# Agents are Systems Software

DevFeed: [Agents are Systems Software](<https://devfeed.tech/articles/agents-are-systems-software-33478.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2025/10/24/systems-software>)

Published: 2025-10-24T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [systems](<https://devfeed.tech/topics/systems.md>), [Software](<https://devfeed.tech/topics/software.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [database](<https://devfeed.tech/tags/database.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [software](<https://devfeed.tech/tags/software.md>), [systems](<https://devfeed.tech/tags/systems.md>)

## AI overview

This opinion argues that well-built AI agents should be treated as systems software: generic, extensible, reusable, and difficult to implement well. It compares agents with web browsers and database engines, and argues that companies should generally use established deep-agent implementations instead of owning that infrastructure. It also discusses the difficulty of building secure, high-performing MCP clients.

## Source excerpt

Agents are hard to build. And when they're done well, they're highly generic and extendable. They're systems, like web browsers or database engines.