AI models
LLM workflows, retrieval, evaluation, tool use, and private-model planning when the project needs more control.
Claude / OpenAI / Gemini / open-model evaluation / model routing / RAG / evals / function calling
AI infrastructure, software and public code
The technology we build with.
Below are the platforms, AI systems, cloud patterns and public repositories behind the work.
Public source code
JarvisNano, Verrow and Kintunnel have public source linked from their case studies. Other work is documented through its architecture, implementation and available product demonstrations.
Read the codeCase studies
Write-ups of what each system does, how it is built and what it changed.
View the work
TL;DR
AI infrastructure and model tooling from a Fort Lauderdale studio: builds on Gemini, NVIDIA NeMo and self-hosted open-weight models, connected with retrieval and MCP servers, and deployed behind server-side token brokers. Some of the source is public on GitHub.
Stack
What we build production systems with
Agent infrastructure
Human-supervised agent systems that can research, code, operate tools, and keep context across real work sessions.
Claude Code / MCP servers / JarvisNano / OpenClaw / Hermes / browser automation / GitHub tools / approval gates
Applications
Production web and mobile software with performance budgets, load testing where it matters, and agreed deadlines.
React 18.3 / TypeScript 5.9 / Vite 8 / Vite+ / Next.js / Node / FastAPI / Phoenix / Flutter
Data and automation
Operational systems that connect CRMs, inboxes, forms, payments, documents, and internal dashboards.
PostgreSQL / Supabase / Redis / GoHighLevel / HubSpot / Stripe / n8n / Make / Zapier / webhooks
Cloud and ownership
Deployments designed around portability, observability, security, and the right amount of managed service.
Docker / Traefik / GitHub Actions / Dokploy / registry.igddev.com / Vercel / AWS / S3/MinIO / hybrid cloud
Interfaces and hardware
Experimental systems where agents meet devices, voice, video, robotics, and real-world inputs.
agent control loops / embedded AI prototypes / ESP32 / voice agents / video understanding / WebRTC / WebSockets
Applied labs
Newer tools we are testing.
We use OpenClaw, NeMoClaw, Hermes and similar tools when they fit a specific workflow: private AI, agentic operations, hardware control, model evaluation, or customer-facing automation.
OpenClaw / agent control
Useful for robotics-style control loops, local assistants, hardware interfaces, and supervised tool execution.
NeMoClaw / NeMo AI operations
Model customization, evaluation, guardrails and deployment planning, when a project needs them.
Hermes / open-model experiments
Private or local model exploration for teams that need portability, cost control, or more ownership of inference.
How this helps clients
Software you can run after we hand it over.
We explain architecture decisions as we make them, and hand over documented code your team can still read six months after launch.
- Start with the business workflow, then choose the stack.
- Use managed platforms when speed matters and portable systems when control matters.
- Keep AI systems observable, reviewable, and grounded in real company data.
- Document architecture and tradeoffs so clients can maintain the code.
FAQ
Frequently asked questions
Common questions about our AI infrastructure, models, MCP servers, and self-hosting.
What AI models and providers does Ingenious Digital work with?
Google Gemini (including the Gemini Live API behind our JARVIS voice assistant), NVIDIA NeMo, and open-weight models we can host ourselves. We choose the model by task, cost and speed, and connect it to your data through retrieval (RAG) and tools (MCP) so it answers from your records.
What are OpenClaw, NeMoClaw, and Hermes?
Internal tools we built and run in production. They handle deployment, orchestration and evaluation: the layer between a raw model and a feature that works reliably.
Do you build MCP servers?
Yes. Model Context Protocol (MCP) servers give AI assistants controlled access to tools, APIs and internal data, so an agent can look up a record, start a workflow or filter a view. Our JarvisNano prototype and JARVIS voice assistant both use MCP.
Can you self-host models instead of using a third-party API?
Yes. When data residency, cost at volume or speed call for it, we run open-weight models on your cloud or your own servers with NVIDIA NeMo tooling. When a hosted model is the better choice, we call it through a server-side broker so keys never reach the browser.
What is RAG and do you implement it?
Retrieval-augmented generation (RAG) makes an AI answer from your own documents and data, which reduces made-up answers and keeps them current. We build the whole pipeline (ingestion, chunking, embeddings, vector search and re-ranking) and connect it to assistants, search and internal tools.
How do you keep AI features secure and reliable in production?
Keys stay on the server behind short-lived token brokers, model calls run behind rate limits and test suites, and agent actions are limited to the MCP tools we allow. We test model behavior before release; our public DRQ Benchmark project shows how.
Work
Related case studies
Portfolio projects with public source: embedded AI hardware, multi-provider LLM benchmarking and lower-level systems work.
- AI & Machine LearningJarvisNanoAn open-source embedded AI project with C/C++ firmware on Seeed XIAO ESP32-S3 Sense and Waveshare AMOLED boards, dynamically loaded Lua skills running on-chip, and hardware-first prototyping to explore assistants that run on a device. A Kotlin Android app is the optional companion.View case study
- Developer ToolsAgent delivery harnessEvery change on this page went through the same pipeline: a board item becomes an agent working in its own isolated copy of the code, then a deterministic gate, then a review by a model from a different vendor, and only then does it land.View case study
- Consumer ProductivityAsteriaAsteria explains a person's birth chart in plain language and keeps calculated fact visibly separate from interpretation. A Rust calculation engine does the astronomy; a React client makes it readable for complete beginners.View case study
Workflow first / Integrated systems / Global delivery
Talk to us about your stack.
Tell us what you run today and what you need it to do, and we will suggest where to start.
Get in touch