THE ANDROID AI RUNTIME

AI that runs on your phone.

EdgeLM runs AI directly on your device — chat, vision, speech and search, private and offline, shared by every app. Download a model once; any EdgeLM-powered app can use it.

No cloud · no account · no tracking · works offline

0on-device decode speed
0things it can do
0models to choose from
0private & offline
WHY EDGELM

On-device by default.

Most AI apps send your words to a server. EdgeLM keeps everything on the phone — faster, private, and free of per-request cloud costs.

Private by design

Your prompts and the AI's replies never leave your device. No cloud, no account, no tracking, no ads.

Works offline

Once a model is downloaded, EdgeLM runs with no internet at all — on a plane, in a tunnel, anywhere.

Shared & efficient

One model, loaded once and served to every app — so a second app adds almost no extra memory.

No cloud cost

Nothing to pay per request and no network round-trips. The compute you already own does the work.

WHAT IT CAN DO

More than chat.

One runtime, five capabilities — each one a model any app on your phone can ask for, and each one gated by its own permission you can revoke.

Chat

Streaming conversation with multi-turn memory. Ask a follow-up and it remembers, without resending the whole thread.

Vision

Describe a photo, read a screenshot, answer questions about what's in an image — locally.

Speech

Live captions as you talk, and transcription that runs faster than people speak. Nothing is uploaded.

Search your notes

On-device embeddings and a local index, so an app can answer from your documents without sending them anywhere.

Agents & tools

The model can call tools an app registers — and every outbound call passes the firewall first.

YOU DECIDE

Private isn't a promise. It's architecture.

"On-device" only means something if you can see and control what leaves. EdgeLM makes that a mechanism, not a policy page.

Per-app permissions

Chat, vision, speech and search are separate grants. An app that wants your microphone has to say so, and you can revoke it.

Data-flow firewall

When an agent tries to reach the internet, the destination is checked against rules you set — and data that came from your device is tracked separately.

Verified downloads

Every model is checked against its SHA-256 before it's installed. A tampered file is deleted, not loaded.

No telemetry

No accounts, no analytics, no ads. There is no server to send anything to.

HOW IT WORKS

Three taps to on-device AI.

EdgeLM guides you through setup and recommends the right model for your phone.

Install EdgeLM Runtime

A quick welcome explains how on-device AI keeps your data private.

Pick an AI

EdgeLM suggests the best model for your phone — one tap to download. Power users can switch to Advanced for the full catalog.

Use it

Try it instantly in the built-in playground. Any EdgeLM-powered app on your phone can now use AI.

A LOOK INSIDE

Simple to start, powerful when you want it.

Plain-language by default — download the recommended model and chat. Full model details and controls are one tap away in Advanced.

The right AI for your phone Chat privately, on your device Choose your assistant Fast, and fully offline Full control when you want it
CHOOSE YOUR MODEL

A model for every phone.

From tiny-and-fast to more capable — each shown in plain language with its size and what it's best for, and a warning if your phone may not have enough memory. Keep several installed and switch instantly.

Quick Assistant
Qwen2.5 0.5B · Fastest

Fast and light — quick questions and short replies on any phone.

Everyday Assistant
Llama 3.2 1B · Balanced

A well-rounded helper for chatting, writing, and summarizing.

Smart Assistant
Qwen2.5 1.5B · Smarter

Sharper answers and better with other languages.

Pro Assistant
Llama 3.2 3B · Capable

Higher-quality writing and thinking. Best on newer phones.

Expert Assistant
Phi-3.5 mini · Most capable

Best for tricky questions, math, and coding help.

Beyond chat

Vision, speech and search are separate downloads — install only what you actually use, and the runtime loads each one on demand and frees it when idle.

Quick Listener
Whisper base · 58 MB

Speech to text, fast enough for live captions as you speak.

Careful Listener
Whisper small · 190 MB

More accurate with accents, noise and proper nouns.

Vision Assistant
SmolVLM 500M · Tiny

Captions photos and answers simple questions about them.

Sharp Vision
Qwen2.5-VL 3B · Capable

Actually reads screenshots and documents. Newer phones.

Audio Companion
LFM2-Audio 1.5B

Answers questions about a recording — hears tone, not just words.

Search Brain
BGE small · 34 MB

Understands meaning so apps can search your notes privately.

FOR DEVELOPERS

On-device AI in a few lines.

EdgeLM is a shared runtime — your app calls it instead of bundling and managing model weights. Add the SDK and stream tokens with an OpenAI-style API.

// settings.gradle.kts — JitPack
maven { url = uri("https://jitpack.io") }

// app/build.gradle.kts
implementation("com.github.Chandra-Mauli-Sharma.EdgeLM:sdk:0.2.0")

// every capability is a cold Flow — collect to start,
// cancel the scope to stop. All on device.
EdgeLM.chat("default", "Explain on-device AI", sessionId = "chat-1")
    .collect { token -> append(token) }

EdgeLM.caption(context, photoUri)      // what's in this image?
EdgeLM.liveTranscribe()                 // captions as you speak
EdgeLM.askByVoice(wav)                  // speak a question, get an answer

// graceful if the runtime isn't installed
EdgeLM.promptInstall(context)
  • One shared model across every app — no per-app weights, minimal extra memory.
  • Chat, vision and speech from the same SDK — four lines each, no inference engine to ship.
  • Permission-gated — declare the capabilities you use; the user can revoke any of them.
  • Streaming + sessions — Kotlin Flows and multi-turn context out of the box.
  • OpenAI-compatible HTTP shim for local tools during development.
  • Desktop console — pull models, watch throughput, test every capability and read the device log, over adb.
Full integration guide → Download EdgeLM Hub →

Bring AI on-device.

Private, offline, shared by every app. Now on Google Play.