ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

LLM 0.32 adds visible reasoning traces, server-side tools, and content-addressable SQLite logs. It supports GPT-5.6 models, with GPT-5.6 Luna as the new default. The release introduces model.prompt(messages=[]) and stream_events(). New llm-chat-completions-server plugin enables an OpenAI-compatible API endpoint.
Tap to vote and see what everyone thinks.
Summary by ByteBrief