CategoryTech Trends

How to Detect Motion Through Walls with ESPectre

H

ESPectre turns a cheap ESP32 board into a motion detector that reads Wi-Fi signal changes rather than using cameras or microphones. It runs as a lightweight firmware and integrates with Home Assistant through ESPHome or MQTT. The system samples CSI (channel state information) from nearby Wi-Fi traffic and applies signal analysis to detect movement through walls. No AI models are involved — it...

How to Transfer Files Securely with E2ECP P2P Encryption

H

E2ECP is a peer-to-peer file transfer tool that works from the web or the CLI. It enables direct, end-to-end encrypted transfers between peers without accounts, cloud storage, or trusting an intermediary. You can share large files by simply creating a room and having your peer join. The system uses P-256 key exchange and AES-GCM for authenticated encryption. Relays assist with NAT traversal but...

Acontext, Open Skill Memory for Agents

A

Acontext is an open skill memory layer for AI agents. It captures learnings from agent runs and turns them into editable skill files. Past executions become reusable across agents and frameworks. The goal is agents that learn from past runs without opaque context pollution. acontext repo snapshot What it does Acontext captures task outcomes, observations, and repeatable patterns from agent...

How to Code on Your Phone with Doom-Coding

H

Doom-Coding is a practical workflow for writing code from your phone. It replaces doom-scrolling with productive programming sessions by using a Tailscale VPN, a terminal app like Termius, and Claude Code running on a persistent home machine you SSH into. The setup lets you prototype and ship projects from cafes, trains, or anywhere with a phone connection. The approach pairs mobile remote access...

How to Run 1-Bit LLMs on CPU with BitNet.cpp

H

BitNet.cpp is Microsoft’s official inference framework for 1-bit LLMs. It enables running very large quantized models on standard CPUs without GPU hardware. The framework provides optimized kernels for lossless inference at 1.58-bit precision using the BitNet b1.58 architecture. The first release focuses on CPU inference, with GPU and NPU support planned. This lets you run models that...

Get in touch

Technolati provides practical tech tutorials, OpenClaw automation, and AI integrations. Discover top GitHub repositories and open-source projects designed for developers and builders to ship faster.