About sembr

sembr is an open-source news intelligence system that synthesises multi-source signal (RSS / NewsAPI / RSSHub) into a daily, subscribable digest.

What it does

sembr ingests multiple news sources (RSS, NewsAPI, RSSHub and others — RSSHub adapts non-RSS feeds like Twitter/X into RSS), recalls relevant items against the intents you define, and uses an LLM to synthesise a referenced digest. Each digest contains numbered citation links, the source domain, a relevance score, and a link to the original article — so every claim is traceable.

What it does not do

• It doesn't make decisions for you — a digest is signal filtering, not investment advice.
• It doesn't recommend individual stocks — topics are scoped to macro / geopolitics / AI / tech / venture / methodology.
• It doesn't collect user data — this site has no analytics, no cookies, no email forms.

Open source & self-hostable

sembr is published on GitHub under Apache-2.0 ( Peakstone-Labs/sembr ↗ ). You can run your own instance via docker compose and configure your own intents and sources.

About this site

sembr.live is the public showcase for the sembr project. The current phase shows the digest format with mock content; the real daily-digest pipeline lands in a later phase.

Disclaimer

For research reference only. Not investment advice.

Content auto-generated by sembr, curated by humans.