Show HN: Ego lite – why our browser agent writes JavaScript not CLI commands

Nicole9 11 points 8 comments May 30, 2026
github.com · View on Hacker News

Discussion Highlights (4 comments)

braxton4

smart move, when I was using agent browser,I have to watch it execute commands one by one, it’s really inefficient. using JS code to execute all commands at once is smart.

imJack

This might be a niche use case, but I love using browser agents for web games. A browser that can run multiple agent-controlled sessions at the same time basically turns multiboxing from a chore into a one-click experience. My productivity may not improve, but my game progression definitely will.

haruharuha

Just tried it out, the Space concept is exactly what I’ve wanted all along,which so straightforward: agent gets its own independent space but still holds my credentials. Browsers like Dia, which evolved from Arc (working on the workspace concept very early on), should have taken this route ages ago. What a missed opportunity that they didn't integrate it this way.

haruharuha

I’ve been wanting to use browser automation to track private twitter accounts that I already follow, since the API obviously won't cut it. My main concern with this browser's automation features is account safety—how well does it mask itself? I'm worried it might trigger the platform's anti-bot detection and get my account flagged or banned :(

Semantic search powered by Rivestack pgvector
8,961 stories · 84,430 chunks indexed