App Intel

Edgi: Offline AI, On-Device

LiveNNOpt1 app · 1.4K installsToolsFreecom.edgi.app

Run LLMs, vision, speech & music AI on-device. Private, offline, no cloud.

Alert me★ WatchOpen in Play ↗
Total installs
1,389
exact · Play shows 1,000+
Installs / day
—
measured after our second crawl (about a day)
Rating
—★
— ratings · — reviews
Released
28 Jun 2026
3mo ago
Last update
5 Aug 2026
v1.0.7 · 2mo ago
Countries
—
not checked yet

Install history

exact counter from Google Play
1.4K1.5K1.7K1.8K2K11 Oct12 Oct12 Oct
1.4K1.5K1.7K1.8K2K11 Oct12 Oct12 Oct

Installs per day · last 90 days

Not enough history yet — check back tomorrow

Change timeline

No changes recorded yet. We compare every crawl with the previous one and list title, icon, screenshots, description, version, price and availability changes here.

Country availability

Availability has not been checked for this app yet. “Check all countries” looks the app up in about 140 Google Play storefronts and shows where it is live, listed but not installable, or missing — plus any country-specific (custom) store listings.

Top countries

Country data will be available soon.

We estimate where downloads come from using the app’s position in Google Play’s top charts in about 140 countries. This app is not in any chart we have collected yet; the estimate appears as soon as it is.

Top chart positions

Not in any tracked top chart.

App manifest

Read this app's manifest from Google Play: permissions, declared SDKs, components and AdMob app ID. Saved analysis appears here automatically.

Manifest analysis reads only the required APK ranges. Base APK downloads may need separate device splits to install.

Data safety

declared by the developer on Google Play
  • No data shared with third parties
  • No data collected

This is the developer's own declaration, summarised from the Play listing. The permissions below show what the app is technically able to access.

Permissions

7 in 3 groups
2 Sensitive2 Notable3 Routine

What this app can do with your phone

  • Use your camera to take photos and record videos
  • Record sound using your phone's microphone
CameraSensitive1

Access to your camera to take photos and record video

  • Use your camera to take photos and record videostake pictures and videos · CAMERA
MicrophoneSensitive1

Access to your phone's microphone to record sound

  • Record sound using your phone's microphonerecord audio · RECORD_AUDIO
OtherNotable5

Access to miscellaneous device features that don't fit other categories

  • Start itself automatically as soon as your phone finishes turning onrun at startup · RECEIVE_BOOT_COMPLETED
  • Keep your phone's processor or screen from going to sleep, which can use more batteryprevent device from sleeping · WAKE_LOCK
  • Check whether you are online and whether you use Wi-Fi or mobile dataview network connections · ACCESS_NETWORK_STATE
  • Connect to the internet to load content and send datafull network access · INTERNET
  • Check with Google Play that you got this app legitimatelyGoogle Play license check · com.android.vending.CHECK_LICENSE

Sensitive = can reach personal data, location, camera/mic or act on your behalf. Notable = changes how your device behaves. Routine = normal for almost every app. Source: Google Play's permission list for all versions of this app.

Store listing

Full description
Edgi is a home for open-source AI models that run entirely on your phone, including models that have not been available offline on Android. No account, no cloud, nothing leaves your device. We port models the rest of mobile AI ignores and make them run offline on everyday Android phones. Browse the in-app catalog, download a model once, and it's yours to use forever, in airplane mode, on a plane, anywhere. What you can run, all on-device: • Chat: A growing library of open language models (LLMs): SmolLM2, Granite, Mamba, OpenELM, LFM2.5, Qwen2.5. Pick a tiny fast one or a larger, smarter one to match your phone. • Vision: Show it a photo and ask about it. On-device vision models describe images and answer questions about what they see. • Speech to text: Transcribe audio with Whisper, fully offline. • Text to speech: Offline text to speech with dozens of natural voices and multiple engines (Kokoro, MMS-TTS, Pocket-TTS). • Music: An AI music generator that runs offline — create short original clips from a text prompt with MusicGen. • Translation: Translate speech across languages with Meta's SeamlessM4T. • Voice cloning: Capture a voice from a short clip and have it read any text, on-device (OpenVoice). Many of these have never been free and fully offline on Android before. Edgi brings them together in one place. Why Edgi is different: • A real catalog. Not one locked-in model, a browsable, growing collection of open-source models, each with clear sizes so you choose what to install. • Truly private. Your prompts, microphone audio, photos, and results are processed on your device and are never uploaded. No servers receive your content. No sign-in. • Works offline. Once a model is downloaded, it runs with no internet. • Built for budget phones. Edgi runs on its own custom inference engine tuned for Qualcomm Adreno GPUs tuned for budget hardware. OPEN SOURCE Edgi runs on adreno-llms, our own OpenCL inference engine for Qualcomm Adreno GPUs, open source and yours to inspect or build on: https://github.com/a8nova/adreno-llms

What's new

Bonsai 27B, a 27-billion-parameter vision-language model at one bit per weight, now runs fully offline on recent flagship phones like the Galaxy S26 Ultra, S25 Ultra and Z Fold 7/8. Ask it about a photo, or just chat. Reasoning models now show their thinking as it happens, and you can expand it afterwards.

Growing in Tools

Category →