{"type": "article", "title": "ContextMemory – Markdown memory for your llama.cpp/vLLM server", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/contextmemory-markdown-memory-for-your-llama-cpp-vllm-server", "original_source": "https://github.com/Kortexio/ContextMemory", "published": "2026-09-29T07:25:09+00:00", "accessed": "2026-09-29", "id": "contextmemory-markdown-memory-for-your-llama-cpp-vllm-server"}