Jev in production › Moderation and content filtering

Sharp

Chrome and Firefox extension that scores each X post against user-written filter rules with a decision model by default (Jev via TypeSafe, OpenRouter or Vercel AI Gateway) and hides posts or holds close calls behind a banner before display.

Open on GitHub ↗

The source publishes no measured number.
Use
Moderation and content filtering
Industry
Media and social
Form
Open-source tool
Stage
In production
Plugs into
Chrome, Firefox
Listed
2026-09-21
Found via
github
Repository
tshmieldev/sharp
Stars
30
Forks
0
Last push
2026-09-23
Language
TypeScript
License
MIT
Sharp screenshot
store/promo.gif in the tshmieldev/sharp README, MIT; shown from GitHub.

The README opens with

Filter your X timeline with an AI model you choose and pay for directly. Describe what you want to see — or never see again — in plain language.

- Filters in your own words. "Hide engagement bait and crypto threads", or "only keep software engineering". Whatever you'd tell a person. - Per-author rules. Never filter someone, or always hide them, straight from a post's ⋯ menu. - Blocked words, matched before the model is asked. - Teach it. Mark a hidden post as a wrong call, or pick "Hide posts like this" from the ⋯ menu; your recent corrections go to the model as examples. - Teach X too. Optionally, Sharp tells X you're not interested in what it hides, so the algorithm learns alongside the model. This is the one feature that acts as you on X; the...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for moderation and content filtering