# Long-running Agents

DevFeed: [Long-running Agents](<https://devfeed.tech/articles/long-running-agents-18054.md>)

Original publisher: [Read original article](<https://addyo.substack.com/p/long-running-agents>)

Author: Addy Osmani

Published: 2026-04-30T14:30:29Z

Content type: opinion

Language: en

Sources: [Elevate](<https://devfeed.tech/sources/elevate.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Persistence](<https://devfeed.tech/topics/persistence.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Frontier Model](<https://devfeed.tech/topics/frontier-model.md>), [Process](<https://devfeed.tech/topics/process.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [frontier-model](<https://devfeed.tech/tags/frontier-model.md>), [persistence](<https://devfeed.tech/tags/persistence.md>), [process](<https://devfeed.tech/tags/process.md>)

## AI overview

This article explains long-running AI agents: systems that continue making progress across multiple sessions, context windows, and sandboxes while preserving state, recovering from failures, and leaving artifacts for later sessions. It distinguishes long-horizon reasoning from long-running execution and discusses the engineering challenges involved.

## Source excerpt

A long-running AI agent can keep making progress over hours, days, or weeks.