fftext - quick summary, fact check, ELI5 on CPU
Fact-check command extracts claims and cites sources—rare for local AI.

LLM summaries of speeches—but no fact-check, opinion filtering, or integration with analysis tools.
Policy researchers, citizens tracking government communications, journalists seeking raw signal
Claude Opus summarization · Perplexity.ai · HackerNews Show & Tell summaries
It generates short, neutral briefs of public statements: 1–3 key points plus a TL;DR, based only on what is explicitly stated in the source text. Each brief links back to the original source.
There’s no commentary, opinion, or fact-checking—just a faster way to read what was said.
It’s intentionally minimal and still early. I’d love feedback on whether you’d use this, whether the format works, and what one change would make it more useful.
Fact-check command extracts claims and cites sources—rare for local AI.
Fact-check mode extracts claims, web-searches each, and labels them with citations — rare for local LLMs.
One form, four outputs—replaces messy Slack threads with audience-specific incident docs.
Yet another AI speech coach, but focused on ESL professionals instead of general language learning.
Minimal OSINT for normal people — WorldMonitor without the intelligence analyst cruft.
Auto-generates narrative arcs from PR history when Changelog.com exists.