AI ENGINEOff
Not connectedRequires native integration
LocalMind AI
WEB PREVIEW
ON-DEVICE INTELLIGENCE
Your AI space
All set to run locally — once the Android engine is connected.
Android bridge not connected
This web preview does not run GGUF or host an API. The llama.cpp engine, Android service, and native storage need to be integrated into the Capacitor project.
DEFAULT MODEL◈
NoneSelect a GGUF modelAPI SERVERStopped
UnavailableAndroid service not installedADDED MODELS▱
0Metadata in this previewOverview
Real-time status of this device
Device resources
RAM memoryUnavailable
CPU usageUnavailable
Metrics available after native integration
Get started here
Your models
◈
Your models will appear here after being added.
Recent activity
Local only—
No activity yet
PRIVATE CHAT
Chat
Chat with a model running on your own device.
✦
A conversation, just for you.
Add a GGUF model and connect the Android engine to start chatting.
Your messages stay on this device.
LOCAL LIBRARY
Models
Manage the GGUF files you want to use with LocalMind.
Native import required
The preview can read the name and size of the chosen file, but cannot copy it to persistent storage or load it into llama.cpp. On Android, connect the document picker and the native bridge.
No model is selected as default.
◈
Your library starts here
Add .gguf files to keep your collection organized. Inference requires native llama.cpp integration.
SYSTEM VISIBILITY
Performance
Real metrics will be displayed when provided by the native engine.
No measurements available
The browser preview does not have reliable access to process RAM, CPU load, or llama.cpp internal metrics. No estimates will be presented as measurements.
Inference settings
Saved in this appThe memory target is not a guarantee: consumption varies by model, context, caches, and operating system.
LOCAL NETWORK ACCESS
API Server
Use your phone as a local endpoint for apps on the same Wi-Fi.
Native server unavailable in this preview
A real server accessible via network requires an Android foreground service, network permissions, and engine integration. This page does not open a network port.
Server control
StoppedUse a port between 1024 and 65535.
Base URLhttp://IP_DO_CELULAR:8080/v1
Protected access
Each request must include a key in the Authorization: Bearer header. Never expose the endpoint without authentication.
Mobile and PC usually need to be on the same local network. Internet access requires additional secure configuration.
Access keys
Keys created here are stored in this app. The preview does not authenticate requests without the native service.
No keys created.
PC Example
curl http://IP_DO_CELULAR:8080/v1/chat/completions \
-H "Authorization: Bearer SUA_CHAVE" \
-H "Content-Type: application/json" \
-d '{"model":"local","messages":[{"role":"user","content":"Olá!"}]}'The example will only work after integrating and starting the native HTTP service with a loaded model.