Digitorn
Digitorn
All terms
Agent concepts

Working memory

Per-session state the agent can write and read across turns, including a goal, a todo list, and arbitrary key-value notes.

also known as: short-term memory, session memory
In depth

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.

Related concepts
Newsletter

Get the next post in your inbox.

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.

One-click unsubscribe. We never share your address. Powered by our own infrastructure, not a tracker.

More in Agent concepts

Agent loop/glossary/agent-loopAgent spawn/glossary/agent-spawnAI agent/glossary/ai-agentCompaction/glossary/compactionCoordinator agent/glossary/coordinatorFunction calling/glossary/function-calling