Release list

Mimic AI Digital Assistant v 1.2.1 Latest

Latest

bmerriott released this 02 Mar 05:24

v1.2.1

0b8184a

🎬 Demo Video

Watch the full demo of MIMIC AI v1.2.0 in action:

👉 MIMIC AI Desktop Assistant v1.2.0 - YouTube

Featuring voice cloning, multi-persona support, and real-time conversation

Mimic AI v1.2.0 - Voice Profiles & Enhanced TTS

🎉 Major Update

Mimic AI v1.2.0 introduces persistent voice profiles for instant voice cloning, improved TTS error handling, Qwen3 1.7B model support with VRAM management, and per-persona memory isolation.

📦 What's Included

**Updated to v1.2.1 to address crashes when accessing the memory manager.

File	Description	Size
`Mimic-AI-Setup.exe`	One-click installer (recommended)	~164 MB
`Mimic-AI-v1.2.0.zip`	Portable ZIP archive	~164 MB
`launch-mimic.bat`	Launch with Python backend	-
`MimicAI-StopAll.bat`	Stop all services	-
`README.md`	Full documentation	-
`QUICKSTART.md`	Quick start guide	-
`CHANGELOG.md`	Version history	-

🚀 Getting Started

New Users

Download Mimic-AI-v1.2.0.zip from GitHub Releases
Extract the entire ZIP to a folder
Run Mimic-AI-Setup.exe
Launch from Start Menu or Desktop
Create your first persona with voice cloning!

Upgrading from v1.1.0?

Your existing personas, memories, and VRM avatars are preserved. Voice profiles will be created automatically when you first use voice features.

Prerequisites (Same as v1.1.0)

Python 3.10-3.12
- Download: https://python.org/downloads/
- ⚠️ Important: Check "Add Python to PATH" during installation!
Ollama (for AI models)
- Download: https://ollama.com
- First-time setup: Run ollama serve once after installing
Docker Desktop (optional, for web search)
- Download: https://docker.com

✨ What's New in v1.2.0

🎙️ Voice Profile System (New!)

Persistent Voice Cloning - Create voice profiles that persist across sessions
Instant Voice Switching - Cached voice clone prompts for near-instant TTS
Voice Profile API - Save/load voice profiles per persona
Disk Caching - Voice clone prompts cached to disk for fast reloading

🧠 Per-Persona Memory Isolation (New!)

Independent Conversations - Each persona now has completely isolated chat history
Memory Files - Stored at ~/MimicAI/Memories/{persona_id}/
Auto-Clear on Switch - Chat automatically clears when switching personas
No Cross-Contamination - Persona A cannot see Persona B's conversations

🔊 Enhanced TTS Engine Support

Qwen3 1.7B Model - Higher quality voice generation (requires ~6GB VRAM)
Auto VRAM Detection - Automatically falls back to 0.6B if insufficient VRAM
GPU Memory Management - New /api/tts/unload endpoint to free VRAM
Engine Switching - Properly unloads models when switching between Qwen3 and KittenTTS

🛡️ Improved Error Handling

TTS Failure Resilience - Text response displays even when voice generation fails
Graceful Degradation - If Qwen3 fails, automatically shows text-only response
Better Error Messages - Clear feedback when tensor mismatches or VRAM issues occur
Voice Prompt Loading - Shows "Generating response..." indicator during LLM inference

🔧 Backend Improvements

Fixed Voice Clone Caching - Properly caches full VoiceClonePromptItem list
Reference Text Handling - Fixed reference text not being passed to voice creation
Memory Management - Added unload_qwen3() with CUDA cache clearing and garbage collection
VRAM Check - Pre-load VRAM check prevents OOM crashes

🎬 VRMA Library Cleanup

Removed Unused Animations - Cleaned up duplicate and unused VRMA files
Synced Resources - All VRMA files properly synced between app/public/vrma/ and src-tauri/resources/vrma/
Optimized Bundle - Reduced release package size

⚠️ Important: License

Mimic AI is licensed under a Proprietary License as a Freemium Product with In-app Purchases

Support Development: Additional Support can be provided by subscribing at https://www.patreon.com/c/MimicAIDigitalAssistant

📋 System Requirements

OS: Windows 10/11 (64-bit)
RAM: 8GB minimum, 16GB recommended
Storage: 5GB free space
GPU: NVIDIA GPU with CUDA support recommended for Qwen3 TTS
- Qwen3 0.6B: ~3GB VRAM
- Qwen3 1.7B: ~6GB VRAM

🐛 Known Issues

First launch may take 30-60 seconds as bundled assets are copied to user data
Docker must be running before enabling web search
Qwen3 1.7B requires significant VRAM - will auto-fallback to 0.6B if insufficient
Some antivirus software may flag the installer (false positive)

🔧 Troubleshooting

"Voice generation failed: Sizes of tensors must match"

This occurs with incompatible reference audio formats
Try re-recording your voice sample in Voice Creator
Ensure reference audio is clear and 3-10 seconds long

Qwen3 TTS not working / Out of Memory

Check GPU VRAM availability in Task Manager
The app will auto-fallback to 0.6B if 1.7B doesn't fit
Use POST /api/tts/unload to free VRAM when switching engines

Text not appearing with voice prompts

Fixed in v1.2.0 - voice prompts now show "Generating response..." indicator
Text appears synchronized with audio playback

All other issues

See v1.1.0 troubleshooting guide in README.md

🎨 Attribution

Default Avatar: PeePhanthong (VRoid Hub)
Animations: VRoid Project by pixiv Inc., 八ツ橋まろんのお店, Kannaku @ Nekokoya
TTS: Qwen3-TTS by Alibaba, KittenTTS by KittenML
See ATTRIBUTION.md for full credits

📄 License

Proprietary License - See LICENSE.txt for full terms

Full Documentation: See README.md and CHANGELOG.md
Issue Tracker: https://github.com/bmerriott/MIMIC-Multipurpose-Intelligent-Molecular-Information-Catalyst-/issues

Assets 4

Mimic AI Digital Assistant v 1.1.0

bmerriott released this 23 Feb 05:27

v1.1.0

cf40edf

🎬 Demo Video

Watch the full demo of MIMIC in action here:

👉 https://imgur.com/a/SjsTsgj

Mimic AI v1.1.0 - VRM Avatar & Persona Memory

🎉 Major Update

Mimic AI v1.1.0 introduces full 3D VRM avatar support with VRoid model integration, avatar-persona memory connection, and a bundled default persona with voice.

📦 What's Included

File	Description	Size
`Mimic-AI-Setup.exe`	One-click installer (recommended)	~152 MB
`Mimic-AI-v1.1.0.zip`	Portable ZIP archive	~158 MB
`launch-mimic.bat`	Launch with Python backend	-
`MimicAI-StopAll.bat`	Stop all services	-
`README.md`	Full documentation	-
`QUICKSTART.md`	Quick start guide	-
`CHANGELOG.md`	Version history	-
`vrma/`	VRM animation library	-

🚀 Getting Started

New Users

Download Mimic-AI-v1.1.0.zip from GitHub Releases
Extract the entire ZIP (keep the vrma/ folder with the installer)
Run Mimic-AI-Setup.exe
Launch from Start Menu or Desktop
Your 3D avatar loads automatically!

Upgrading from v1.0?

Your existing personas and memories are preserved. The default "Mimic" persona will automatically upgrade to the new 3D VRM avatar. You can switch between avatar types (VRM or Abstract) in the Persona Manager at any time.

Prerequisites (Same as v1.0)

Python 3.10-3.12
- Download: https://python.org/downloads/
- ⚠️ Important: Check "Add Python to PATH" during installation!
Ollama (for AI models)
- Download: https://ollama.com
- First-time setup: Run ollama serve once after installing
Docker Desktop (optional, for web search)
- Download: https://docker.com

✨ What's New in v1.1.0

🎭 VRM Avatar Support (New!)

Full 3D Avatar Support - Load and display VRM models from VRoid Hub or custom creations
Bundled Default Avatar - Ships with pre-configured VRM avatar (PeePhanthong)
Expression & Lip-Sync - VRM avatars show expressions and lip-sync to speech
Height-Based Camera - Camera intelligently positions based on avatar model height

🎬 VRMA Animation Support (New!)

Animation Library - Play VRMA animation files on VRM avatars
Bundled Animations - Includes greetings, poses, dances, and idle animations
Context-Aware - Avatars automatically play appropriate animations based on conversation

🧠 Avatar-Persona Memory Integration (New!)

Shared Context - Avatars now access their persona's contextual memory
Emotional Reflection - Avatar expressions reflect the persona's emotional state
Personality-Driven - Avatar behavior influenced by persona's personality traits

🎨 Avatar Personality System (New!)

Automatic Trait Extraction - Derives personality traits from personality prompts
Voice Parameter Derivation - Adjusts voice parameters based on extracted traits
Dynamic Emotional State - Avatar tracks emotional states during conversations

🧍 Persona Learning System (New!)

Interaction Tracking - Records conversation history per persona
Emote Learning - Tracks preferred emotes based on user feedback
Relationship Metrics - Calculates rapport, familiarity, and trust scores
Favorite Topics - Identifies and remembers user's favorite conversation topics

🔊 Procedural Vocalizations (New!)

AI-generated non-verbal sounds (giggles, sighs, hums) using Qwen3 TTS
Cached in IndexedDB (max 10 per persona)

🔧 Improvements

Fixed Camera Snapping - Avatar no longer zooms in too close after loading
Fixed Audio Playback - Resolved AudioContext suspension causing silent audio
Longer Voice Prompts - Increased silence delay from 3.5s to 5s
Real-Time Blob Colors - Colors update instantly when using color wheel

⚠️ Important: License Change

Mimic AI is now licensed under a Proprietary License with 7-Day Trial

7-Day Free Trial: Full functionality for 7 days from first launch
Subscription: $5/month via Patreon for continued use after trial
Support Development: Subscribe at https://www.patreon.com/c/MimicAIDigitalAssistant

Previously MIT licensed (v1.0). See LICENSE.txt for full terms.

📋 System Requirements

OS: Windows 10/11 (64-bit)
RAM: 8GB minimum, 16GB recommended
Storage: 5GB free space (increased from v1.0 due to bundled assets)
GPU: Optional but recommended for faster inference

🐛 Known Issues

First launch may take 30-60 seconds as bundled assets are copied to user data
Docker must be running before enabling web search
Some antivirus software may flag the installer (false positive)

🔧 Troubleshooting

Avatar not loading (red cube appears)

This is normal on first launch - assets are being copied
Wait 10-15 seconds, then restart the app
Check %APPDATA%\com.mimicai.app\vrm_library\ for default_bundled.vrm

"VRM not found in library" error

Verify the release ZIP was extracted completely
The vrma/ folder should be in the same directory as the installer
Re-extract the ZIP if files are missing

Voice not working with Qwen3

Ensure Python backend is running (use launch-mimic.bat instead of direct launch)
Check TTS backend connection indicator (top-right of app)
Default voice is pre-configured - test in Voice Studio

All other issues (same as v1.0)

See v1.0 troubleshooting guide in README.md

🎨 Attribution

Default Avatar: PeePhanthong (VRoid Hub)
Animations: VRoid Project by pixiv Inc., 八ツ橋まろんのお店, Kannaku @ Nekokoya
See ATTRIBUTION.md for full credits

📝 Checksums

📄 License

Proprietary License with 7-Day Trial - See LICENSE.txt for full terms

Full Documentation: See README.md and CHANGELOG.md
Issue Tracker: https://github.com/bmerriott/MIMIC-Multipurpose-Intelligent-Molecular-Information-Catalyst-/issues

Assets 4

Mimic AI Digital Assistant

bmerriott released this 19 Feb 14:32

v1.0.0

5682ec7

Mimic AI v1.0.0 - Initial Release

🎉 First Official Release

Mimic AI - Your privacy-first, AI-powered desktop assistant with voice synthesis, persistent memory, and local model inference.

📦 What's Included

File	Description	Size
`Mimic-AI-Setup-v1.0.exe`	One-click installer (recommended)	~121 MB
`Mimic-AI-v1.0.zip`	Portable ZIP archive	~121 MB
`README.txt`	Installation and troubleshooting guide	-
`QUICKSTART.md`	Quick start documentation	-

🚀 Getting Started

Prerequisites

Before installing Mimic AI, you need:

Python 3.10-3.12
- Download: https://python.org/downloads/
- ⚠️ Important: Check "Add Python to PATH" during installation!
Ollama (for AI models)
- Download: https://ollama.com
- First-time setup: After install, open and use at least one model
Docker Desktop (optional, for web search)
- Download: https://docker.com
- Only needed if you want web search functionality

Installation

Download Mimic-AI-Setup-v1.0.exe
Double-click to run the installer
Follow the installation wizard
Launch Mimic AI from Start Menu or Desktop

First Launch

On first run, Mimic AI will:

Configure Ollama for Tauri WebView compatibility (automatic)
Verify Python and install required dependencies
Start the TTS (Text-to-Speech) backend
Start Ollama (if not already running)
Initialize SearXNG in Docker (if enabled)

Note: First launch may take 30-60 seconds as services start up.

✨ Features

🤖 Local AI Inference - Runs entirely on your machine using Ollama
🗣️ Voice Synthesis - Dual TTS engine support (Browser-Based & Qwen3-TTS)
🧠 Persistent Memory - Conversation memory with per-persona context
🔍 Web Search - Privacy-focused SearXNG integration
🎙️ Wake Word Detection - Hands-free activation
👁️ Vision Support - Image analysis with vision-capable models
🔒 Audio Watermarking - All generated audio is watermarked

🔧 Key Features

Automatic Ollama Configuration

Mimic AI automatically configures Ollama with the required environment variables (OLLAMA_ORIGINS=*) for Tauri WebView compatibility. No manual setup needed!

Auto Model Selection

If your default model isn't installed, Mimic AI automatically selects the first available model from your Ollama installation.

Direct SearXNG Connection

SearXNG connection is checked directly (bypassing the Python backend), so web search works immediately when Docker is running.

🐛 Known Issues

First launch may take longer as Python dependencies are installed
Docker must be running before enabling web search
Some antivirus software may flag the installer (false positive)

🔧 Troubleshooting

"Python not found" error

Ensure Python 3.10-3.12 is installed and in PATH
Restart Mimic AI after installing Python

"Ollama not connected"

First time only: Run ollama serve once to initialize Ollama
Pull a model: ollama pull llama3.2
Mimic AI will auto-start Ollama for you on subsequent launches
Check Ollama is running: http://localhost:11434/api/tags

"TTS backend not connected"

Ensure Python dependencies are installed
Check the startup log: %APPDATA%\com.mimicai.app\startup.log

Web search not working

Ensure Docker Desktop is installed and running
Enable web search in Mimic AI settings
SearXNG container will be created automatically

📋 System Requirements

OS: Windows 10/11 (64-bit)
RAM: 8GB minimum, 16GB recommended
Storage: 5GB free space
GPU: Optional but recommended for faster inference

📝 Checksums

SHA256: (to be added after build)

🙏 Credits

Built with Tauri, React, and Rust
Uses Ollama for local LLM inference
Voice synthesis powered by Browser-Based TTS and Qwen3-TTS

📄 License

MIT License - See LICENSE file for details

Full Documentation: See README.md in the repository
Issue Tracker: https://github.com/bmerriott/MIMIC-Multipurpose-Intelligent-Molecular-Information-Catalyst-/issues

Assets 4

Releases: bmerriott/MIMIC-Multipurpose-Intelligent-Molecular-Information-Catalyst-

Release list

Mimic AI Digital Assistant v 1.2.1

🎬 Demo Video

Mimic AI v1.2.0 - Voice Profiles & Enhanced TTS

🎉 Major Update

📦 What's Included

🚀 Getting Started

New Users

Upgrading from v1.1.0?

Prerequisites (Same as v1.1.0)

✨ What's New in v1.2.0

🎙️ Voice Profile System (New!)

🧠 Per-Persona Memory Isolation (New!)

🔊 Enhanced TTS Engine Support

🛡️ Improved Error Handling

🔧 Backend Improvements

🎬 VRMA Library Cleanup

⚠️ Important: License

📋 System Requirements

🐛 Known Issues

🔧 Troubleshooting

"Voice generation failed: Sizes of tensors must match"

Qwen3 TTS not working / Out of Memory

Text not appearing with voice prompts

All other issues

🎨 Attribution

📄 License

Uh oh!

Mimic AI Digital Assistant v 1.1.0

🎬 Demo Video

Mimic AI v1.1.0 - VRM Avatar & Persona Memory

🎉 Major Update

📦 What's Included

🚀 Getting Started

New Users

Upgrading from v1.0?

Prerequisites (Same as v1.0)

✨ What's New in v1.1.0

🎭 VRM Avatar Support (New!)

🎬 VRMA Animation Support (New!)

🧠 Avatar-Persona Memory Integration (New!)

🎨 Avatar Personality System (New!)

🧍 Persona Learning System (New!)

🔊 Procedural Vocalizations (New!)

🔧 Improvements

⚠️ Important: License Change

📋 System Requirements

🐛 Known Issues

🔧 Troubleshooting

Avatar not loading (red cube appears)

"VRM not found in library" error

Voice not working with Qwen3

All other issues (same as v1.0)

🎨 Attribution

📝 Checksums

📄 License

Uh oh!

Mimic AI Digital Assistant

Mimic AI v1.0.0 - Initial Release

🎉 First Official Release

📦 What's Included

🚀 Getting Started

Prerequisites

Installation

First Launch

✨ Features

🔧 Key Features

Automatic Ollama Configuration

Auto Model Selection

Direct SearXNG Connection

🐛 Known Issues

🔧 Troubleshooting

"Python not found" error

"Ollama not connected"

"TTS backend not connected"

Web search not working

📋 System Requirements

📝 Checksums

🙏 Credits