Resources
Free tools, checklists, and references for sovereign AI teams.
Practical resources for engineers and architects building private AI systems. No signup, no paywall. Use them, share them, build with them.
Free Resources
Tools for readiness, architecture, cost, model choice, evaluation, and deployment planning.
These resources cover the questions that come up in sovereign AI projects: Are we ready? How does the system work? What will it cost? Which model and hardware should we use? How do we evaluate and deploy safely?
Hardware-to-Model Matchmaker
Pick your GPU — or enter your VRAM — and instantly see which open-weight LLMs you can self-host, at which quantization, with how much headroom. Covers Llama, Mistral, Qwen, DeepSeek, Gemma, Phi, and more.
EU AI Act Risk Checker
Run a versioned orientation covering EU scope, operator role, prohibited practices, intended-purpose high-risk cases, Article 6(3), Article 50, and related data-law flags.
Sovereign AI TCO & Unit Economics Calculator
Compare fully loaded private infrastructure with managed inference. Model depreciation, energy, PUE, operations, utilization, air-gap overhead, cost per accepted outcome, break-even volume, and estimated value.
Sovereign AI Readiness Checklist
A 43-point audit checklist across six control domains: data boundary, model selection, deployment control, governance, guardrails, and observability. Run it interactively in your browser and get your readiness score instantly.
Private RAG Architecture Diagram Pack
Five professional architecture diagrams covering every layer of a private RAG system — pipeline overview, chunking strategy, hybrid retrieval, guardrails, and observability. Available in PNG, SVG, and PDF.
LLM Token Cost Calculator
Estimate monthly and annual LLM inference costs for your RAG workload. Model sovereign, conditional, and public API options with RAG retrieval overhead included. Updates live as you adjust inputs.
Model Selection Guide
Answer four questions about your data sensitivity, infrastructure, and use case. Get a specific model recommendation with rationale — not a generic list. Includes a quick-reference matrix for ten common scenarios.
RAG Evaluation & Hallucination Test Kit
A practical evaluation kit for private RAG systems covering grounded answers, citations, no-answer behavior, stale documents, prompt injection, and access-control tests.
Air-Gapped AI Deployment Checklist
Validate whether an AI runtime, RAG pipeline, model supply chain, offline build process, and governance controls are ready for restricted environments.
Edge AI & TinyML Readiness Checklist
Check whether a factory, IoT, sensor, camera, or field-device AI use case is ready for a small model, edge runtime, and controlled deployment process.
Local LLM Hardware Sizing Guide
Estimate GPU memory, quantization fit, context overhead, concurrency, and deployment targets for local LLM and private RAG workloads.
Coming Soon
More resources in progress
The next resources in the pipeline. Subscribe via the contact page to be notified when they launch.
Private RAG Starter Kit
Paid KitFastAPI + vector DB + Docker — deployable in a weekend
Hallucination Guard Reference
Free GuideSource-grounding patterns and validation pipeline designs
OpenShift AI Deployment Pack
Paid KitManifests, routes, PVCs, and monitoring for enterprise Kubernetes
Sovereign EvalOps Runner
Reference ArchitectureOffline-first regression runner, baseline diff, and CI/CD evidence export
AI System Passport
Reference TemplateOwnership, risk, BOM, evaluation, authority, cost, and change evidence
Observability Dashboard Pack
Paid KitPre-configured Prometheus and Grafana dashboards for RAG systems
Sovereign AI Glossary
Free ReferencePrecise definitions for RAG, sovereignty, guardrails, and deployment terms
Stay Updated
Get notified when new resources launch
New resources are published regularly.
Send a quick message via the contact page and mention resource updates. We will notify you when new tools, guides, and kits are published.