Do coding agents recommend Lago?
Lago was chosen in 11% of 548 judged usage-based billing sessions, ranking third. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Lago was chosen in 11% of 548 judged usage-based billing sessions, ranking third. It was also raised as a candidate in 377 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in usage-based billing inside a realistic codebase. Not what a chat assistant says about Lago. What an agent actually installed.
The numbers
| Category | Usage-based billing |
| Sessions in the category | 548 |
| Sessions where Lago was chosen | 62 |
| Install share | 11% |
| Rank in category | 3 of 16 |
| Codebases it won in | 8 |
| Raised as a candidate, not chosen | 377 |
| Chosen when considered | 14% |
| Site | getlago.com |
By agent
Claude Code, Codex, Cursor and Muse Code land within 8 points of each other on Lago, which is closer than most products in this experiment manage. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Lago | Share |
|---|---|---|---|
| Claude Code | 127 | 18 | 14% |
| Codex | 164 | 22 | 13% |
| Cursor | 132 | 15 | 11% |
| Grok Build CLI | 26 | 1 | 4% |
| Muse Code | 99 | 6 | 6% |
By who was asking
Lago does much better with one kind of buyer than another. It won 19% of sessions asked as senior engineer and 2% of those asked as junior developer.
| Who is asking | Sessions | Chose Lago | Share |
|---|---|---|---|
| Junior developer | 100 | 2 | 2% |
| Senior engineer | 202 | 38 | 19% |
| Enterprise team | 246 | 22 | 9% |
What Lago was up against
The full ranking in usage-based billing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Metronome | 225 | 41% |
| 2 | Built in-house (no product adopted) | 107 | 20% |
| 3 | Orb | 88 | 16% |
| 4 | Lago (this page) | 62 | 11% |
| 5 | Stripe Billing | 13 | 2% |
| 6 | CGRateS | 13 | 2% |
| 7 | OpenMeter | 9 | 2% |
| 8 | Oracle BRM | 7 | 1% |
What this means
This is an integration problem, not a presence problem. Agents raised Lago in 377 sessions and chose it in 62, 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 548 sessions in usage-based billing are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every usage-based billing run can be replayed on the board.
If you work on Lago: 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 Lago?
Yes. Lago was chosen in 62 of the 548 judged sessions in usage-based billing, a 11% install share, ranking third in its category.
Does Claude Code recommend Lago?
In 18 of the 127 sessions in usage-based billing run with Claude Code, which is 14%.
Do different coding agents treat Lago differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 6% and 14% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 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 Lago considered but not chosen?
It was raised as a candidate in 377 sessions without being chosen, and chosen in 62. That is a 14% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.