Codex vs Cursor: what 52K developers’ public commits show
Among 363,366 people with detectable AI coding-tool attribution in public repositories, 46,204 have Cursor attribution and 6,966 have Codex attribution.
18% of people with Codex attribution also have Cursor attribution.
These counts reflect which tools leave detectable public attribution, not market share or total use.
- Developers with Cursor attribution46,20412,375 active in the last 30 days
- Developers with Codex attribution6,9663,723 active in the last 30 days
- Codex developers who also use Cursor18%1,250 people with both
Codex vs Cursor usage, side by side
| Tool | Developers | Share | Active, 30 days | Only this tool | Median commits |
|---|---|---|---|---|---|
| Cursor | 46,204 | 12.7% | 12,375 (27%) | 21,896 | 11 |
| Codex | 6,966 | 1.9% | 3,723 (53%) | 655 | 41 |
Do developers use Codex and Cursor together?
Read each row as: of the developers with the row's tool, the share who also have the column's tool. The overlap is asymmetric, because the populations differ in size.
| Developers with… | …also Cursor | …also Codex |
|---|---|---|
| Cursor | — | 3% (1,250) |
| Codex | 18% (1,250) | — |
Cursor vs Codex: how the tools differ
| Codex | Cursor | |
|---|---|---|
| Made by | OpenAI | Anysphere |
| Interface | Command line, IDE extension, and a cloud agent | The editor itself: completion, chat and an agent |
| Runs | On your machine, or as cloud tasks in their own environment | As a desktop editor, with background agents available |
| Pricing | See OpenAI | See Anysphere |
Choosing between Codex and Cursor
The deciding question is usually where you want to work. Codex suits the terminal, or handing tasks to a cloud agent that works in parallel. Cursor suits staying inside an editor with AI completion, chat and an agent beside the code.
Many developers do not choose. 18% of developers with Codex attribution also have Cursor attribution, so pairing the tools is common among the most active public users.
Why these numbers are not market share
DevImprint counts tools from public attribution in repository history. Tools differ in whether, and how often, they leave that attribution, and developers can switch it off. A tool that attributes its work by default will appear far more often than one that usually leaves no trace, whatever their real user bases are.
The data therefore answers “how many developers show detectable use of each tool in public code”, not “how many developers use each tool”. Private repositories, inline completion and unattributed use are invisible to it. See what this leaderboard cannot see and the methodology. GitHub Copilot, Windsurf and similar tools rarely leave detectable attribution, so they are not compared here.
Codex vs Cursor: common questions
Do more developers use Codex or Cursor?
Cursor. 46,204 developers show Cursor attribution in public commits, against 6,966 for Codex. Tools differ in how often they leave public attribution, so this describes public, attributed use rather than overall popularity.
Do developers use Codex and Cursor together?
Rarely: 18% of developers with Codex attribution also have Cursor attribution (1,250 people). Commit data cannot tell whether they use both at once or moved from one to the other.
What is the difference between Codex and Cursor?
Codex is a coding agent from OpenAI; Cursor is an AI code editor from Anysphere, built on VS Code. Codex suits the terminal, or handing tasks to a cloud agent that works in parallel; Cursor suits staying inside an editor with AI completion, chat and an agent beside the code.
Is Codex or Cursor better?
Public commit data cannot say which is better: commit counts do not measure quality, productivity or fit for a task. Choose by where you want to work, and note how many developers use more than one.
Other comparisons
Codex vs Claude CodeCursor vs Claude CodeCodex vs Claude Code vs Cursor
Cite this statistic
DevImprint recorded 1,250 people with detected attribution for both Codex and Cursor for Codex and Cursor. Population: people in the complete ranked population. Source snapshot: 2026-11-08T20:28:18.634744+00:00 (d5ada2cdab024e900790b6073b24a564c20dccc8e8748dea35d39a81c87e6499). 33.2% of known repositories scanned; provisional. Methodology: 2026-09-14. Page: https://devimprint.com/compare/codex-vs-cursor/. Current data: https://devimprint.com/leaderboard.json