{"slug": "ask-hn-will-we-start-seeing-tools-for-llm-use", "title": "Ask HN: Will we start seeing tools for LLM use?", "summary": "A Hacker News user asks whether the community will develop tools that structure command-line output specifically for LLM consumption, noting that current compression methods save tokens but may increase interaction turns.", "body_md": "| ||||||||||||\n1 point by |\nMany projects and addons exists to reduce the verbosity on standard bash / git /npm etc. Commands that agents pass regularly as tools to LLMs. (eg. rtk, headroom, lean-ctx). Tool output compression does yield good token savings. Though it can lead to increased turns - effectively nullifying the per turn token savings. This is the current topology. Are we going to see a class of products and libraries that structure o/p to what models want to see? | |||||||||||\n|", "url": "https://wpnews.pro/news/ask-hn-will-we-start-seeing-tools-for-llm-use", "canonical_source": "https://news.ycombinator.com/item?id=48606997", "published_at": "2026-06-20 06:58:33+00:00", "updated_at": "2026-06-20 07:38:01.882870+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools", "ai-tools"], "entities": ["bash", "git", "npm", "rtk", "headroom", "lean-ctx"], "alternates": {"html": "https://wpnews.pro/news/ask-hn-will-we-start-seeing-tools-for-llm-use", "markdown": "https://wpnews.pro/news/ask-hn-will-we-start-seeing-tools-for-llm-use.md", "text": "https://wpnews.pro/news/ask-hn-will-we-start-seeing-tools-for-llm-use.txt", "jsonld": "https://wpnews.pro/news/ask-hn-will-we-start-seeing-tools-for-llm-use.jsonld"}}