flutter{"sdk":"flutter"}
flutter_localizations{"sdk":"flutter"}
intlany
cupertino_icons^1.0.8
flutter_riverpod^3.3.1
go_router^17.1.0
shadcn_ui^0.54.0
url_launcher^6.3.1
characters^1.4.0
dio^5.9.2
flutter_secure_storage^10.3.1
aws_common^0.7.7
aws_signature_v4^0.6.11
cryptography^2.9.0
flutter_tts^4.2.5
file_picker^12.0.0-beta.5
path_provider^2.1.5
haptic_feedback^0.6.4+3
hugeicons^1.1.5
google_fonts^8.1.0
syntax_highlight{"git":{"url":"https://github.com/abdulmominsakib/syntax_highlight.git"}}
animations^2.2.0
cue^0.3.1
logger^2.7.0
shared_preferences^2.5.5
objectbox^5.3.1
objectbox_flutter_libs^5.3.1
path^1.9.1
flutter_gemma^1.7.0
flutter_gemma_litertlm^1.6.0
llamadart^0.8.4
llamadart_llama_cpp_flutter^0.0.4
wakelock_plus^1.2.8
flutter_local_notifications^22.0.1
audioplayers^6.4.0
just_audio^0.10.5
just_audio_background^0.0.1-beta.17
audio_session^0.2.3
device_info_plus^13.1.0
package_info_plus^10.1.0
in_app_review^2.0.12
sherpa_onnx^1.13.2
archive^4.0.2
loading_animation_widget^1.3.0
gpt_markdown^1.1.7
speech_to_text^7.4.0
share_plus^13.2.0
image_picker^1.1.2
pdfrx^2.4.7
permission_handler^11.4.0
auto_size_text_plus^3.0.2
device_calendar_plus^0.8.0
home_widget^0.9.3
apple_mlx{"path":"packages/apple_mlx"}
flutter_gemma_builtin_ai^0.2.1
geolocator^14.0.3
geocoding^5.0.0
flutter_sms_inbox^1.0.5
flutter_test개발 의존성{"sdk":"flutter"}
plugin_platform_interface개발 의존성^2.1.8
url_launcher_platform_interface개발 의존성^2.3.2
flutter_lints개발 의존성^6.0.0
build_runner개발 의존성^2.13.1
change_app_package_name개발 의존성^1.4.0
objectbox_generator개발 의존성any

앱 카테고리

생성형 AI 및 LLM

원본 README

아래는 영문 원문 스냅샷입니다. 최신 내용은 GitHub에서 확인하세요.

README 펼치기 / 접기

LocalMind

Your AI. Your Device. Your Rules.

LocalMind is a premium Flutter mobile application designed to provide a beautiful, fast, and privacy-respecting interface for local LLM servers and cloud providers.

LocalMind Header Image

https://raw.githubusercontent.com/abdulmominsakib/localmind/HEAD/docs/appstore_download_button.svg https://raw.githubusercontent.com/abdulmominsakib/localmind/HEAD/docs/playstore_download_button.webp https://raw.githubusercontent.com/abdulmominsakib/localmind/HEAD/docs/github_download_button.webp

Vision

Built for those who value privacy and performance, LocalMind connects directly to your local inference servers like LM Studio or Ollama, as well as cloud providers like OpenRouter. No middleware, no tracking, and no hidden subscriptions. Just you and your models.

Key Features

On-Device AI Support (iOS & Android): Private, fast, and offline. Run powerful GGUF and LiteRT models (Gemma, Qwen, DeepSeek R1) directly on your device via llamadart and flutter_gemma. No internet connection required.
Model Context Protocol (MCP): Seamlessly connect to local or remote MCP servers. Grant models access to custom tools and integrations (e.g., file access, web APIs, shell actions) with fine-grained global and chat-level toggles.
Model Manager: Download curated models or download GGUF models directly from HuggingFace. Manage model files directly within the app.
Multi-Server Connection: Connect to Ollama, LM Studio, OpenRouter, or any OpenAI-compatible API with real-time server health and speed monitoring.
Premium Chat Experience: A polished, Claude/ChatGPT-inspired user interface featuring:
- Streaming Responses: Real-time SSE support for instant generation.
- Markdown Rendering: Beautiful rendering of text and code with rich syntax highlighting.
- Expandable Reasoning Logs: Collapsible, step-by-step visualization of thought processes for reasoning models like DeepSeek R1.
- Edit & Regenerate: Edit past user prompts to truncate the conversation history and regenerate responses.
- Saved Messages Picker: Quick-access shortcut in the input bar to store, organize, and reuse prompts or templates.
- Message Variants: Swipe and navigate through alternative model replies/variations.
- Temporary Chats: Incognito mode that allows conversations to run in-memory without saving logs to local history.
- Smart Suggested Replies: Context-aware follow-up prompts to keep conversations going.
Voice & Audio (STT & TTS):
- Speech-to-Text (STT): Dictate your prompts directly via native voice input.
- Text-to-Speech (TTS): Listen to model responses with custom playback speeds, replay caching, and background play.
Multimodal & Attachments: Attach photos, documents, and other files to prompt vision-capable models.
Persona Management: Easily switch between specialized AI personas (Code Assistant, Math Tutor, etc.) or create your own with custom system instructions.
Live Model Swapping: Swap active models mid-conversation without breaking context or losing chat history.
Conversation History: Full-text search through your chats, folder grouping, pinning, and local-only storage.
Backup & Restore: Export and import complete backup archives (including chat history, personas, and app settings) locally.
Deep Customization:
- Theming: Premium dark-first interface with full light mode support.
- Chat Parameters: Fine-tune temperature, top_p, max token limits, and context window size.

Tech Stack

LocalMind is built with modern, scalable technologies:

Framework: Flutter (Latest Stable)
On-Device AI: llamadart + flutter_gemma (supporting llama.cpp & LiteRT) for native, high-performance localized inference.
UI Components: Shadcn-inspired design system (shadcn_ui)
State Management: Riverpod for robust, testable state.
Local Storage: ObjectBox (and Hive) for high-performance on-device persistence.
Networking: Dio for optimized REST API handling.
Rendering: gpt_markdown + syntax_highlight for rich content.

Privacy First

Zero Analytics: We don't track how you use the app.
Local Storage: Your conversations are stored only on your device, encrypted via Hive.
Direct Traffic: Network requests go directly to your servers. LocalMind never sees your data.

Contributors

We are incredibly grateful to the developers who have helped build LocalMind:

Abdul Momin Sakib onlypuppy7 Léo Reynal dtrknt15 Nils Jannasch ystartgo

Roadmap (Future Plans)

LocalMind is rapidly evolving. Here is what's coming next:

[x] AI Voice (Text-to-Speech): Listen to your AI's responses with high-quality TTS.
[x] Context Smart Replies: Integrated suggested follow-ups to keep the conversation flowing.
[x] Multimodal Support: Attach images and documents for vision-capable models.
[x] Tablet/Desktop Optimization: A split-view layout for large-screen productivity.
[x] Export Options: Export your chats to Markdown or PDF to share or archive.
[x] Quick Shortcuts: OS-level widgets and shortcuts for launching new chats instantly.
[x] Voice-to-Voice Mode: Engage in real-time, low-latency spoken conversations with local models.
[x] S3 Cloud Sync: End-to-end encrypted cloud sync for settings, custom personas, and chats in your own S3 server.

Getting Started

Prerequisites

Flutter SDK (latest stable)
A running local LLM server (e.g., Ollama or LM Studio)

Installation

Clone the repository: git clone https://github.com/abdulmominsakib/localmind.git
Install dependencies: flutter pub get
Run the app: flutter run

License

LocalMind is open source and available under the MIT License. Contributions are welcome!