1 file changed
+62
-25
README.md
+62
-25
@@ -16,46 +16,81 @@ LocalMind is a premium Flutter mobile application designed to provide a beautifu
16
</a>
17
</p>
18
19
-## 🚀 Vision
19
+## Vision
20
21
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.
22
23
-## ✨ Key Features
24
-
25
-- 📲 **On-Device AI Support (Android)**: Private, fast, and offline. Run powerful AI models directly on your device with no internet required.
26
-- 📂 **Model Manager**: Download and manage curated models like Qwen 3 (0.6B), DeepSeek R1, and Gemma 4 directly within the app.
27
-- 🖥️ **Multi-Server Connection**: Seamlessly connect to LM Studio, Ollama, or OpenRouter with real-time health monitoring.
28
-- 💬 **Premium Chat Experience**: A polished, ChatGPT/Claude-inspired interface with:
29
- - **Streaming Responses**: Real-time SSE support for instant feedback.
30
- - **Markdown Rendering**: Beautiful rendering of text and code with syntax highlighting.
31
- - **Message Actions**: Copy, retry, or delete individual messages with a long-press menu.
32
-- 🎨 **Revamped Sidebar**: A cleaner, more intuitive, and feature-rich navigation experience.
33
-- 🧠 **Persona Management**: Switch between specialized AI personas (Code Assistant, Math Tutor, etc.) or create your own with custom system prompts.
34
-- 🔄 **Live Model Swapping**: Change the active model mid-conversation without losing context.
35
-- 📦 **Conversation History**: Full-text search through your past chats, pinning important conversations, and local-only storage.
36
-- 🎨 **Deep Customization**:
37
- - **Theming**: Premium dark-first design (with light mode support).
38
- - **Chat Parameters**: Fine-tune temperature, top_p, max tokens, and context length.
39
-
40
-## 🛠️ Tech Stack
23
+## Key Features
24
+
25
+- **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.
26
+- **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.
27
+- **Model Manager**: Download curated models or download GGUF models directly from HuggingFace. Manage model files directly within the app.
28
+- **Multi-Server Connection**: Connect to Ollama, LM Studio, OpenRouter, or any OpenAI-compatible API with real-time server health and speed monitoring.
29
+- **Premium Chat Experience**: A polished, Claude/ChatGPT-inspired user interface featuring:
30
+ - **Streaming Responses**: Real-time SSE support for instant generation.
31
+ - **Markdown Rendering**: Beautiful rendering of text and code with rich syntax highlighting.
32
+ - **Expandable Reasoning Logs**: Collapsible, step-by-step visualization of thought processes for reasoning models like DeepSeek R1.
33
+ - **Edit & Regenerate**: Edit past user prompts to truncate the conversation history and regenerate responses.
34
+ - **Saved Messages Picker**: Quick-access shortcut in the input bar to store, organize, and reuse prompts or templates.
35
+ - **Message Variants**: Swipe and navigate through alternative model replies/variations.
36
+ - **Temporary Chats**: Incognito mode that allows conversations to run in-memory without saving logs to local history.
37
+ - **Smart Suggested Replies**: Context-aware follow-up prompts to keep conversations going.
38
+- **Voice & Audio (STT & TTS)**:
39
+ - **Speech-to-Text (STT)**: Dictate your prompts directly via native voice input.
40
+ - **Text-to-Speech (TTS)**: Listen to model responses with custom playback speeds, replay caching, and background play.
41
+- **Multimodal & Attachments**: Attach photos, documents, and other files to prompt vision-capable models.
42
+- **Persona Management**: Easily switch between specialized AI personas (Code Assistant, Math Tutor, etc.) or create your own with custom system instructions.
43
+- **Live Model Swapping**: Swap active models mid-conversation without breaking context or losing chat history.
44
+- **Conversation History**: Full-text search through your chats, folder grouping, pinning, and local-only storage.
45
+- **Backup & Restore**: Export and import complete backup archives (including chat history, personas, and app settings) locally.
46
+- **Deep Customization**:
47
+ - **Theming**: Premium dark-first interface with full light mode support.
48
+ - **Chat Parameters**: Fine-tune temperature, top_p, max token limits, and context window size.
49
+
50
+## Tech Stack
51
52
LocalMind is built with modern, scalable technologies:
53
54
- **Framework**: [Flutter](https://flutter.dev/) (Latest Stable)
45
-- **On-Device AI**: [LiteRT (TensorFlow Lite)](https://ai.google.dev/edge/litert) for high-performance localized inference.
55
+- **On-Device AI**: `llamadart` + `flutter_gemma` (supporting llama.cpp & LiteRT) for native, high-performance localized inference.
56
- **UI Components**: Shadcn-inspired design system (`shadcn_ui`)
57
- **State Management**: [Riverpod](https://riverpod.dev/) for robust, testable state.
58
- **Local Storage**: [ObjectBox](https://objectbox.io/) (and Hive) for high-performance on-device persistence.
59
- **Networking**: [Dio](https://pub.dev/packages/dio) for optimized REST API handling.
50
-- **Rendering**: `flutter_markdown` + `flutter_highlight` for rich content.
60
+- **Rendering**: `gpt_markdown` + `syntax_highlight` for rich content.
61
52
-## 🛡️ Privacy First
62
+## Privacy First
63
64
- **Zero Analytics**: We don't track how you use the app.
65
- **Local Storage**: Your conversations are stored only on your device, encrypted via Hive.
66
- **Direct Traffic**: Network requests go directly to _your_ servers. LocalMind never sees your data.
67
58
-## 🗺️ Roadmap (Future Plans)
68
+## Contributors
69
+
70
+We are incredibly grateful to the developers who have helped build LocalMind:
71
+
72
+<p align="left">
73
+ <a href="https://github.com/abdulmominsakib">
74
+ <img src="https://github.com/abdulmominsakib.png?size=100" width="50" height="50" style="border-radius: 50%; margin-right: 4px;" title="Abdul Momin Sakib (abdulmominsakib)" alt="Abdul Momin Sakib"/>
75
+ </a>
76
+ <a href="https://github.com/onlypuppy7">
77
+ <img src="https://github.com/onlypuppy7.png?size=100" width="50" height="50" style="border-radius: 50%; margin-right: 4px;" title="onlypuppy7" alt="onlypuppy7"/>
78
+ </a>
79
+ <a href="https://github.com/leo-rnl">
80
+ <img src="https://github.com/leo-rnl.png?size=100" width="50" height="50" style="border-radius: 50%; margin-right: 4px;" title="Léo Reynal (leo-rnl)" alt="Léo Reynal"/>
81
+ </a>
82
+ <a href="https://github.com/dtrknt15">
83
+ <img src="https://github.com/dtrknt15.png?size=100" width="50" height="50" style="border-radius: 50%; margin-right: 4px;" title="dtrknt15" alt="dtrknt15"/>
84
+ </a>
85
+ <a href="https://github.com/NJannasch">
86
+ <img src="https://github.com/NJannasch.png?size=100" width="50" height="50" style="border-radius: 50%; margin-right: 4px;" title="Nils Jannasch (NJannasch)" alt="Nils Jannasch"/>
87
+ </a>
88
+ <a href="https://github.com/ystartgo">
89
+ <img src="https://github.com/ystartgo.png?size=100" width="50" height="50" style="border-radius: 50%; margin-right: 4px;" title="ystartgo" alt="ystartgo"/>
90
+ </a>
91
+</p>
92
+
93
+## Roadmap (Future Plans)
94
95
LocalMind is rapidly evolving. Here is what's coming next:
96
@@ -65,8 +100,10 @@ LocalMind is rapidly evolving. Here is what's coming next:
100
- [x] **Tablet/Desktop Optimization**: A split-view layout for large-screen productivity.
101
- [x] **Export Options**: Export your chats to Markdown or PDF to share or archive.
102
- [ ] **Quick Shortcuts**: OS-level widgets and shortcuts for launching new chats instantly.
103
+- [ ] **Voice-to-Voice Mode**: Engage in real-time, low-latency spoken conversations with local models.
104
+- [ ] **S3 Cloud Sync**: End-to-end encrypted cloud sync for settings, custom personas, and chats in your own S3 server.
105
69
-## 🛠️ Getting Started
106
+## Getting Started
107
108
### Prerequisites
109
@@ -81,6 +118,6 @@ LocalMind is rapidly evolving. Here is what's coming next:
118
119
---
120
84
-## 📄 License
121
+## License
122
123
LocalMind is open source and available under the MIT License. Contributions are welcome!