Keystone – building self-configuring agents

Show HN: Control your X/Twitter feed using a small on-device LLM

Operating in show hn launch, Keystone – building self-configuring agents operates.

Profile

We built a Chrome extension and iOS app that filters Twitter's feed using Qwen3.5-4B for contextual matching. You describe what you don't want in plain language—it removes posts that match semantically, not by keyword.What surprised us was that because Twitter's ranking algorithm adapts based on what you engage with, consistent filtering starts reshaping the recommendations over time. You're implicitly signaling preferences to the algorithm. For some of us it "healed" our feed.Currently running inference from our own servers with an experimental on-device option, and we're working on fully on-device execution to remove that dependency. Latency is acceptable on most hardware but not great on

Keystone – building self-configuring agents is positioned in show hn launch, a segment that rewards a clear, focused offering.

It is recorded at the Show HN launch stage.

Website: imbue.com/product/bouncer