Cursor puts the agent in your editor. Codex puts it where the work arrives.
Cursor and Codex put the same agent loop in different places. Cursor keeps it in a VS Code-based editor, next to Tab completion and inline edit. Codex spreads one agent across the CLI, IDE extension, desktop app and cloud tasks, with Slack and Linear hand-offs. Choose by where your work starts: in the editor, or in GitHub, Slack and Linear. AI Developer Toolkit teaches all three tools side by side: 400+ guides and 100+ recipes, each showing when it was last updated.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
- Compare data, updated
- 2026-10-12
- Cursor docs
- 2026-08-28
- Codex 0.157.1
- 2026-09-26
- List prices captured
- 2026-09-26
Which one fits how you work?
Tick the lines that are true for you. Each one is a verdict line from the toolkit’s compare data, checked 2026‑10‑12.
Pick Cursor if
Editor-first: you steer each change as it lands
Pick Codex if
Multi-surface: one agent across CLI, IDE, desktop and cloud
Station by station.
The jobs a coding-agent workflow has to do, with what each tool names for them. The note beside each station says whether the difference should change your choice.
Intent
Project instructions, skills, plan mode
Same shape Both have project instructions, skills and plan mode: Rules, Agent Skills and Plan Mode in Cursor (its agent runtime also loads AGENTS.md); AGENTS.md, /skills and /plan in Codex.
Cursor
- Rules
- Cursor's docs:
AGENTS.mdin the project root and in subdirectories (nested files combine, the more specific one wins), andCLAUDE.mdread the same way and always applied;.cursorrulesis legacy Cursor token management guide, 2026-10-12 - The agent runtime in
@cursor/sdk1.0.32 loads a root and nestedAGENTS.mdunconditionally, andCLAUDE.mdonly with third-party config loading on, while Cursor's docs sayCLAUDE.mdis always applied Cursor token management guide, Cursor SDK 1.0.32, 2026-09-26 - Agent Skills
- Plan Mode
Cursor docs, 2026-08-28
Codex
-
AGENTS.md(/initcreates one) - Skills:
/skills,.agents/skills/ - Plan:
/plan
Codex 0.157.1, 2026-09-26
Harness
Permissions and approvals, sandbox, MCP, hooks, organisation policy
Differs Both have hooks, MCP, a sandbox and an organisation policy layer. Codex documents 12 hook events that need persisted trust, plus an approval policy and a reviewer model; Cursor's hooks can block, and its run modes are Auto-review, Allowlist and Run Everything (Cursor docs, checked 2026-10-12).
Cursor
- Run modes: Auto-review (the recommended default), Allowlist and Run Everything Cursor docs, Cursor 3.24, 2026-10-12
- Auto-review runs shell commands in a sandbox when possible;
sandbox.jsonconfigures it Cursor docs, Cursor 3.24, 2026-10-12 - Hooks: JSON over stdio, before or after agent-loop stages; can block
- MCP
- Organisation policy: Team and MDM settings layers (SDK 1.0.32)
- File deny rules: the agent runtime refuses reads of paths in
.cursorignore, passes the list to the shell sandbox and blocks the agent from editing the file Cursor privacy and security guide, Cursor SDK 1.0.32, 2026-09-22 - Starting mode: Auto-review, the recommended default since 3.6 (2026-05-29) Cursor docs, Cursor 3.24, 2026-10-12
Cursor docs, 2026-08-28
Codex
- Approval policy (
-a on-requestor-a never) plus automatic review (--approve-for-me); starts inon-request - OS sandbox:
--sandbox read-only,workspace-write,danger-full-access; permission profiles (beta) - Hooks: 12 events; need persisted trust before they run
- MCP client:
codex mcp add,config.toml; does not run as an MCP server (removed in 0.154.0) - File access: a permission profile with a
denyfilesystem rule (beta);--sandboxalone restricts writes, not reads - Organisation policy:
requirements.toml(allow_managed_hooks_only,permission_profile,mcp_servers)
Codex 0.157.1, 2026-09-26
Loop
Stop conditions, /goal, /loop, scheduled runs, headless
Differs Both have /goal: stable in Codex, marked "Rolling out" in Cursor (Cursor docs, checked 2026-10-12). Cursor has a /loop skill; Codex has no /loop in 0.162.1 (checked 2026-10-12). Both run headless (print mode, codex exec) and on a schedule, but Cursor Automations start Cloud Agents while Codex automations run locally in the desktop app.
Cursor
-
/goal, marked "Rolling out" Cursor docs, Cursor 3.24, 2026-10-12 -
/loopbundled skill since 3.5 - Scheduled runs: Automations, which start Cloud Agents
- Headless: print mode (
agent -p) Cursor docs, Cursor 3.24, 2026-10-12 - Machine-readable output:
--output-format textis documented Cursor docs, Cursor 3.24, 2026-10-12 - Other output formats: not verified for this page (checked 2026-10-12) Cursor docs, Cursor 3.24, 2026-10-12
Cursor docs, 2026-08-28
Codex
-
/goal(featuregoals, stable) - No
/loopin Codex 0.162.1 (slash-command enum, binary strings) or the developer-commands reference (checked 2026-10-12); use/goalor CI Loop command guide, Codex 0.162.1, 2026-10-12 - Scheduled runs: automations run locally in the desktop app, which must be open and the machine awake Background and cloud agents guide, 2026-09-26
- Headless:
codex exec(aliase);--json(JSONL events);--output-schema FILE;-o FILE
Codex 0.157.1, 2026-09-26
Graph
Subagents, worktrees, background sessions
Differs Both have subagents, worktrees and cloud runs, but the loop lives in different places. Cursor keeps the agent in the editor, and its Cloud Agents run in isolated VMs; Codex spreads one agent across the CLI, IDE extension, desktop app and cloud tasks (codex cloud, experimental), with the codex agents command center.
Cursor
- Subagents, including on their own cloud VMs
- Worktrees
- Background sessions: Cloud Agents in isolated VMs
Cursor docs, 2026-08-28
Codex
- Subagents:
/subagents; multi-agent on by default - Worktrees:
--worktreeflag or/worktree - Background sessions: the
codex agentscommand center - Cloud: Codex cloud (
codex cloud, experimental)
Codex 0.157.1, 2026-09-26
Verification
Diff review, review agents, security review, checkpoints and rewind
Same shape Both review in the session: /review in Codex, Agent Review and /review in Cursor, which also runs /review-bugbot. Codex reviews from the shell too (codex review), and both have a security review (@codex security review, /review-security and Security Agents). One caveat: Cursor lists /rewind in its CLI, while Codex's Esc Esc does not restore files (0.157.1).
Cursor
- In the session: Agent Review (
/agent-review) and/review, which runs/review-bugbotCursor code review guide, 2026-09-15 - Bugbot on the pull request
- Security review:
/review-securitybefore the push; Security Agents on the pull request Cursor code review guide, 2026-09-15 - Rewind: checkpoints, stored locally and separate from Git; restoring one reverts files only Cursor docs, Cursor 3.24, 2026-10-12
Cursor docs, 2026-08-28
Codex
- In the session:
/review - From the shell or CI:
codex review,codex exec review - Security review:
@codex security review - Rewind: Esc Esc backtracks the conversation to an earlier message; it does not restore files (0.157.1). Use Git for file state
Codex 0.157.1, 2026-09-26
Release
CI and GitHub Actions, repo-event triggers, pull-request routing
Differs Both take work from Slack and Linear and have a GitHub Actions step. Codex reviews on a mention (@codex review); Cursor adds Bugbot, Security Agents and PR Routing & Approval, which can approve low-risk PRs.
Cursor
- GitHub Actions: Cursor CLI in GitHub Actions (documented)
- Review on the pull request: Bugbot
- Hand-offs: Automations triggered from Slack, Linear, GitHub, GitLab, webhooks, Sentry and PagerDuty
- Reviewer routing and approval: PR Routing & Approval (can approve low-risk PRs)
- Start a cloud run from code: Cloud Agents API and webhooks
Cursor docs, 2026-08-28
Codex
- GitHub Actions:
openai/codex-action@v1 - Review on the pull request:
@codex reviewon GitHub and GitLab, on a mention and without a separate workflow file - Hand-offs: Slack (
@ChatGPT, with Cloud delegation to a Codex Cloud task) and Linear (@Codex) Codex docs, 2026-10-12 - Reviewer routing and approval: through your own CI and CODEOWNERS
- Start a cloud run from code:
codex cloud(experimental)
Codex 0.157.1, 2026-09-26
Editor
Tab completions, inline edit, extensions and keybindings
Differs Cursor is the editor, with Tab completion and inline edit. Codex has an IDE extension for VS Code, Cursor and Windsurf; the docs call it an agent, not a completion engine, and Tab completion and inline edit are not found for it in the docs (checked 2026-09-26).
Cursor
- The Cursor editor itself, with Tab completion and inline edit
- Inline edit is usually bound to
Cmd+K(macOS) orCtrl+K(Windows, Linux); shortcuts move between builds Inline edit guide, 2026-09-26 - Shortcuts are VS Code keybindings attached to Cursor's AI commands; pin them in
keybindings.jsonCursor shortcuts reference, 2026-09-26 - VS Code extensions IDE migration guide, 2026-09-26
Cursor docs, 2026-08-28
Codex
- IDE extension for VS Code, Cursor and Windsurf (per the OpenAI README)
- Tab completions and inline edit: not found in the docs (checked 2026-09-26). The migration guide calls Codex an agent, not a completion engine, and keeps your editor's completion beside it IDE migration guide, 2026-09-26
Codex 0.157.1, 2026-09-26
Read a gap as a gap in what we read. A line that says “not found in the docs” means we could not source it on that date. A Cursor cell with no later stamp comes from docs read before cursor.com could not be reached on 2026‑09‑26. Re-check a Cursor cell before you automate against it.
- Drawing
- Cursor vs Codex
- Source
- The compare data, 2026‑10‑12. Each cell above names the page and the day it was read.
Models and what they cost.
Codex is included in ChatGPT Plus ($20/month), Pro ($100, $200 or $500) and Business ($20 per user per month billed annually), and in Edu and Enterprise (OpenAI, read 2026-10-12); the 5x and 20x Plus-usage ratios of Pro at $100 and $200 come from a secondary source (TechCrunch, 2026-04-09). Cursor Pro is $20/month, Pro+ $60 and Ultra $200 (cursor.com/pricing, read 2026-10-12); Cursor's included-usage amounts per plan are not verified here.
| US list prices, 2026‑09‑26 | Cursor | Codex |
|---|---|---|
| Models | Several vendors in one picker. No single default model: Hobby uses Auto. Cursor's own pool is Grok 4.7 (which Cursor calls its flagship model), Grok 4.6, Grok 4.5 and Composer 2.5; Claude Opus 5.5, Fable 5.1, Sonnet 5.5 and Haiku 5.5 are third-party models billed at API rates; no GPT-6 model is listed (Cursor, checked 2026-10-12) | Default GPT-6.1 Sol (since CLI 0.159.1, 2026-09-29, at low effort); GPT-6 Astra chosen by hand for the hardest work; GPT-6 Sol and GPT-6 Luna in the picker; GPT-5.6 Sol, Terra and Luna still selectable. Switch with /model |
| Context window | Set by the model: Grok 4.7 has a 256K standard window and 500K long context, and Claude Sonnet 5.5 up to 1M (Cursor model pages, checked 2026-10-12) | 272K by default in Codex, up to 872K (GPT-6.1 Sol, GPT-6 Astra, Sol and Luna) |
| Entry plan | $20/month Cursor ProUnlimited Tab completions, extended Agent usage limits on all models, Bugbot and Cloud Agents (cursor.com/pricing, read 2026-10-12) | $20/month ChatGPT PlusCodex included (OpenAI pricing page, read 2026-10-12) |
| Middle plan | $60/month Cursor Pro+The same individual-plan features as Pro; Cursor recommends Pro+ for daily Agent users (cursor.com/pricing, read 2026-10-12) | $100/month ChatGPT Pro (5x Plus)Codex; 5x Plus usage on Codex (secondary source: TechCrunch, 2026-04-09). Price: OpenAI, read 2026-10-12 |
| Top individual plan | $200/month Cursor UltraThe same individual-plan features as Pro; Cursor recommends Ultra for Agent power users (cursor.com/pricing, read 2026-10-12) | $200/month ChatGPT Pro (20x Plus)Codex; 20x Plus usage on Codex (secondary source: TechCrunch, 2026-04-09). Price: OpenAI, read 2026-10-12. OpenAI also lists a $500 Pro tier |
| Team seat | Teams Standard $40/user/month ($32 billed annually); Teams Premium $120/user/month ($96 billed annually), "5x the usage of a Standard seat"; Enterprise custom (cursor.com/pricing, read 2026-10-12) | ChatGPT Business $20/user/month billed annually ($25 billed monthly, 2+ users), with Codex included; Edu and Enterprise include Codex, price on contact (OpenAI, read 2026-10-12) |
Use both, if each one earns its seat
Pick by where the task starts and how much supervision it needs, not by which model is "smarter".
Hold both to one gate: tests, type check and lint on every pull request, whichever agent opened it, with one review bot per repository.
Add Codex only if work arrives in GitHub, Slack or Linear and your company already has ChatGPT plans that include it. Otherwise the extra surfaces cost more governance than they save.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
In the editor
A small edit in the file you have open
Tab and inline edit keep you in the file; there is nothing to delegate.
On screen
A UI change you judge by looking at it
You accept or reject each change as the dev server reloads.
From chat
A bug reported in a Slack thread or a Linear issue
@ChatGPT in Slack (with Cloud delegation) or @Codex in Linear starts a Codex cloud task from the thread; nobody changes tools.
On the pull request
Review of every pull request
@codex review with automatic reviews; run one bot per repository, not both.
AGENTS.md as the single source for instructions, with Cursor Rules pointing at it; MCP servers and skills installed with npx skills add <owner/repo>; and one gate: AGENTS.md rules, CI checks, one review bot per repository and one evidence format. requirements.toml for Codex, the Team and MDM settings layers for Cursor. “Using several of them can feel messy. I switch between Claude Code, Cursor, VS Code, GitHub, and other agents, and often have to explain the same project or problem again.” Questions before you choose.
Something else? Write to support@developertoolkit.ai.
Does Codex have Tab completions?
Not that the docs we read describe (checked 2026-09-26). They call Codex an agent, not a completion engine; its IDE extension (VS Code, Cursor and Windsurf, per OpenAI's README) puts the agent beside the file you are editing. Tab completion and inline edit are documented for Cursor (Cursor docs, 2026-08-28).
Which costs less for a small team?
ChatGPT Business is $20 per user per month billed annually ($25 monthly, 2+ users) with Codex included, while Cursor Teams Standard is $40 ($32 billed annually) and Teams Premium $120 ($96 billed annually) (OpenAI and cursor.com/pricing, read 2026-10-12). The seat is only the allowance: both meter agent work beyond it, and Cursor's included-usage amounts per plan are not verified here, so price a team from your own invoices.
Can I use both?
Yes, if each earns its seat. Cursor covers the editing surface; Codex covers the places work arrives from. Keep AGENTS.md as the single source for instructions, point Cursor Rules at it, and install skills in both with npx skills add <owner/repo>.
Which gives more model choice?
The docs do not rank them. Cursor offers several vendors in one picker and names no single default model: its own pool is Grok 4.7, Grok 4.6, Grok 4.5 and Composer 2.5, it lists Claude models, and no GPT-6 model is in its list (Cursor, checked 2026-10-12). Codex runs GPT-6.1 Sol by default, with GPT-6 Astra, Sol and Luna in the picker, and also reaches Amazon Bedrock and local models through --oss.
Other comparisons.
Each one gives a verdict first, then goes station by station.
Does this page answer your questions?
One tap, no sign-in.
What are you here for?
What is holding you back?
How does it read?
Thanks. If you left an email, Michał will reply.
Answering your questions?
One tap each. Close whenever you like.
no sign-in
Pick one. Learn the workflow once.
The guides cover Cursor, Claude Code and Codex side by side, in the same order, so a move to the other tool later costs you little.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
Michał replies, not a bot. The address is used for this reply only.