- Who
- Anthropic
- What
- explains the architecture and core primitives for building always-on agents
- Quote
This post breaks down the primitives behind always-on agents and walks through how they fit together.
What happened
Anthropic’s post explains how to build always-on agents from five primitives: an event inbox, timers, memory, permissions, and an outbox. It describes how these components coordinate brief runs across sessions, including resuming work after user input and managing unattended tool calls. The post also compares options such as storing memories in durable databases or object stores and using a scheduler or durable execution engine for timers.
Why it matters
The post organizes always-on agent design around five primitives, giving readers a concrete architecture for handling events, continuity, permissions, and user-facing messages across runs.
Read next
See the full storyAnthropic Outlines Five Primitives for Always-On AgentsThe story so far
Anthropic outlined five primitives for building always-on agents: an event inbox, timers, memory, permissions, and an outbox. Together, they coordinate brief runs across sessions, resume work after user input, and manage tool calls made without a person present. The post describes options for implementing the components, including durable databases or object stores for memory and a scheduler or durable execution engine for timers. Dotey separately explained the same five components through an AI assistant, saying it can remain idle much of the time without calling a model or incurring costs.
