Lot Vulture has launched a software platform that converts existing RTSP, ONVIF, or snapshot IP cameras into real-time parking occupancy maps, using on-device computer vision to avoid the $200–$500 pe…
A developer built a hybrid video upscaler that runs entirely in the browser, dynamically switching between AI-based ONNX inference and WebGPU spatial upscaling based on input resolution. The tool, par…
Dubai startups in 2026 face stricter UAE data sovereignty and AI Act compliance, making on-device AI a strategic moat for corporate data privacy, according to a technical article promoting the FRIDAY …
Rostam Labs released Rembed, a pure-Go text embedding inference engine that runs BERT-style and decoder-derived embedding models without ONNX Runtime or cgo, achieving statistical parity with ONNX Run…
Clojurists Together's Q2 2026 funded project iLLaManati, led by Dragan Djuric, delivered a high-performance local LLM library in 100% Clojure, achieving 16 tokens/second on a 7-year-old CPU and 80+ to…
A developer has built Psycho-Acoustic, a mental health monitoring tool that uses the HuBERT model, HuggingFace Transformers, and Librosa to quantify emotional states from non-verbal acoustic features.…
Nari Labs, Meta, and the open-source community have released text-to-speech models that achieve sub-50 ms latency on consumer hardware, making instant voice for games and streams production-ready. A p…
A developer detailed a method for implementing object detection on Android devices to enable autonomous robots to recognize objects locally, reducing reliance on network connectivity. The approach use…
Engineers at an unnamed company cut inference cold start times from minutes to seconds by profiling their startup sequence and finding that 90% of the delay came from moving large files. They reduced …
NVIDIA Triton Inference Server is an open-source inference serving software that simplifies and accelerates AI model deployment across frameworks like TensorFlow, PyTorch, and ONNX Runtime on diverse …
ONNX Runtime, an open-source inference engine, enables interoperability of machine learning models across frameworks and hardware platforms by leveraging the ONNX standard. It simplifies deployment by…
An AWS developer built a zero-shot image classifier using a CLIP model inside a Lambda container to distinguish AWS Builder Cards from other images without any training data or GPU. The model, which e…
NobodyWho announced speech support in its on-device inference engine, adding Text to Speech (TTS) via Kokoro, Pocket TTS, and Supertonic, and Speech to Text (STT) via Whisper, all running on ONNX Runt…
FFmpeg 9.0 “Lei” shipped today, adding Vulkan GPU acceleration for 360-degree video and Samsung's APV codec, plus ONNX Runtime GPU execution for AI filters, while removing the CELT decoder and droppin…
FFmpeg 9.0, the latest feature release of the open-source multimedia library, is now available with more Vulkan acceleration, including APV video decoding and Apple ProRes RAW Vulkan acceleration, plu…
Oye Collective has built a local PII detection feature for coding agent transcripts that scans for secrets without sending data to the cloud. The system combines regex for structured tokens like API k…
DictaFlow's Local Offline Mode enables dictation on Windows, Apple silicon Macs, and iPhones without an internet connection using on-device models like NVIDIA's Parakeet TDT 0.6B v3, while competitor …
PostSlate, a video editing startup, achieves up to 10x faster inference on edge devices by switching from ONNX Runtime CPU to ncnn with Vulkan GPU backend, with ArcFace R50 dropping from 30 ms to 3 ms…
OpenSquilla's SquillaRouter uses a small on-device machine learning model to route each agent turn to the cheapest capable LLM provider, treating model choice as a live routing problem rather than a s…
A developer shipping three browser-based AI tools—a stem splitter using Meta's HTDemucs, a Whisper speech-to-text model, and a third unnamed tool—found that model corruption, ONNX Runtime graph optimi…