AIHOT is a self-hosted engine for running your own AI news site: it watches the sources you choose, scores every story twice, and publishes only the coverage worth reading. Point it at RSS feeds, web list pages, JSON APIs, X accounts, WeChat public accounts, or content pushed in by scripts, polled on schedules you control. After deduplication and pre-screening, every story faces two independent scoring passes under the same rubric, so one generous run cannot wave a weak story through. Coverage of the same story clusters into one event across the last two weeks, so forty outlets on one launch read as a single developing story. Hotness is measured per event: each source counts once per 48 hours and its weight halves daily, so repeat posting cannot inflate the ranking. Digests compile on schedule: a daily edition at 08:00, a weekly review on Mondays, and a monthly rollup on the first, assembled by rules without model calls. Readers browse topic pages by company, research direction, and content form, search titles, summaries, and full text, and keep local favorites with export and import. From the admin backend you can test sources, correct scores by hand, calibrate selection against labeled samples, and swap the model behind each pipeline step. Output flows through RSS, a public API, MCP, agent Markdown, and llms.txt, so humans and AI agents can subscribe. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Follow every blog, newsletter, and news site you like from one distraction-free inbox with the self-hosted Fusion RSS reader, which has no AI features by design. A left sidebar lists feed groups with unread counts and jumps between Unread, Starred, and All, while the center list shows articles under filter tabs with read and star buttons on every card. Click a card and a right-hand drawer opens with the full sanitized article, a link to the original, and Previous and Next buttons. Press Cmd or Ctrl+K, or the slash key, to search feeds and articles from anywhere. Stay on the keyboard with Google Reader-style keys such as j and k to move, m to mark read, s to star, and g then u to jump to Unread; the question mark lists them all. Add a feed by entering a site address and letting auto-discovery find it, then pick its group, refresh frequency, and HTTP proxy, or suspend it to pause updates. OPML import and export bring subscriptions in or out. Starred articles are saved as snapshots that outlive their source feed. Fever API compatibility lets Reeder, Unread, and FeedMe read the same library. Sign in with a password or OIDC single sign-on, and install the interface as a PWA with Light, Dark, and System themes in eight languages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.