providers, spin up a GPU in one API call, pay by the second.
- Spot pricing — typically 60-80% cheaper than on-demand
- One API call to browse offers and rent a GPU
- Same API key and billing as Smart Inference
- Live pricing comparison: https://aivory.net/smart-inference/cheap-gpu/
- GPU models with dedicated pages: H100, H200, A100, A6000, L40S, RTX 5090, RTX 4090, RTX 3090, V100
- Example: https://aivory.net/smart-inference/cheap-gpu/h100/
- Docs: https://aivory.net/docs/smart-inference/gpu/

## Compliance Standards Supported

### Security & Privacy
- OWASP Top 10
- GDPR, DSGVO
- HIPAA, CCPA
- PCI-DSS

### Service & Management
- SOC 2
- ISO 27001, 27017, 27018
- TISAX

### EU Regulations
- DORA
- NIS2
- EU AI Act

### Financial
- AML, Geldwäschegesetz

## Documentation

- Docs Home: https://aivory.net/docs/
- Guard Docs: https://aivory.net/docs/guard/
  - JetBrains Plugin: https://aivory.net/docs/guard/plugin/
  - VS Code Extension: https://aivory.net/docs/guard/vscode-extension/
  - Cursor Extension: https://aivory.net/docs/guard/cursor-extension/
  - Antigravity Extension: https://aivory.net/docs/guard/antigravity-extension/
  - Claude Code Plugin: https://aivory.net/docs/guard/claude-code/
  - MCP Integration: https://aivory.net/docs/guard/mcp/
  - AI Agent Integrations: https://aivory.net/docs/guard/ai-agent-integrations/
  - Dashboard: https://aivory.net/docs/guard/dashboard/
- Architect Docs: https://aivory.net/docs/architect/
  - Getting Started: https://aivory.net/docs/architect/getting-started/
  - Setup Wizard: https://aivory.net/docs/architect/setup-wizard/
  - Designer: https://aivory.net/docs/architect/designer/
  - Infrastructure Management: https://aivory.net/docs/architect/infrastructure-management/
  - Terraform: https://aivory.net/docs/architect/terraform/
  - Kubernetes: https://aivory.net/docs/architect/kubernetes/
  - Docker: https://aivory.net/docs/architect/docker/
  - Credential Vault: https://aivory.net/docs/architect/credential-vault/
  - JetBrains Plugin: https://aivory.net/docs/architect/plugin/
  - VS Code Extension: https://aivory.net/docs/architect/vscode-extension/
  - Cursor Extension: https://aivory.net/docs/architect/cursor-extension/
  - Antigravity Extension: https://aivory.net/docs/architect/antigravity-extension/
- Smart Inference Docs: https://aivory.net/docs/smart-inference/
  - Getting Started: https://aivory.net/docs/smart-inference/getting-started/
  - API Reference: https://aivory.net/docs/smart-inference/api/
  - OpenAI Compatibility: https://aivory.net/docs/smart-inference/api/compatibility/
  - Models: https://aivory.net/docs/smart-inference/models/
  - Routing: https://aivory.net/docs/smart-inference/routing/
  - Headers: https://aivory.net/docs/smart-inference/headers/
  - Billing: https://aivory.net/docs/smart-inference/billing/
  - Errors: https://aivory.net/docs/smart-inference/errors/
  - GPU Spot Marketplace: https://aivory.net/docs/smart-inference/gpu/
  - GPU API Reference: https://aivory.net/docs/smart-inference/gpu/api/
  - GPU Billing: https://aivory.net/docs/smart-inference/gpu/billing/

## Model Landing Pages

Individual pages with live pricing for each supported model:
- All Models: https://aivory.net/si-models/
- DeepSeek V3.2: https://aivory.net/si-models/deepseek-v3-2/
- DeepSeek V4 Flash: https://aivory.net/si-models/deepseek-v4-flash/
- Gemma 4 31B: https://aivory.net/si-models/gemma-4-31b/
- Gemma 2 9B: https://aivory.net/si-models/gemma2-9b/
- Llama 4 Maverick: https://aivory.net/si-models/llama-4-maverick/
- Llama 4 Scout: https://aivory.net/si-models/llama-4-scout/
- Llama 3.3 70B: https://aivory.net/si-models/llama-3-3-70b/
- Qwen 3 235B: https://aivory.net/si-models/qwen-3-235b/
- Qwen 3.5 27B: https://aivory.net/si-models/qwen-3-5-27b/
- Qwen 2.5 72B: https://aivory.net/si-models/qwen-2-5-72b/
- Mixtral 8x7B: https://aivory.net/si-models/mixtral-8x7b/
- Mistral Nemo 12B: https://aivory.net/si-models/mistral-nemo-instruct/
- Mistral Small 24B: https://aivory.net/si-models/mistral-small-24b-2501/
- Mistral Small 3.2 24B: https://aivory.net/si-models/mistral-small-3-2-24b-2506/
- Voxtral Mini 3B (audio): https://aivory.net/si-models/voxtral-mini-3b-2507/
- Voxtral Small 24B (audio): https://aivory.net/si-models/voxtral-small-24b-2507/

## GPU Landing Pages

Individual pages with live spot pricing for each GPU model:
- All GPUs: https://aivory.net/smart-inference/cheap-gpu/
- H100: https://aivory.net/smart-inference/cheap-gpu/h100/
- H200: https://aivory.net/smart-inference/cheap-gpu/h200/
- A100: https://aivory.net/smart-inference/cheap-gpu/a100/
- A6000: https://aivory.net/smart-inference/cheap-gpu/a6000/
- L40S: https://aivory.net/smart-inference/cheap-gpu/l40s/
- RTX 5090: https://aivory.net/smart-inference/cheap-gpu/rtx-5090/
- RTX 4090: https://aivory.net/smart-inference/cheap-gpu/rtx-4090/
- RTX 3090: https://aivory.net/smart-inference/cheap-gpu/rtx-3090/
- V100: https://aivory.net/smart-inference/cheap-gpu/v100/
- B200: https://aivory.net/smart-inference/cheap-gpu/b200/
- B300: https://aivory.net/smart-inference/cheap-gpu/b300/
- MI300X: https://aivory.net/smart-inference/cheap-gpu/mi300x/
- L4: https://aivory.net/smart-inference/cheap-gpu/l4/
- L40: https://aivory.net/smart-inference/cheap-gpu/l40/
- T4: https://aivory.net/smart-inference/cheap-gpu/t4/
- A10G: https://aivory.net/smart-inference/cheap-gpu/a10g/
- A40: https://aivory.net/smart-inference/cheap-gpu/a40/
- RTX 6000 Ada: https://aivory.net/smart-inference/cheap-gpu/rtx-6000-ada/
- RTX 5000 Ada: https://aivory.net/smart-inference/cheap-gpu/rtx-5000-ada/
- RTX 4000 Ada: https://aivory.net/smart-inference/cheap-gpu/rtx-4000-ada/
- RTX PRO 6000: https://aivory.net/smart-inference/cheap-gpu/rtx-pro-6000/
- RTX A5000: https://aivory.net/smart-inference/cheap-gpu/rtx-a5000/
- RTX A4000: https://aivory.net/smart-inference/cheap-gpu/rtx-a4000/
- RTX A4500: https://aivory.net/smart-inference/cheap-gpu/rtx-a4500/
- RTX PRO 4500: https://aivory.net/smart-inference/cheap-gpu/rtx-pro-4500/
- RTX 5080: https://aivory.net/smart-inference/cheap-gpu/rtx-5080/
- RTX 4080: https://aivory.net/smart-inference/cheap-gpu/rtx-4080/
- RTX 3080: https://aivory.net/smart-inference/cheap-gpu/rtx-3080/
- RTX 2000 Ada: https://aivory.net/smart-inference/cheap-gpu/rtx-2000-ada/
- RTX 3070: https://aivory.net/smart-inference/cheap-gpu/rtx-3070/
- RTX 4070 Ti: https://aivory.net/smart-inference/cheap-gpu/rtx-4070-ti/
- RTX A2000: https://aivory.net/smart-inference/cheap-gpu/rtx-a2000/

## AI Agent Integrations (Guard)
Guides for integrating Guard with AI coding assistants:
- Claude Code: https://aivory.net/docs/guard/ai-agent-integrations/claude-code/
- Cursor: https://aivory.net/docs/guard/ai-agent-integrations/cursor/
- Windsurf: https://aivory.net/docs/guard/ai-agent-integrations/windsurf/
- GitHub Copilot CLI: https://aivory.net/docs/guard/ai-agent-integrations/github-copilot-cli/
- Aider: https://aivory.net/docs/guard/ai-agent-integrations/aider/
- OpenAI: https://aivory.net/docs/guard/ai-agent-integrations/openai/
- DeepSeek: https://aivory.net/docs/guard/ai-agent-integrations/deepseek/
- Gemini CLI: https://aivory.net/docs/guard/ai-agent-integrations/gemini-cli/
- Generic MCP Setup: https://aivory.net/docs/guard/ai-agent-integrations/other/

## Key URLs

- Website: https://aivory.net/
- Dashboard/App: https://app.aivory.net/
- Try Free (overview): https://aivory.net/try-free/
- Try Guard Free: https://aivory.net/try-free-guard/
- Try Architect Free: https://aivory.net/try-free-architect/
- Guard Premium Plans: https://app.aivory.net/register/plans
- Architect Premium Plans: https://app.aivory.net/architect/plans
- About: https://aivory.net/about/
- Contact: https://aivory.net/contact/
- Support/FAQ: https://aivory.net/support/
- Privacy Policy: https://aivory.net/dataprivacy/
- Terms of Service: https://aivory.net/terms/

## Machine-Readable Page Content

Every page on aivory.net is also available as Markdown by appending `/md/` to the URL (e.g. https://aivory.net/guard/md/, https://aivory.net/docs/smart-inference/md/). Use these when you want the page body without HTML chrome.

## Contact

- Support: aivee@aivory.net
- Sales & General: contact@aivory.net
- GitHub: https://github.com/aivorynet/
- Twitter/X: https://x.com/aivory_net
- LinkedIn: https://www.linkedin.com/company/aivory-net/
- Discord: https://discord.com/invite/QMucsXSjNQ

## Company

Founded by Paul Piper and Jennifer Brehm. Enterprise developers with 20+ years of collaboration and extensive experience in developer tooling, AI, and compliance.

## Pricing

- **Guard** - Free tier covers OWASP Top 10 scanning; Premium adds full compliance standards + dashboard; Enterprise adds custom standards, SSO, and dedicated support.
- **Architect** - Free tier for individual use; Premium adds team features and managed deployment; see https://app.aivory.net/architect/plans.
- **Smart Inference** - Pay as you go, top up from $10, default $100 monthly cap (adjustable). Per-request pricing varies by chosen model and routed provider; see https://aivory.net/smart-inference/ for the live model table.

## Technical

- Guard: no source code leaves your IDE - scanning is local
- MCP (Model Context Protocol) server for AI agent integration
- Real-time validation with instant feedback
- Audit trails for compliance reporting
- Smart Inference: OpenAI-compatible REST API at https://smart.aivory.net/v1, scored cheapest-first routing with automatic provider fallback
- GPU Spot Marketplace: rent spot GPUs via API, pay by the second, same billing as inference