← All sources

PyTorchKR news

The latest AI and developer news from PyTorchKR, with short summaries.

Visit website →

WeClaw Releases Bridge Connecting WeChat with AI Agents

It is an open-source tool that links WeChat messages with AI agents like Claude and Gemini for remote control.

·2026.07.15 10:00

Rust-based PDF-to-Markdown extraction tool released

It's a high-performance Rust library that determines whether a PDF contains text without OCR and converts it to Markdown.

·2026.07.15 08:00

Google Unveils SensorFM, a Health Foundation Model Built on 1 Trillion Minutes of Data

Google announced SensorFM, a large-scale health foundation model built using wearable data from 5 million people.

·2026.07.15 06:00

Hands-on Tutorial Generation Tool Lathe Released

Lathe, a tool that lets you learn LLM-generated technical tutorials by practicing directly in a local UI, has been released.

·2026.07.14 20:00

colibri: Running a 744B MoE on a Consumer PC

An inference engine written in C has been released that keeps a large MoE model's weights on disk and streams only the parts needed, allowing it to run even on low-spec PCs.

·2026.07.14 15:00

Introducing Weft, an AI Orchestration Language

Weft is introduced as a programming language that automates the construction of AI systems by using LLMs, humans, and APIs as first-class nodes.

·2026.07.14 12:00

AI Agent Proxy Server Plano Unveiled

Plano, an AI-native proxy server that solves the deployment and operational complexity of agent apps, has been unveiled.

·2026.07.14 08:00

LOTUS: An LLM-Based Framework for Large-Scale Data Processing

This introduces LOTUS, an LLM-based data analysis optimization framework developed by researchers at Stanford and Berkeley.

·2026.07.14 06:00

Meta Unveils IKBO for RecSys Inference Optimization

Meta has unveiled IKBO technology that eliminates the redundant data duplication overhead occurring during recommendation model inference.

·2026.07.13 22:00

NVIDIA Unveils 4D Interaction Reconstruction Technology from Monocular Video

It is a technology that reconstructs 4D interactions between humans and objects, without restriction to object categories, using only a single RGB video.

·2026.07.13 21:00

Google Unveils Nexus, a Multi-Agent Time-Series Forecasting Framework

Google researchers proposed Nexus, a multi-agent time-series forecasting framework that simultaneously processes numerical data and textual context.

·2026.07.13 18:00

Collection of Social Media Content Creation Skills for Claude Released

A workflow-based skill collection has been released to help Claude agents produce consistent content.

·2026.07.13 16:00

System Prompt Released to Reduce Verbosity in LLM Responses

It's an open-source system prompt project that helps LLMs deliver only the core content by removing unnecessary embellishments and repetition.

·2026.07.13 15:00

BigSet, an AI Agent That Generates Datasets from Natural Language

It's an AI agent tool that explores the web using only natural language commands to generate and automatically update structured datasets.

·2026.07.13 14:00

UI Design Guide for Agents 'Skills for Design Engineers' Released

A collection of agent skills has been released to help coding agents implement UI animations and design details with precision.

·2026.07.13 12:00