Here's a thinking process: 1. **Analyze User Input:** - **Role:** Technical news summarizer - **Task:** Condense provided news into brief HTML summary - **Input:** A news item with title, source, URL, author, date, and description - **Output Format:** Specific HTML with `

` for 2-4 sentence summary and `` for link - **Rules:** - 2-4 sentences max - Precise technical language - No invented info - Output ONLY valid HTML, no text before/after - English only 2. **Extract Key Info from News:** - Title: `jundot /omlx` - Source: `github-trending/python` - URL: `https://github.com/jundot/omlx` - Author: `jundot` - Date: `2026-08-17` - Description: `LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar` 3. **Draft Summary (2-4 sentences, technical, precise):** - Key points: LLM inference server, continuous batching, SSD caching, Apple Silicon, macOS menu bar management - Draft 1: omlx is an LLM inference server optimized for Apple Silicon