Working memory is the agent's scratchpad. Different from raw context (which is just the conversation history), working memory is structured: it has a goal, a todo list, named facts, and survives compaction. On Digitorn working memory is a module, the agent calls remember/recall/forget/todo_add/todo_update like any other tool. Useful for multi-step tasks that need to remember what they decided five turns ago.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.