The AlgoFly Journal.
Inside the tools we build and the ideas that move us forward.
Practical perspectives on AI, engineering, and open source.
Voice Keyboard: Self-Hosted Whisper Dictation That Types into Your Apps
Turn speech into keyboard input with your own Whisper server, desktop clients, and an optional ESP32 Bluetooth keyboard.
Inside PortHub: Shared Terminals, Private Networks, and the Tools Between Them
Persistent terminal sharing, resumable file sync, screenshot links, smart web proxies, and modular native agents: explore what makes PortHub different.
Inside Autolycus Search: Streaming Jackett Results Before Every Indexer Finishes
How Autolycus turns Jackett into an incremental search experience with bounded concurrency, live filtering, cancellation, and visible indexer errors.
Building Label Assist with Segment Anything in Our Annotation Tool
How promptable segmentation becomes useful labeling assistance: editable proposals, human review, coordinate mapping, and reliable dataset exports.
How to Train an Image Classification Model with DINOv3 on a Custom Dataset
Foundation models are revolutionizing computer vision, and Meta's DINOv3 stands out as a particularly powerful vision backbone. If you're looking to achieve state-of-the-art performance on your custom image classification tasks, DINOv3 is a
Introducing SAHI and Sliding Window Functions for Large Image Processing
What is Small Object Detection? Detecting very small objects in images is a hard problem in computer vision. Normally, when an image is sent through a detection model, it has to be resized to fit the model’s input size, which is usually no
A Remote PC Power Button with ESP8266: Control, Status, and the Details That Matter
A close look at AlgoFly’s ESP8266 power-button project: a browser control, WebSocket status, relay timing, and reliable standby power.