AI News, page 7 of 7
AI and software engineering, as it happens.
oMLX writes the KV cache to SSD, so a coding agent on a Mac stops recomputing the whole context
A local inference server for Apple Silicon that persists KV cache blocks across an in-memory tier and an SSD tier, so a shifting prompt prefix does not force a full recomputation. 21,152 stars, Apache 2.0.
Superagent gives every chat its own git checkout, and lets the agent drive a browser you can watch
A macOS desktop app for Claude Code where every conversation gets a private branch and checkout, the agent drives a visible browser on your own logins, and an iOS Simulator streams into the window.