01
Runtime lifecycle
Model management, hardware compatibility, dynamic switching & zero-downtime updates.
LOCAL-FIRST AI & PRIVACY FOUNDATIONS
Building the infrastructure
for privacy-first AI products.
I build the foundations that let AI products work with sensitive data while keeping privacy, control, and critical processing close to the user.
Current work spans local LLM inference, private speech, and on-device AI—validated through products that protect sensitive conversations, documents, and financial data.
- Applications: ClosedRoom, RedactGuard, and Aura Finance.
- Infrastructure: Local LLM Server, Local ASR Server, and Android LLM Harness.
- Hardware: laptop, desktop, and Android devices, with no cloud required.
VISION
AI products should be able to understand sensitive information without forcing people to surrender control of their conversations, documents, or personal data.
MISSION
Build reusable local AI and data-protection foundations that make privacy-first products possible across desktop and mobile.
- Local by default
- Privacy by architecture
- Open & auditable
FROM LOCAL MODELS TO REAL PRODUCTS
Running a model locally is only the beginning.
Shipping product-grade, privacy-first AI requires far more than weights on a device. It demands solving four key technical challenges:
02
Observability & telemetry
Performance tracking, latency metrics, accuracy signals & memory profiling without privacy leakage.
03
Hardware adaptation
RAM/VRAM constraints, resident memory optimization & thermal management on desktop and mobile.
04
Developer ergonomics
Unified OpenAI-compatible APIs, reliable local IPC & intuitive user experiences.
THE INFRASTRUCTURE STACK (THREE PILLARS)
Three infrastructure pillars
Each project solves a different part of the local-AI product stack. Reusable infrastructure, not isolated experiments.
ACTIVE
Local LLM Server
High-performance local inference server with model lifecycle, dynamic routing and telemetry.
Explore the pillar
Provides an OpenAI-compatible API across local backends such as GGUF and Apple Silicon MLX, managing resident runtimes, configuration and telemetry.
- OpenAI-compatible local API
- GGUF and Apple Silicon (MLX) backends
- Runtime model switching & multi-residency
ACTIVE
Local ASR Server
Privacy-first speech recognition server optimized for sub-second latency and accuracy.
Explore the pillar
Handles microphone & system audio capture, local session storage, and Whisper transcription on Apple Silicon with zero cloud calls.
- Microphone & system-audio capture
- Local Whisper transcription with VAD
- OpenAI-compatible audio endpoint
IN PROGRESS
Android Local LLM Harness
On-device LLM runtime harness for Android apps with strict resource control.
Explore the pillar
Reusable runtime for embedding GGUF models in native Kotlin and Capacitor Android applications with lifecycle control and diagnostics.
- GGUF import & cryptographic integrity check
- Managed model and context lifecycle
- Real-time streaming & cancellation
ARCHITECTURE RELATIONSHIP
Local LLM ServerLocal ASR ServerAndroid LLM Harness
APIs / Protocols (gRPC, WebSocket, Local IPC)Reference Applications (ClosedRoom, RedactGuard, Aura Finance)
PROVING GROUNDS
Reference applications that validate the stack
ClosedRoom, RedactGuard, and Aura Finance demonstrate how privacy-first AI protects conversations, sensitive documents, and personal financial data in practice.
ACTIVE
ClosedRoom
Privacy-first meeting intelligence.
Local-first meeting capture, Whisper transcription and structured insights. Your conversations stay 100% on-device.
TranscriptionSummariesAction ItemsSearch
What it validates
- Local ASR & private speech recognition
- Local LLM analysis & structured insights
- Installable desktop app packaging & offline workflows
ACTIVE
RedactGuard
Local document anonymization & PII protection.
A local document-anonymisation workflow that detects PII via local LLMs, provides human-in-the-loop review, and selectively redacts sensitive data. Data minimisation built into the architecture.
Doc IntelligencePII DetectionHuman ReviewSelective RedactionSafe Export
What it validates
- Local document intelligence & PII detection
- Human review & selective AI redaction
- Data minimisation & safe document portability
IN PROGRESS
Aura Finance
Privacy-first personal finance.
Local AI for transaction categorization, forecasting and budget planning. Your financial data never leaves your device.
Spending InsightsForecastingBudgetsPrivacy First
What it validates
- Privacy-first product design & local data model
- Mobile UX & local storage sovereignty
- Proving ground for Android on-device AI integration
Reference applications validate the infrastructure and show what it can enable. They are the beginning, not the limit, of the ecosystem.
WHAT THIS ENABLES
What the stack makes easier to build next
Exploration areas unlocked by core local AI infrastructure.
01
Meeting intelligence
Private, local summaries & action items from audio.
02
Personal finance
Local transaction analysis, budget forecasting & planning.
03
Document analysis
Query confidential documents without cloud exposure.
04
Professional assistants
Domain-aware copilots that keep workflows private.
05
Personal knowledge
Your notes, custom models, and data sovereignty.
06
Offline productivity
Work anywhere without sacrificing privacy.
07
Sensitive-data workflows
Process confidential data safely on local hardware.
08
Mobile AI applications
Powerful on-device experiences, completely offline-first.
GUIDING ARCHITECTURAL PRINCIPLES
Privacy-first is an architectural discipline
Core tenets guiding engineering decisions across infrastructure and application layers.
01
Local by default
Compute happens on your device, by default.
02
Privacy by architecture
Privacy is designed in, not bolted on.
03
Observable & measurable
We instrument, benchmark and share results.
04
Reusable across apps
Build once. Use everywhere. Composability first.
05
Evidence over claims
We ship, test and publish evidence.
REAL-WORLD EVIDENCE & TRACK RECORD
Proven capability to deliver at scale
"My local-first work is independent, but it builds on years spent designing, evaluating, and scaling AI systems in complex organisations."
Enterprise
Scale & Governance
AI Technical Leadership
Experience leading AI initiatives in complex organisations, turning experiments into adopted, governed, and scaled systems.
80+
Research & Insights
80+ Articles Published
Long-form research, model evaluations, and practical LLM insights shared with the technical community.
150+
Engineering Mentorship
150+ AI Projects Reviewed
Hands-on feedback, architecture guidance, and mentoring for emerging AI engineers and technical teams.
Top 111
Award & Recognition
Nova 111 (2022)
Selected by Nova Talent among emerging Italian talent driving innovation and technology leadership.
KNOWLEDGE & PUBLIC RESEARCH
Building, documenting, and sharing in public
Continuous synthesis across three public channels: Build → Document → Distribute.
ABOUT DANIELE
I work where AI infrastructure, product strategy, and clear engineering intersect.
I am Daniele Moltisanti, an AI technical leader and builder based in Milan. My work combines technical architecture, product thinking, and the ability to transform complex AI research into understandable decisions and reliable, intuitive software.
Alongside my independent work, I lead and design AI initiatives in complex organisations, translating technical possibilities into systems that can be adopted, governed, and scaled.
I also write, teach, and speak about AI architecture, strategy, and the path from experimentation to reliable products.
COLLABORATE
Let's build the future of local AI infrastructure.
Open to collaboration, architecture feedback, and engineering challenges across local LLM performance, Android on-device inference, and privacy-first product design.
danielemoltisanti@gmail.com Milan, Italy