Private Beta

AMINA CORE

Private Intelligence. Local First.

RTX 5090 100% Local No Cloud Multi-Modal Python 3.13 FastAPI

Capabilities

Everything runs on your hardware. Nothing leaves your machine.

🎙️

Voice Intelligence

Wake-word detection, Silero VAD, and faster-Whisper for speech-to-text. Zero-shot voice cloning via OmniVoice TTS — speaks in a natural voice with sub-200ms latency.

STT + TTS
👁️

Vision Mode

Continuous screenshot and camera analysis using local vision models (Gemma 4, Qwen3-VL). Proactive commentary and context-aware responses based on what's on screen.

Multi-modal

Autonomous Scheduling

Amina schedules her own wake-ups and sends reminders via Telegram. Full task management with /tasks, /snooze, /reschedule, /done, and /history — no server required.

Telegram
🎨

Creative Studio

Generates stories chapter-by-chapter with matching images. Produces music via ComfyUI, renders video with LTX, and composes multi-track playlists with DJ intros.

Image · Video · Music · Story
🧠

Deep Memory

Tri-store memory system: short-term ring buffer, episodic journal with semantic search (sentence-transformers), and a structured profile of long-term facts per user.

Episodic + Semantic
🔐

Privacy First

All inference runs locally via llama.cpp. User data is isolated per account with optional 7-Zip AES-256 encryption at rest. No API keys, no telemetry, no cloud.

Local · Encrypted
🤖

Multi-User Support

Separate memory, personality, and media per user. GPU resource ownership with conflict resolution — competing requests queue intelligently without crashing services.

Session-Isolated
🖥️

Workspace Agent

A pi.dev terminal bridge with an agentic coding assistant. Plan, execute, and iterate on tasks in a sandboxed environment — with optional desktop control mode.

Agentic

Tech Stack

Built on open-source inference — no proprietary cloud services.

llama-cpp-python faster-whisper OmniVoice TTS sentence-transformers FastAPI + Uvicorn ComfyUI yt-dlp + ffmpeg python-telegram-bot asyncio PyTorch nightly cu130

Architecture

Inference
llama.cpp · sm_120
GPU
NVIDIA RTX 5090
Context
16k – 256k tokens
STT
Whisper + Silero VAD
TTS Latency
<200ms first byte
Memory
RAM + VRAM 32 GB
🔒

Restricted Access

This system is closed to the public. Account creation is disabled — only authorized administrators may proceed.

Administrator Login
System online