From the experiment

Do coding agents recommend Cursor SDK?

Cursor SDK was chosen in 14% of 681 judged agent frameworks sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Cursor SDK was chosen in 14% of 681 judged agent frameworks sessions, ranking second. It was also raised as a candidate in 98 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in agent frameworks inside a realistic codebase. Not what a chat assistant says about Cursor SDK. What an agent actually installed.

The numbers

CategoryAgent frameworks
Sessions in the category681
Sessions where Cursor SDK was chosen94
Install share14%
Rank in category2 of 35
Codebases it won in12
Raised as a candidate, not chosen98
Chosen when considered49%
Sitecursor.com

By agent

The three agents treat Cursor SDK very differently. Cursor chose it in 47% of its sessions in this category and Claude Code in 0%, a spread of 47 points.

AgentSessionsChose Cursor SDKShare
Claude Code23700%
Codex24300%
Cursor2019447%

A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 0%, not 14%.

By who was asking

Cursor SDK performs similarly across the four kinds of buyer, from 9% to 20%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.

Who is askingSessionsChose Cursor SDKShare
Vibe coder1632817%
Junior developer1572113%
Senior engineer254249%
Enterprise team1072120%

What Cursor SDK was up against

The full ranking in agent frameworks, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)17025%
2Vercel AI SDK9514%
3Cursor SDK (this page)9414%
4Inngest507%
5Temporal294%
6Prism284%
7OpenAI Agents SDK244%
8LangGraph233%

What this means

Cursor SDK was raised in 98 sessions and chosen in 94. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

Where these numbers come from

The 681 sessions in agent frameworks are part of a published set of 5,292, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every agent frameworks run can be replayed on the board.

If you work on Cursor SDK: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.

<!-- generated by scripts/write-data-pages.mjs -->

Common questions

Do coding agents recommend Cursor SDK?

Yes. Cursor SDK was chosen in 94 of the 681 judged sessions in agent frameworks, a 14% install share, ranking second in its category.

Does Claude Code recommend Cursor SDK?

In 0 of the 237 sessions in agent frameworks run with Claude Code, which is 0%.

Do different coding agents treat Cursor SDK differently?

Yes, and by a wide margin. Cursor chose it in 47% of its runs and Claude Code in 0%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 51 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.

How often is Cursor SDK considered but not chosen?

It was raised as a candidate in 98 sessions without being chosen, and chosen in 94. That is a 49% conversion from considered to chosen.

Where this comes from

Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages