{"data":{"slug":"timmyy123-llm-hub","name":"LLM-Hub","tagline":"Local AI Assistant on your phone","github_url":"https://github.com/timmyy123/LLM-Hub","owner":"timmyy123","repo":"LLM-Hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/164847362?v=4","primary_language":"C++","stars":561,"forks":116,"topics":["ai","gemma","gemma4","gemma4-agent-skills","gptoss","granite","imagegeneration","lfm25","llama","llm","llm-inference","mistral","music","musicgeneration","phi4","rag","stable-diffusion","videogeneration","whisper"],"archived":false,"github_pushed_at":"2026-08-24T07:20:33+00:00","maintenance_label":"Very active","stars_delta_30d":47,"url":"https://www.graphcanon.com/tools/timmyy123-llm-hub","markdown_url":"https://www.graphcanon.com/tools/timmyy123-llm-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/timmyy123-llm-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=timmyy123-llm-hub","description":"Local AI Assistant","homepage_url":"https://llm-hub.app","license":"Other","open_issues":37,"watchers":10,"ai_summary":"timmyy123/LLM-Hub offers a local deployment of an AI assistant for mobile devices using C++. It supports various models and frameworks, including LLM inference and model training.","readme_excerpt":"# LLM Hub πŸ€–\n\n**LLM Hub** is an open-source mobile app for on-device LLM chat, image generation, video generation, and music generation, available for both **Android** and **iOS**. It's optimized for mobile usage (CPU/GPU/NPU acceleration) and supports multiple model formats so you can run powerful models locally and privately.\n\n🌟 **Featured:** Featured by **RunAnywhere** on their website β€” read the [LLM Hub iOS Case Study](https://www.runanywhere.ai/blog/llm-hub-ios-case-study)!\n\n## Download\n\n\n \n \n \n \n
\n \n \n \n
\n\n**πŸ’» Desktop Versions Coming:** Windows and macOS native apps are planned, bringing desktop-class experiences with advanced cursor integration and Claude Code–like capabilities.\n\n\n## πŸ“Έ Demo & Screenshots\n\n| Vibe Coder Demo on iOS | Image Generation on Android |\n| :-: | :-: |\n| | |\n| Vibe Coder using Gemma 4 model on iPhone (HTML preview) | Stable Diffusion image generation on Android |\n\n| AI Agent Termux Command Execution on Android | Music Generation on iOS |\n| :-: | :-: |\n| | |\n| Autonomous AI Agent executing Termux shell commands (`ls` list files) with live terminal output on Android | On-device music generation with Magenta Realtime 2 on iPhone |\n\n## πŸš€ Features\n\n### πŸ› οΈ AI Tools Suite\n| Tool | Description |\n|------|-------------|\n| **πŸ’¬ Chat** | Multi-turn conversations with RAG memory, web search, TTS auto-readout, and multimodal input |\n| **πŸ€– AI Agent** | **[NEW]** Autonomous device agent with function calling, interactive maps, device tools, MCP tools, and Termux terminal command generation on Android |\n| **πŸ€– creAItor** | **[NEW]** Design custom AI personas with specialized system prompts (PCTF) in seconds |\n| **πŸ’» Vibe Coder** | **[NEW]** Explain your app idea and watch it be built in real-time with live HTML/JS preview |\n| **✍️ Writing Aid** | Summarize, expand, rewrite, improve grammar, or generate code from descriptions |\n| **🎨 Image Generator** | Create images from text prompts using Stable Diffusion 1.5 with swipeable gallery |\n| **🎡 Music Generator** | **[NEW]** Generate music and sound effects locally with SoundGen on Android and Magenta Realtime 2 on iOS |\n| **πŸ” Image Upscale** | **[NEW]** Upscale images up to 4Γ— using AI super-resolution models (RealESRGAN, UltraSharp) with NPU acceleration |\n| **πŸŽ₯ Video Generator** | **[NEW]** Generate videos from text prompts or images using Stable Video Diffusion on iOS |\n| **🌍 Translator** | Translate text, images (OCR), and audio across 50+ languages - offline |\n| **πŸŽ™οΈ Transcriber** | Convert speech to text with on-device processing using Whisper models |\n| **πŸ›‘οΈ Scam Detector** | Analyze messages and images for phishing with risk assessment |\n| **πŸ—£οΈ VibeVoice** | **[NEW]** Hands-free AI voice chat |\n\n### πŸ€– AI Agent & Termux Terminal Command Generation\nThe **AI Agent** turns on-device LLMs into autonomous assistants with device function calling capabilities:\n- **Device Actions & Function Calling**: Embedded interactive maps (OpenStreetMap), calendar management, alarm setup, flashlight toggle, SMS & Email composition, cryptographic hashing (SHA-256/MD5), and math calculation.\n- **MCP Tools**: Connect Model Context Protocol (MCP) servers so the Agent can discover and use e","github_created_at":"2025-07-08T09:40:31+00:00","created_at":"2026-07-11T11:45:39.557229+00:00","updated_at":"2026-08-25T06:02:20.217803+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"gemma3","name":"gemma3"},{"slug":"gemma3n","name":"gemma3n"},{"slug":"gemma4","name":"gemma4"},{"slug":"gemma4-agent-skills","name":"gemma4-agent-skills"},{"slug":"gptoss","name":"gptoss"},{"slug":"granite","name":"granite"},{"slug":"lfm25","name":"lfm25"}],"trust":{"provenance":{"is_fork":false,"github_id":1015965886,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-25T06:02:19.503Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":0,"last_release_at":"2026-06-03T16:25:29Z","stars_delta_30d":47,"open_issues_delta_30d":6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:45:40.682Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-25T06:02:19.939Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-08-25T06:02:19.939Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-25T06:02:19.939Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need local deployment of LLMs on mobile devices without relying on cloud services.","Developing applications in C++ that require AI inference and training functionalities."],"when_not_to_use":["Your project requires real-time heavy-load AI operations beyond what mobile resources can handle locally.","If your application is not compatible with or cannot be adapted to a C++ environment."],"source":"enrich:decision_facts","observed_at":"2026-07-16T20:19:13.990Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Local AI assistant for mobile phones via C++, supports multiple models."}]}}