<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel>
<title>Open models news · Which AI Map</title><link>https://whichaimap.com/open-models.html</link>
<description>What changed in Open models, in plain English.</description>
<item><title>External sandboxes for coding agents</title><link>https://simonwillison.net/2026/Nov/17/external-sandboxes-for-coding-agents/</link><guid>https://simonwillison.net/2026/Nov/17/external-sandboxes-for-coding-agents/</guid><pubDate>Tue, 17 Nov 2026 22:52:29 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Simon Willison</source><description>External sandboxes for coding agents I&#39;ve been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this project with Prime Radiant , the AI research lab behind Superpowers and other projects . My post on th</description></item>
<item><title>Hugging Face and OpenRouter join forces to make open-weight models easy to run</title><link>https://huggingface.co/blog/openrouter</link><guid>https://huggingface.co/blog/openrouter</guid><pubDate>Mon, 16 Nov 2026 00:00:00 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Hugging Face</source><description>Hugging Face partnered with OpenRouter to make hosting and deploying open-weight AI models easier for developers.</description></item>
<item><title>LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B</title><link>https://huggingface.co/blog/ibm-granite/llmon-an-llm-native-markup-language-now-in-granite</link><guid>https://huggingface.co/blog/ibm-granite/llmon-an-llm-native-markup-language-now-in-granite</guid><pubDate>Thu, 12 Nov 2026 19:07:35 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Hugging Face</source><description>IBM released Granite 4.1 3B and 8B models featuring LLMON, an LLM-native markup language for structured generation.</description></item>
<item><title>BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model</title><link>https://huggingface.co/blog/qvac/botpsy</link><guid>https://huggingface.co/blog/qvac/botpsy</guid><pubDate>Wed, 11 Nov 2026 05:01:16 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Hugging Face</source><description>Researchers released BotPsy, a sub-billion-parameter open model optimized to run agentic personal assistants directly on local devices.</description></item>
<item><title>Token Pooling-Aware Training for Multi-Vector Embedding Models</title><link>https://huggingface.co/blog/token-pooling</link><guid>https://huggingface.co/blog/token-pooling</guid><pubDate>Wed, 11 Nov 2026 00:00:00 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Hugging Face</source><description></description></item>
<item><title>Pay for Hugging Face Hub with your Google Cloud Account</title><link>https://huggingface.co/blog/hub-gcp-marketplace</link><guid>https://huggingface.co/blog/hub-gcp-marketplace</guid><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Hugging Face</source><description>Hugging Face now supports paying for Hub subscriptions and services directly through Google Cloud accounts.</description></item>
<item><title>Decision Models in Hugging Face</title><link>https://huggingface.co/blog/decision</link><guid>https://huggingface.co/blog/decision</guid><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate><source url="https://whichaimap.com/open-models.html">Hugging Face</source><description></description></item>
</channel></rss>
