OpenAI Codex

OpenAI's coding agent CLI (and related app-server path). Tool-using, session-gated.

Choose it when

You want OpenAI’s coding agent in a terminal or ChatGPT, session-gated.

Skip it when

You need a self-hosted gateway or an Anthropic-only stack.

01 / Classification

Autonomy evidence

This is our classification, not a vendor badge. The record says what the product normally does. The gaps stay visible.

How we classify it

Tool use + multi-step plans, still human-gated per session.

Runs unattended

No — the current record treats it as session-gated.

Trigger

Not recorded yet.

State

Not recorded yet.

Tools

CLI · ChatGPT Codex · Editor · Scheduled background tasks (vendor-claimed)

Human control

Not recorded yet.

02 / Operations

Control reality

Useful agents eventually touch something real. This is the operational picture we have, not a promise hidden in a sales page.

Where it runs

cli

Data boundary

Not recorded yet.

Identity & permissions

Not recorded yet.

What it can write

repo files · shell · worktrees

Surfaces

CLI · ChatGPT Codex · Editor · Scheduled background tasks (vendor-claimed)

Export / lock-in

Not recorded yet.

03 / Receipts

Evidence ledger

Here is what this brief is built on. “Documented” means we found a source. “Tested” means this desk actually ran it. Those are different things.

Evidence status

documented

Source set

1 primary source

Evidence review

Not recorded yet.

Sources on file

Corrections

Not recorded yet. If we change a material claim, the correction belongs here.

04 / Change log

Related coverage

The brief tells you what the product is. Payloads track the changes that may alter the decision.