From the experiment

Do coding agents recommend Vercel AI SDK?

Vercel AI SDK is the most chosen agent framework, taking 14% of 681 judged agent frameworks sessions. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Vercel AI SDK is the most chosen agent framework, taking 14% of 681 judged agent frameworks sessions. It was also raised as a candidate in 101 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 Vercel AI SDK. What an agent actually installed.

The numbers

CategoryAgent frameworks
Sessions in the category681
Sessions where Vercel AI SDK was chosen95
Install share14%
Rank in category1 of 35
Codebases it won in6
Raised as a candidate, not chosen101
Chosen when considered48%
Siteai-sdk.dev

By agent

The three agents agree closely on Vercel AI SDK, choosing it at rates within 5 points of each other.

AgentSessionsChose Vercel AI SDKShare
Claude Code2373414%
Codex2433916%
Cursor2012211%

By who was asking

Vercel AI SDK does much better with one kind of buyer than another. It won 40% of sessions asked as vibe coder and 3% of those asked as senior engineer.

Who is askingSessionsChose Vercel AI SDKShare
Vibe coder1636540%
Junior developer1571912%
Senior engineer25473%
Enterprise team10744%

What Vercel AI 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 SDK (this page)9514%
3Cursor SDK9414%
4Inngest507%
5Temporal294%
6Prism284%
7OpenAI Agents SDK244%
8LangGraph233%

What this means

Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.

The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.

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 Vercel AI 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 Vercel AI SDK?

Yes. Vercel AI SDK was chosen in 95 of the 681 judged sessions in agent frameworks, a 14% install share, ranking first in its category.

Does Claude Code recommend Vercel AI SDK?

In 34 of the 237 sessions in agent frameworks run with Claude Code, which is 14%.

Do different coding agents treat Vercel AI SDK differently?

Not much. The three agents chose it at similar rates, between 11% and 16% of their runs.

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 Vercel AI SDK considered but not chosen?

It was raised as a candidate in 101 sessions without being chosen, and chosen in 95. That is a 48% 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