The recorded integration surface covers 5 named target(s) and 6 extensibility path(s); treat those lists as the practical ceiling of this snapshot. Its verification stage rests on 1 retained run(s) using Hands-on setup or capability check retained by RepoRadar verification harness, not on score alone. RepoRadar keeps permanent head-to-head records for it: Cursor vs OpenAI Codex vs Claude Code (against Cursor, Claude Code); Replit vs Cursor vs OpenAI Codex (against Replit, Cursor); GitHub Copilot CLI vs OpenAI Codex vs Claude Code (against GitHub Copilot, Claude Code). This decision log retains 1 dated change event(s) (1 new entity); the most recent was new entity on 2026-07-14.
Codex is included across eligible ChatGPT plans with plan-dependent limits; flexible usage is credit- and token-based, so there is no single standalone monthly price.
Checked 2026-07-12 · Source is stale; recheck before purchase.
Privacy and code-data boundary
Code and task context are processed according to the selected ChatGPT, Business, Enterprise, API, or cloud-task terms; organizational controls should be reviewed before sensitive repository use.
Training/data-use check: Treatment varies by product and plan; verify workspace data controls and current terms.
Verification record
Installed and tested · Hands-on setup or capability check retained by RepoRadar verification harness · last checked 2026-07-13T03:19:54.905224Z
Hands-on runs
partial · cohort-20260712-codex-installed-help
Tester
RepoRadar automated local verification harness
Started
2026-07-13T03:19:54.809478Z
Completed
2026-07-13T03:19:54.905224Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
0 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
Executed bounded check: Load the installed Codex CLI command surface.
Captured the complete sanitized stdout, stderr, exit status, and 0.10-second wall time.
Observed results
Command exited 0 after 0.10 seconds.
The command produced a successful local process exit; complete output is retained.
Observed strengths
The installed Codex CLI help exposed interactive prompting, non-interactive exec and review commands, and explicit login and logout controls.
Friction
No blocking friction was observed during this bounded local check.
Limitations
Help output proves local CLI startup only; it does not exercise an authenticated coding task.
This bounded cohort check is not a production benchmark or a claim of real user-workflow adoption.
Pricing assessment: No paid plan or metered provider usage was exercised; package or licensing, hosting, and provider costs remain workflow-dependent.
Privacy assessment: No repository content, user data, or provider prompt was transmitted; broader product data handling was not assessed by this bounded run.
This record renders 3 retained source link(s) across 2 source host(s). A checked date is shown only when the record contains one; multiple vendor documents are not presented as independent corroboration.
28 dated snapshots retained from 2026-07-14 through 2026-08-28; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.
RepoRadar scoreTrend begins after a second recorded point.
Momentum signalTrend begins after a second recorded point.
Integrations baselineGitHub, VS Code, Cursor, Windsurf, Slack
Recent dated points
Date
Score
Momentum
Stars
Risk
Verdict
Maintenance
2026-08-28
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-26
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-21
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-20
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-19
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-18
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-17
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-15
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-14
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-13
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-12
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
2026-08-11
Not recorded
Not recorded
Not recorded
plan-dependent
evaluate
official product reviewed
Why the record changed
new entity
Newly added to RepoRadar's decision catalog.
Record facts
Vendor
OpenAI
Category
coding agent
Maintenance status
official product reviewed
First tracked
2026-07-12
Record updated
2026-08-28
Verification stage
installed and tested
Local-model compatibility
not marked compatible
Every value above is rendered from a field in the retained commercial record; RepoRadar supplies the labels and formatting. Review the linked evidence before relying on a missing or ambiguous field.
Frequently asked questions
Can OpenAI Codex run against locally hosted models?
The retained record does not mark it as compatible with locally hosted models. That absence is not proof of incompatibility; confirm current support with the vendor.
Who publishes OpenAI Codex?
OpenAI Codex is published by OpenAI. RepoRadar tracks it as a commercial record and links the supporting record sources that are available.
Where can OpenAI Codex be deployed?
Retained deployment models for OpenAI Codex: local_cli, IDE_extension, desktop_app, vendor_cloud. Governance-sensitive teams should confirm data-residency behavior on the linked privacy source.