Self-hosting an AI coding agent workbench: running Codex on my own machines

Description and use

<p>Most AI coding assistants assume you are fine sending your repository somewhere else. For side projects that is a reasonable trade. For anything with a client contract, an internal service, or a repository you cannot move, it is not.</p> <p>The interesting shift of the last year is that the <em>agent</em> part has become a commodity — Codex, OpenCode, Claude Code and friends all expose a CLI you can run yourself. What is still missing for most teams is everything <em>around</em> the agent: where does it run, which filesystem does it see, who reviews the diff, and how do you run the same rou

Problem

<p>Most AI coding assistants assume you are fine sending your repository somewhere else. For side projects that is a reasonable trade. For anything with a client contract, an internal service, or a repository you cannot move, it is not.</p> <p>The interesting shift of the last year is that the <em>agent</em> part has become a commodity — Codex, OpenCode, Claude Code and friends all expose a CLI you can run yourself. What is still missing for most teams is everything <em>around</em> the agent: where does it run, which filesystem does it see, who reviews the diff, and how do you run the same rou

Outcome

<p>Most AI coding assistants assume you are fine sending your repository somewhere else. For side projects that is a reasonable trade. For anything with a client contract, an internal service, or a repository you cannot move, it is not.</p> <p>The interesting shift of the last year is that the <em>agent</em> part has become a commodity — Codex, OpenCode, Claude Code and friends all expose a CLI you can run yourself. What is still missing for most teams is everything <em>around</em> the agent: where does it run, which filesystem does it see, who reviews the diff, and how do you run the same rou

Evidence

Self-hosting an AI coding agent workbench: running Codex on my own machines

Source