Add Gemini Nano
Add on-device LLM via Gemini Nano (Pixel 8+, Galaxy S24+) using MediaPipe LLM Inference or ML Kit. Use when the user says 'gemini nano', 'on-device ai android', 'on-device llm android', 'no-cloud llm'.
Install
$ agentstack add skill-khadinakbarlabs-expo-mobile-app-builder-add-gemini-nano ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-khadinakbarlabs-expo-mobile-app-builder-add-gemini-nano) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Add Gemini Nano (On-Device LLM)
Android's equivalent of Apple Foundation Models. Free, offline, private.
Hardware required
- Pixel 8 Pro / 8a / 9 / 9 Pro
- Samsung Galaxy S24 / S25 series
- Some OnePlus 12+
- ~4GB+ RAM for model
Options
Option A: MediaPipe LLM Inference (recommended)
# Add to expo prebuild via config plugin
pnpm add @1mt/expo-on-device-aiimport { generateText } from '@1mt/expo-on-device-ai';
const result = await generateText({ prompt: 'Summarize: ...' });Option B: AI Edge SDK (Google native)
Requires native Kotlin module — drop down via expo-modules-core.
Option C: ML Kit GenAI (newer, 2025+)
For specific tasks: summarization, image description, etc.
When to use vs cloud LLM
- Privacy-sensitive (no data leaves device)
- Offline functionality required
- Cost reduction (no API bill)
- Avoid Google Play AI policy disclosure (no third-party transfer)
Cross-platform pattern
- iOS: Foundation Models (skill:
add-foundation-models) - Android: Gemini Nano
- Wrapper:
@1mt/expo-on-device-aicovers both with same API
Limitations
- Smaller context window than cloud (~1k-4k tokens)
- Generation speed: 10-30 tok/sec
- Only ~50% of Android devices support
- Quality below GPT-4 — good for summarization, classification, simple chat
Fallback for unsupported devices
if (await isGeminiNanoAvailable()) {
return await generateText({ prompt });
}
return await callCloudLLM({ prompt }); // with 5.1.2(i) consentPair with
add-openai-streaming-androidfor cloud fallbackplay-ai-disclosurefor compliance (still needed even for on-device if it's AI-generated content)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: khadinakbarlabs
- Source: khadinakbarlabs/expo-mobile-app-builder
- License: MIT
- Homepage: https://khadinakbar.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.