RepoRadar
Leave a Tip
Item detail
github.com

openai/codex

RepoRadar surfaced openai/codex — a developer tool — into the Coding Agents section, where it sits at Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Open on GitHub →Back to radar
Score9.4
Popularity94.0
Risknone
TierGold
Score breakdown
Usefulness9.0
Novelty7.0
Momentum8.0
Maturity9.2
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for solo developers and teams that want a local terminal coding assistant with a narrow execution scope, explicit approvals, and straightforward model routing before turning on heavier agent frameworks.

Who should use it

developers who want a terminal-native coding agent teams that need command-line productivity with visible diffs before commit small teams onboarding a practical first-agent workflow before adding full MCP infra

Who should skip it

Move on from openai/codex if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

openai/codex is tracked by RepoRadar as a developer tool in the Coding Agents section. It was first seen on 2026-06-17 and last updated on 2026-06-17. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for openai/codex are workflow potential (10.0) and maturity (9.2), while novelty (7.0) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned openai/codex a composite score of 9.4 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 94.0 and never affects the composite score or tier. The risk label of 'none' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

Runs local shell-backed workflows when commands are approved — teams should set strict command policies in sensitive repositories.

Evidence links
Closest alternatives / related signals
coding-agent terminal cli code-editing approval-gates openai
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T05:17:02.644918Z.

partial · cohort-20260712-codex-installed-version

Tester
RepoRadar automated local verification harness
Started
2026-07-13T03:19:54.687941Z
Completed
2026-07-13T03:19:54.794377Z
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: Read the installed Codex CLI version.
  • Captured the complete sanitized stdout, stderr, exit status, and 0.11-second wall time.
Observed results
  • Command exited 0 after 0.11 seconds.
  • The command produced a successful local process exit; complete output is retained.
Observed strengths
  • The installed Codex CLI launched locally in 0.11 seconds and reported codex-cli 0.144.1 in the credential-stripped check.
Friction
  • No blocking friction was observed during this bounded local check.
Limitations
  • No repository edit, authentication, sandbox execution, or model call was attempted.
  • 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.

Open retained test log →

partial · cohort-20260712-codex-isolated-npm

Tester
RepoRadar automated local verification harness
Started
2026-07-13T03:19:55.407151Z
Completed
2026-07-13T03:20:02.096356Z
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: Resolve and launch the current Codex npm package in an isolated cache.
  • Captured the complete sanitized stdout, stderr, exit status, and 6.69-second wall time.
Observed results
  • Command exited 0 after 6.69 seconds.
  • The command produced a successful local process exit; complete output is retained.
Observed strengths
  • The pinned @openai/[email protected] package resolved in an isolated npm cache, launched, and reported codex-cli 0.144.1.
Friction
  • No blocking friction was observed during this bounded local check.
Limitations
  • Version startup does not exercise authentication, repository access, or a model-backed workflow.
  • 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.

Open retained test log →

failed · cohort-20260714-codex-local-responses-read-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:09:27.916404Z
Completed
2026-07-14T05:10:33.964474Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
2 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.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official @openai/[email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in shell_command tool, then asserted exactly two streamed /v1/responses requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run Codex's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 66.05-second wall time.
Observed results
  • Check exited 1 after 66.05 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 14 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates Codex's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

passed · cohort-20260714-codex-local-responses-read-workflow-v2

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:16:53.229770Z
Completed
2026-07-14T05:17:02.644918Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded representative workflow
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.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official @openai/[email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in shell_command tool, then asserted exactly two streamed /v1/responses requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run Codex's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 9.42-second wall time.
Observed results
  • Command exited 0 after 9.42 seconds.
  • Codex exposed and executed its built-in shell_command tool once, returned the synthetic marker to the loopback model, completed the second turn, and left the fixture byte-identical.
  • Expected marker 'CHECK_OK cli=codex requests=2 tool=shell_command unchanged=true' was observed in retained output.
  • Validated result.json: 9 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
  • Validated transcript.json: 3 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The official CLI completed a full provider-to-tool-to-provider agent turn with an allowlisted built-in read tool and machine-readable output, without an account or hosted model.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 5 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates Codex's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

38 dated snapshots retained from 2026-06-17 through 2026-08-03; 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 score9.4 current · +0.0 net
Repository momentum10.0 current · +2.0 net
GitHub stars (observed)103,513 current · +5,670 net
GitHub stars103,513 exact observation
Versionrust-v0.147.0-alpha.4
Last release2026-07-31T17:54:49Z
Maintenanceactive
Current risknone
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-039.410.0103,513nonetry nowactive
2026-08-029.410.0103,250nonetry nowactive
2026-08-019.49.0103,013nonetry nowactive
2026-07-319.48.0Not recordednonetry nownot recorded
2026-07-309.48.0Not recordednonetry nownot recorded
2026-07-299.410.0102,312nonetry nowactive
2026-07-289.49.0102,037nonetry nowactive
2026-07-219.49.099,050nonetry nowactive
2026-07-209.49.099,050nonetry nowactive
2026-07-199.49.099,050nonetry nowactive
2026-07-189.49.099,050nonetry nowactive
2026-07-179.49.099,050nonetry nowactive

Why the record changed

stars changed

Stars changed: 103250 → 103513.

stars changed

Stars changed: 103013 → 103250.

stars changed

Source-observed stars changed: 102929 → 103013. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 102926 → 102929. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 102924 → 102926. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 102037 → 102312.

version changed

Version changed: rust-v0.146.0-alpha.14 → rust-v0.147.0-alpha.1.

stars changed

Source-observed stars changed: 101979 → 102037. This reports the retained observation delta and does not infer why the upstream change occurred.

version changed

Version changed: rust-v0.145.0-alpha.20 → rust-v0.146.0-alpha.14.

stars changed

Stars changed: 99050 → 101979.

stars changed

Source-observed stars changed: 99038 → 99050. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 99036 → 99038. This reports the retained observation delta and does not infer why the upstream change occurred.