<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hosted on Phil Wheat</title><link>https://philwheat.net/tags/hosted/</link><description>Recent content in Hosted on Phil Wheat</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 13 Oct 2026 08:38:00 -0500</lastBuildDate><atom:link href="https://philwheat.net/tags/hosted/index.xml" rel="self" type="application/rss+xml"/><item><title>Abacus ChatLLM</title><link>https://philwheat.net/links/abacus-chatllm/</link><pubDate>Tue, 13 Oct 2026 08:38:00 -0500</pubDate><guid>https://philwheat.net/links/abacus-chatllm/</guid><description>&lt;p&gt;A hosted agent - I haven&amp;rsquo;t tried it but several people recommended it.&lt;/p&gt;&#10;&lt;p&gt;ChatLLM (from Abacus.AI) is an &amp;ldquo;AI super-assistant&amp;rdquo; subscription: one ~$10/month account for a rotating roster of all the frontier models (the FAQ names GPT-6 variants, Sonnet/Opus, Gemini, Grok, Qwen, DeepSeek, Kimi, GLM plus ~20 more, updated 24–48h after releases), image and video generation, a coding agent CLI, and a general Abacus AI Agent. The differentiators are breadth plus enterprise plumbing: team seats, conversation imports from ChatGPT/Claude, connectors to GDrive/Slack/Confluence, custom chatbots on your data, SOC-2 Type-2 and HIPAA. Hosted only — nothing local — with generous-feeling token limits and automatic model-switching when rate-limited.&lt;/p&gt;</description></item></channel></rss>