Tag
Lastbook 推出一款免费、本地、离线的桌面应用,整合生存与重建社会所需的急救、饮水、食物、维修知识、地图、视频,以及基于本地 Gemma 26B 模型的 AI 问答功能。
NIDO 0.1.67-alpha, a 100% offline personal AI assistant for Android, is released following a full app audit that identified 124 issues—88 of which are fixed and verified in this version, alongside 4,711 passing tests and a rebuilt Local knowledge pack.
Survival LLM is a free, open-source AI assistant and emergency reference library that runs fully offline on your own computer, answering first-aid and disaster-preparedness questions with citations from trusted sources like FEMA, CDC, and Wikipedia.
This paper presents the first end-to-end benchmark of a voice-first offline AI stack for African language communities, evaluating three instruction-tuned 2–5B models across four quantization formats on NVIDIA Jetson Orin NX and Raspberry Pi 5 hardware, finding that Q4_K_M offers the best size-to-quality trade-off.
A position paper introducing 'Model as a Library' (MaaL), a software architecture that packages small, community-enrolled speech models as versioned on-device dependencies for offline, hallucination-free data collection in low-resource African languages. It proposes keyword spotting to turn closed-vocabulary digital forms into voice-based, on-device data collection for low-literacy populations, and transpiling existing form tools into MaaL schemas.
A developer built a fully offline AI assistant on a Mac mini using a 3B parameter model that can diagnose and fix code errors via voice input with zero API costs and no internet, sharing the full build and repo.
NoteWorthy is a new AI-powered notes app launched on Product Hunt that runs entirely on-device across iPhone, iPad and Mac, auto-categorizing notes and generating summaries without any data leaving the device, no account, and no subscription.
An individual built an AI system for factory floors that operates offline to assist technicians by providing historical solutions for machine error codes.
This paper investigates offline multimodal large language models as decision support tools for air operations, detailing a modular retrieval-augmented architecture and presenting a pilot study with the Brazilian Air Force that demonstrates reduced cognitive workload and improved efficiency in doctrinal assessment tasks.
Audiobookify is an EPUB reader app for iPhone that features local offline TTS with optimized AI models for efficiency in battery life and narration quality.
A developer demonstrates a complete offline voice-to-action agent on Android using small local models (Silero VAD, Parakeet-EOU STT, FunctionGemma 270M, Pocket TTS), running in ~1.2 GB with no cloud dependencies.
A tweet highlights a GPU dock praised as the nicest ever made, with a previous demo running a local, offline LLM over USB using a 24GB GPU.
Google's Developer Expert community built an offline AI racing coach that processes live car telemetry at the edge, demonstrating real-time AI without cloud reliance.
NativeMind is a private, open-source browser extension that runs local AI models via Ollama or WebLLM, enabling offline AI features for privacy-conscious users.
A fully offline AI reads over 4,000 pages of declassified UFO files using OCR and vector database, providing cited answers locally without cloud or API keys.
Introduces how to run a private AI locally on a 16GB RAM laptop using Ollama, no subscription or API key required, with offline use and privacy protection.
Small AI models are proving valuable in regions with unreliable networks, enabling life-saving applications like counterfeit drug detection and disease identification in crops without needing constant internet connectivity.
Project Nomad is a fully offline survival AI computer, integrating local AI chat, Wikipedia, maps, courses and other massive offline content, supporting one-click deployment, suitable for scenarios like network outages, remote areas, etc.
Introduces Agentic Swarm, an open-source desktop application that orchestrates 5 AI agents using Google's Gemma-4 model, running entirely offline.
The two most powerful AI models (Fable 5 and GPT 5.6) have allegedly been locked behind government access, prompting the author to build a private offline AI agent using a local model on a MacBook.