OpenAI Codex
OpenAI's agentic coding tool (CLI, IDE, and cloud) that runs agents and connects to MCP servers and skills.
- Sato Score88
OpenAI Codex is a partly open-source agent framework by OpenAI, with last code activity on 2026-10-23 (Active). Latest release on 2026-10-23. Sato Score 88/100 (how open, active and verifiable it is, not a safety grade), as of 2026-10-24. How the score works →
See how to install OpenAI Codex →Last commit Oct 22, 2026 · Last release Oct 23, 2026 (rust-v0.165.0-alpha.1) · ★ 130,453
Listed from openai.com on 2026-06-08. Install: reproduced by Sato Hub on 2026-09-25. Evidence →
Next step
Watch OpenAI Codex
One email if what we observe changes — its repo goes quiet or disappears, or the listing is retired. Nothing else.
Check it from your agent
Add Sato Hub’s MCP server (no key), then ask:
https://satohub.ai/api/mcpRun Sato Hub Preflight on openai/codex before I use it.Your project?
Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.
Claim this listing →Overview
OpenAI Codex is an agentic coding system spanning a CLI, IDE extensions, and a cloud agent. It executes multi-step coding tasks and connects to MCP servers, so onchain agent skills and MCPs (Bankr, CryptoSkills, Base MCP, OpenSea, etc.) can be wired into it. The Codex CLI is open source; the underlying models are proprietary. It is a general-purpose harness rather than an onchain agent.
Sato Score
88/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 16/20
- Interface verifiability
- 8/10
- Docs & demo
- 6/10
- Listing transparency & provenance
- 15/15
- Independent verification
- 8/10
Independently verified — listing reviewed against evidence, never self-reported.
Sato Check
v0.164.0 · as of 2026-10-23- Does it take your key?
- No key read found
- Does your key leave?
- Not yet run · earlier run 2026-10-19: not observed
- Can it move funds on its own?
- Unknown
A profile describes what we read and ran, with dates. It is not a safety rating, an audit or an endorsement, and "not found" is not "not there".
Evidence — listed vs checked · what the words mean
Listed from openai.com on 2026-06-08. Install: reproduced by Sato Hub on 2026-09-25.
| Claim | Value | Evidence | Source | Checked |
|---|---|---|---|---|
| Chains supported | not stated | self-reported | developers.openai.com | as of 2026-10-24 |
| Verification status | Verifiedreview date and evidence link not recorded on this listing | ✓ reviewed | — | not dated |
| Recent activity | last release 2026-10-23 · last commit 2026-10-22 | observed | github.com/openai/codex | 2026-10-24 |
| Install works | reproduced — install and entry both completedshows the install path works as written; not a statement about runtime behaviour | ✓ reproduced | github.com/openai/codex | 2026-09-25 |
| Website answers | answered, but declined our check (HTTP 403) | observed | openai.com | 2026-10-24 |
| Daily check record | 53 of 53 daily checks since 2026-09-01 succeededa success rate of our checks, not uptime; the source is this listing's own history | observed | — | 2026-10-23 |
| Takes your key | no private-key read found in what we read | traced | satohub.ai | 2026-10-23 |
| Key leaves the machine | not yet run with planted test keysthe sandbox lane has not run on this version | observed | satohub.ai | not dated |
| Moves funds on its own | unknown — could not read what it exposes | traced | satohub.ai | 2026-10-23 |
| Built by | OpenAIconfidence 0.95 | self-reported | github.com/openai/codex | as of 2026-06-25 |
| Creator profile | https://github.com/openaiconfidence 0.90 | self-reported | github.com/openai/codex | as of 2026-06-25 |
| Deploys as | Self-hosted, Hosted, npmconfidence 0.85 | self-reported | github.com/openai/codex | as of 2026-06-25 |
| Works with | MCP, VS Code, Cursor, Windsurf, ChatGPTconfidence 0.80 | self-reported | github.com/openai/codex | as of 2026-06-25 |
| Sato Score | 88/100 (High)how open, active and verifiable — not a safety or quality grade | computed | satohub.ai | 2026-10-24 |
Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.
Install — reproduced in a container Sep 25, 2026
Runtime: Node.js
npm install -g @openai/codex # or: brew install codex codex # start the Codex CLI
You supply: An OpenAI account — ChatGPT sign-in or an API key (OPENAI_API_KEY)
Read from the project’s own docs as of 2026-09-25. What a deploy spec is →
Observed record — 91 daily checks since 2026-07-26
- Succeeded
- 54
- Failed
- 37
- Their error
- 0
- Unattributed
- 37
State changed on 2026-09-01 (unclear → responding).
This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 37 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. The rate above leaves those checks out; the counts include them.
Last 30 days — to 2026-10-24, one point per UTC day
A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.
Skills that target this — 2, with disclosures
nature-image2pptskills.sh · yuan1z0825
6,820 installs"Reconstruct slide images, screenshots, scanned PDFs, or image-only PPTX files as object-level editable PowerPoint. Use for 图片转可编辑PPT、截图还原PPT and diagram reconstruction; not authoring a new deck from research notes."
gan-style-harnessskills.sh · affaan-m
4,060 installsGAN（生成的敵対ネットワーク）スタイルの評価ハーネス、画像生成パターン、および品質メトリクス。
Disclosures describe what a skill declares and does; they are not safety verdicts. All skills →
Details
- Chains
- Unknown
- Agent types
- Agent Harness, Coding Agent, Skill Runtime
- Open source
- Partial
- Pricing
- ChatGPT plans / API usage
- Deploys as
- Self-hosted, Hosted, npm
- Works with
- MCP, VS Code, Cursor, Windsurf, ChatGPT
- Last checked
- 2026-10-24
Marketplace Signals
- ▸ Functional agent
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Recent Activity
All news →Releases and posts from OpenAI Codex, pulled from its GitHub and X.
codex 0.165.0-alpha.1
Release 0.165.0-alpha.1
codex 0.164.0
New Features Save reusable prompts and slash commands in ten numbered /presets slots, with a keyboard menu for quick access. ( #54380 , #54381 ) Set model, reasoning effort, speed, and permission profiles directly with inline /model and /permissions arguments. ( #54378 , #54383 ) Preview viewed and generated images in the fullscreen transcript on terminals supporting Kitty or Sixel graphics. ( #54
codex 0.164.0-alpha.12
Release 0.164.0-alpha.12
codex 0.164.0-alpha.11
Release 0.164.0-alpha.11
codex 0.164.0-alpha.10
Release 0.164.0-alpha.10
codex 0.164.0-alpha.8
Release 0.164.0-alpha.8
Listing History
Recorded changes to OpenAI Codex's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Oct 23, 2026New release published
- Oct 22, 2026New release published
- Sep 25, 2026Verified: deploy spec
- Jul 28, 202670 releases trackedShowing the 2 most recent. Full release history is retained in the listing record.
- Jul 27, 2026Sato Hub began tracking this listing
- Jul 14, 2026Enriched: is agent
- Jun 25, 2026Auto-enriched: creator name, creator profile url, deployment options, supported integrations +1 more
Compared with
Appears in
Related Resources
Coinbase AgentKit
ActiveCoinbase's toolkit for giving AI agents wallets and the ability to take onchain actions.
Hyperliquid
ActiveOnchain perpetual futures and spot DEX running on its own L1 with an HyperEVM smart-contract layer.
ElizaOS
ActiveOpen-source TypeScript framework for building crypto-native multi-agent systems.
Reference
QuestionsWhat people ask about this pageShowHide
Questions people ask about OpenAI Codex
- Is OpenAI Codex open source?
- Partly. Some of OpenAI Codex is published as source (https://github.com/openai/codex) and some is not. Checked as of 2026-10-24.
- Which chains does OpenAI Codex support?
- Sato Hub has no confirmed chain list for OpenAI Codex as of 2026-10-24; treat chain support as unknown.
- Is OpenAI Codex still maintained?
- The most recent code activity Sato Hub observed was on 2026-10-23 (last commit 2026-10-22, last release 2026-10-23), which Sato Hub labels "Active". Posts on X are not counted as maintenance. Activity is a recency signal, not a quality judgment.
- How do I install or run OpenAI Codex?
- Node.js. Install: npm install -g @openai/codex && # or: brew install codex. Entry: codex # start the Codex CLI. Sato Hub reproduced this install in a container on 2026-09-25.
- Is OpenAI Codex verified on Sato Hub?
- Sato Hub holds one earned check for OpenAI Codex: Independently verified — listing reviewed against evidence, never self-reported. Its Sato Score is 88 of 100, a measure of how open, active and verifiable the project is, not a safety, quality or returns grade.
Cite this pagePlain text, APA or BibTeXShowHide
Cite this page
Sato Hub. "OpenAI Codex — Sato Hub." Sato Hub, updated 2026-10-24, accessed 2026-10-24. https://satohub.ai/resources/openai-codexData last refreshed 2026-10-24; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.
Join the Sato Hub Briefing
Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.