Loading...
private.meDocs
Get AI
PRIVATE.ME PLATFORM

AI: On-Device AI Inference

Unified interface for on-device AI via Ollama, WebLLM, or platform-native models. Summarization, reply suggestions, intent classification, and embeddings. All inference runs locally. Zero data leaves the device.

AI/ML AVAILABLE NOW On-Device
Section 01

The Problem

Cloud AI services see all user data. On-device AI has no unified interface across providers. Privacy-preserving AI inference does not exist for email.

Every cloud AI service (OpenAI, Anthropic, Google) requires sending full message content to remote servers. For email containing sensitive legal, medical, or financial data, this is unacceptable. The AI provider becomes another attack surface.

On-device alternatives exist (Ollama, WebLLM, Apple Foundation Models) but each has a different API, different model formats, and different capabilities. Building a product that works across all of them requires a unified abstraction layer.

The Old Way

Email App full message Cloud AI API SEES ALL DATA trains on content logs queries Data Exposure no privacy
Section 02

The PRIVATE.ME Solution

A unified AI provider abstraction that runs entirely on-device. Supports Ollama (managed sidecar for desktop), WebLLM (browser), and platform-native models. Zero data transmitted to external services.

Provider abstraction normalizes the API across backends. Application code calls summarize() or suggestReply() without knowing which model is running underneath. Switching from Ollama to WebLLM requires changing one configuration line.

Managed sidecar for desktop: Ollama is installed and managed automatically. Model downloads happen in the background. The AI is always available without user configuration.

The New Way

Email App message AI Provider unified API on-device Ollama WebLLM Native Local 0 data out
Section 03

How It Works

Four AI capabilities exposed through a single provider interface: summarization, reply suggestion, intent classification, and embedding generation.

createProvider() summarize() message digest suggestReply() draft response classify() intent detection embed() vectors All inference on-device — zero data transmitted externally
Key Security Properties
On-device only: All inference runs locally. No API calls to external AI services.
Provider agnostic: Switch between Ollama, WebLLM, or native models without code changes.
Managed sidecar: Ollama installed and managed automatically on desktop.
No training: User data never used for model training. Models are read-only.
Section 04

Use Cases

Email
Email Reply Suggestions

Generate contextual reply drafts from message content. All processing on-device. No cloud AI sees your email.

Ollama
Productivity
Message Summarization

Summarize long email threads into concise digests. Runs locally with configurable model size and quality tradeoffs.

Local LLM
Classification
Intent Classification

Classify messages by intent (action required, FYI, scheduling, urgent) to power smart inbox prioritization.

On-Device
Search
Embedding Generation

Generate vector embeddings for semantic search without sending content to external embedding APIs.

Vectors
Section 05

Integration

Quick Start
import { createProvider, summarize } from '@private.me/ai';

// Create on-device AI provider
const ai = createProvider('ollama');

// Summarize an email thread — runs entirely on device
const summary = await summarize(ai, emailThread, {
  maxLength: 100,
  style: 'executive'
});

// Generate reply suggestion
const reply = await ai.suggestReply(emailThread, {
  tone: 'professional'
});
createProvider(backend: 'ollama' | 'webllm' | 'native'): AIProvider
Initialize an on-device AI provider. Ollama for desktop (managed sidecar), WebLLM for browser, native for platform-specific models (Apple Foundation, Gemini Nano).
summarize(provider: AIProvider, content: string, config?: SummarizeConfig): Promise<string>
Generate a concise summary of the provided content. Configurable length and style. All processing on-device.
Section 06

Security Properties

PropertyMechanismGuarantee
Data localityOn-device inferenceZero data transmitted
Provider isolationManaged sidecar processProcess separation
No trainingRead-only model filesNo data retention
API uniformityProvider abstractionBackend agnostic
Graceful fallbackCapability detectionFeature degradation
0
bytes sent to cloud
3
provider backends
4
AI capabilities
100%
on-device
GET STARTED

Ready to deploy ai?

Talk to Sol, our AI platform engineer, or book a live demo with our team.

Book a Demo

© 2026 StandardClouds Inc. dba PRIVATE.ME. All rights reserved.

VERIFIABLE WITHOUT CODE EXPOSURE

Ship Proofs, Not Source

Ai generates cryptographic proofs of correct execution without exposing proprietary algorithms. Verify integrity using zero-knowledge proofs — no source code required.

XPROVE CRYPTOGRAPHIC PROOF
Download proofs:

Verify proofs online →

Use Cases

🏛️
REGULATORY
FDA / SEC Submissions
Prove algorithm correctness for privacy-preserving AI without exposing trade secrets or IP.
Zero IP Exposure
🏦
FINANCIAL
Audit Without Access
External auditors verify on-device AI inference without accessing source code or production systems.
FINRA / SOX Compliant
🛡️
DEFENSE
Classified Verification
Security clearance holders verify privacy-preserving AI correctness without clearance for source code.
CMMC / NIST Ready
🏢
ENTERPRISE
Procurement Due Diligence
Prove security + correctness during RFP evaluation without NDA or code escrow.
No NDA Required