DEMO / RECORDING
Overview & result
Turn saved LinkedIn posts into a searchable board. Jev chooses a category for each post; Python reads the visible cards and exports the board, CSV and JSON. Search and filters run in the board.
From the original post
Jev + LinkedIn bookmarks = your saved posts are finally searchable ✅
479 posts classified in 225 seconds for $0.0195 🤯
LinkedIn has no native way to search what you saved Jev reads every post and tags the topic, hook, and format you can finally find that post you saved 6 months ago
So: save, classify, search. Never lose a good post again.
Free and open source. try it below ↓
How Jev fits in the loop
- Browser code reads visible saved-post cards from the user’s Chrome session.
- One Jev Choice question selects a category from the user’s definitions.
- The board searches and filters the saved text; CSV and JSON preserve the results.
How to reproduce
- Clone the author’s repository and run uv run jev-linkedin-saved --demo for its sample dashboard.
- For your own saves, follow the README’s Chrome and API-key setup, then run uv run jev-linkedin-saved.
Why this build matters
Provides a practical route from a bookmark collection to material you can find again.
Limitations
- Not independently run or benchmarked by JevForAgents.
- Only visible card text is read; collapsed text can be missed. Classification sends extracted text to the selected API provider.
- The inspected code classifies categories; separate hook and format tagging is not established.
- The post reports 225 seconds; the video board shows 730.4 seconds. These timings are not treated as equivalent.