OffGridPete writes that Fieldwatch is a passive, receive-only Android app that listens for nearby Wi-Fi access points and Bluetooth LE advertisements to help users identify radio sources around them. Built as a personal hobby tool, it runs entirely offline with no account, no backend server, and no dongle. The app was originally named Spectre but was renamed to avoid confusion with another existing app, and it is distributed as a sideload APK under the MIT License.
- Includes an extensible signature library for identifying radio sources
- Features GPS co-travel detection ("possible tail") and a Debrief report
- Privacy mode can mask Remote IDs on-screen while full coordinates are retained in logs
- Not capable of capturing Wi-Fi probe frames, Bluetooth Classic, cellular, or direction-finding data
- Includes an extensible signature library for identifying radio sources
- Features GPS co-travel detection ("possible tail") and a Debrief report
- Privacy mode can mask Remote IDs on-screen while full coordinates are retained in logs
- Not capable of capturing Wi-Fi probe frames, Bluetooth Classic, cellular, or direction-finding data
Hylki is a fast, GNOME-native email client built in Rust with GTK 4 and libadwaita, offering a three-pane layout, unified inbox, and first-class OAuth support with privacy as a core design principle.
- The app contains no generative AI features and never sends mail to such services, though the majority of its Rust code was written with Claude Code
- Hylki is the successor to two earlier projects (Veem and Vireo) and can install alongside Vireo, automatically migrating accounts, settings, and cached mail on first launch
- The Flatpak is the only recommended install method, as Arch, Debian/Ubuntu, and Snap packages were discontinued after version 1.7.0
- The app contains no generative AI features and never sends mail to such services, though the majority of its Rust code was written with Claude Code
- Hylki is the successor to two earlier projects (Veem and Vireo) and can install alongside Vireo, automatically migrating accounts, settings, and cached mail on first launch
- The Flatpak is the only recommended install method, as Arch, Debian/Ubuntu, and Snap packages were discontinued after version 1.7.0
OpenHuman is an open-source agent harness designed as a personal AI super intelligence, featuring local-first memory through Markdown trees in SQLite and orchestration capabilities via checkpointed graphs. It functions as a brain that builds persistent context from various data sources like email and calendars, acting as both an orchestrator for multi-agent workflows and a deep researcher with built-in web search and media generation tools.
- Features "Memory Trees" stored locally in Markdown format to create a Karpathy-style Obsidian wiki.
- Provides end-to-end encrypted agent-to-agent messaging using the Signal protocol.
- Supports visual, trigger-driven workflows that can be proposed by an AI and reviewed on a canvas.
- Includes a "Privacy Mode" which ensures no inference data leaves the user's machine when toggled.
- Features "Memory Trees" stored locally in Markdown format to create a Karpathy-style Obsidian wiki.
- Provides end-to-end encrypted agent-to-agent messaging using the Signal protocol.
- Supports visual, trigger-driven workflows that can be proposed by an AI and reviewed on a canvas.
- Includes a "Privacy Mode" which ensures no inference data leaves the user's machine when toggled.
An investigation into how smart TVs collect and transmit user data back to manufacturers. This research examines the extent of telemetry in modern televisions, focusing on privacy implications and methods used for tracking viewer habits through Automatic Content Recognition (ACR).
- The mechanics of background data collection within operating systems
- Privacy risks associated with continuous monitoring
- Differences in tracking practices across various major brands
- The mechanics of background data collection within operating systems
- Privacy risks associated with continuous monitoring
- Differences in tracking practices across various major brands
The article discusses the benefits of running Google’s Gemma 4 models locally on personal hardware to ensure data privacy and independence from cloud services. By executing these multimodal models on a laptop, users can process images and audio without exposing sensitive information to third-party servers. The text highlights how efficient architecture allows for vision capabilities and speech recognition even with limited VRAM.
* Localized processing avoids the risks of uploading private or regulated data
* Native audio support in specific model variants like E2B and E4B
* Large context windows allow for deep analysis of lengthy documents and codebases
* Reduced reliance on internet connectivity during mobile workflows
* Localized processing avoids the risks of uploading private or regulated data
* Native audio support in specific model variants like E2B and E4B
* Large context windows allow for deep analysis of lengthy documents and codebases
* Reduced reliance on internet connectivity during mobile workflows
This article explores the practical differences between using browser extensions for ad-blocking and implementing a network-wide DNS sinkhole. While browser tools like uBlock Origin provide granular element filtering, they only protect specific applications. A DNS sinkhole protects every device on a home network—including smart TVs and IoT devices—by intercepting malicious or tracking domains at the DNS level. For maximum protection, the author suggests using both methods together to combine wide-scale domain blocking with fine-grained cosmetic filtering.
TextGen is an open-source desktop application designed for running large language models locally with complete privacy and zero telemetry. It provides a user interface and API that supports text, vision, tool-calling, and web search functionality. The software allows users to switch between multiple backends such as llama.cpp, Transformers, ExLlamaV3, and TensorRT-LLM without restarting the application.
Main topics:
Multimodal support for visual understanding via image attachments
OpenAI/Anthropic compatible API with tool-calling capabilities
Fine-tuning functionality for LoRAs on chat or raw text datasets
Integrated image generation using diffusers models
Support for various installation methods including portable builds and Docker
Main topics:
Multimodal support for visual understanding via image attachments
OpenAI/Anthropic compatible API with tool-calling capabilities
Fine-tuning functionality for LoRAs on chat or raw text datasets
Integrated image generation using diffusers models
Support for various installation methods including portable builds and Docker
Most users treat self-hosted large language models like a simple chat interface, effectively limiting their potential to basic question-and-answer tasks. The author suggests moving beyond this ChatGPT clone approach by integrating local AI as an always-on intelligence layer within your digital workflow. By treating the LLM as a backend engine rather than just a website, you can gain superior privacy and control while automating complex tasks across your files and devices.
- Theft Detection Lock with offline and authentication safeguards
- Private Space sandboxing for app isolation
- Now Playing background music recognition
- Private Space sandboxing for app isolation
- Now Playing background music recognition
While cloud-based AI models are more powerful, running small language models locally on a smartphone offers unique advantages in privacy and practicality. This article explores how on-device LLM can be used for tasks that don't require massive computing power but benefit from being offline or private. Key use cases include:
* Using it as a private thinking partner for personal questions.
* Organizing messy, unstructured notes and brain dumps.
* Performing quick code logic checks and debugging snippets while away from a computer.
* Acting as a low-pressure language tutor that works without an internet connection.
* Using multimodal capabilities to analyze images like whiteboards or product labels via the phone camera.
* Using it as a private thinking partner for personal questions.
* Organizing messy, unstructured notes and brain dumps.
* Performing quick code logic checks and debugging snippets while away from a computer.
* Acting as a low-pressure language tutor that works without an internet connection.
* Using multimodal capabilities to analyze images like whiteboards or product labels via the phone camera.
