From the experiment

Do coding agents recommend LangGraph?

LangGraph was chosen in 3% of 681 judged agent frameworks sessions, ranking seventh. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

LangGraph was chosen in 3% of 681 judged agent frameworks sessions, ranking seventh. It was also raised as a candidate in 167 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 LangGraph. What an agent actually installed.

The numbers

CategoryAgent frameworks
Sessions in the category681
Sessions where LangGraph was chosen23
Install share3%
Rank in category7 of 35
Codebases it won in9
Raised as a candidate, not chosen167
Chosen when considered12%
Sitelangchain.com

By agent

The three agents agree closely on LangGraph, choosing it at rates within 2 points of each other.

AgentSessionsChose LangGraphShare
Claude Code23742%
Codex243104%
Cursor20194%

By who was asking

LangGraph performs similarly across the four kinds of buyer, from 1% to 5%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.

Who is askingSessionsChose LangGraphShare
Vibe coder16332%
Junior developer15721%
Senior engineer254135%
Enterprise team10755%

What LangGraph 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 SDK9414%
4Inngest507%
5Temporal294%
6Prism284%
7OpenAI Agents SDK244%
8LangGraph (this page)233%

What this means

This is an integration problem, not a presence problem. Agents raised LangGraph in 167 sessions and chose it in 23, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.

That is the cheaper of the two problems to have. The reason is written down in each losing transcript.

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 LangGraph: 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 LangGraph?

Yes. LangGraph was chosen in 23 of the 681 judged sessions in agent frameworks, a 3% install share, ranking seventh in its category.

Does Claude Code recommend LangGraph?

In 4 of the 237 sessions in agent frameworks run with Claude Code, which is 2%.

Do different coding agents treat LangGraph differently?

Not much. The three agents chose it at similar rates, between 2% and 4% 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 LangGraph considered but not chosen?

It was raised as a candidate in 167 sessions without being chosen, and chosen in 23. That is a 12% 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