Do coding agents recommend Stream Chat and Video?
Stream Chat and Video is the most chosen in-app communication provider, taking 30% of 175 judged in-app chat and calls sessions.
Stream Chat and Video is the most chosen in-app communication provider, taking 30% of 175 judged in-app chat and calls sessions. It was also raised as a candidate in 84 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in in-app chat and calls inside a realistic codebase. Not what a chat assistant says about Stream Chat and Video. What an agent actually installed.
The numbers
| Category | In-app chat and calls |
| Sessions in the category | 175 |
| Sessions where Stream Chat and Video was chosen | 52 |
| Install share | 30% |
| Rank in category | 1 of 17 |
| Codebases it won in | 4 |
| Raised as a candidate, not chosen | 84 |
| Chosen when considered | 38% |
| Site | getstream.io |
By agent
The three agents land within 13 points of each other on Stream Chat and Video, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Stream Chat and Video | Share |
|---|---|---|---|
| Claude Code | 71 | 18 | 25% |
| Codex | 72 | 22 | 31% |
| Cursor | 32 | 12 | 38% |
By who was asking
Stream Chat and Video does much better with one kind of buyer than another. It won 48% of sessions asked as senior engineer and 14% of those asked as enterprise team.
| Who is asking | Sessions | Chose Stream Chat and Video | Share |
|---|---|---|---|
| Vibe coder | 60 | 19 | 32% |
| Junior developer | 58 | 15 | 26% |
| Senior engineer | 29 | 14 | 48% |
| Enterprise team | 28 | 4 | 14% |
What Stream Chat and Video was up against
The full ranking in in-app chat and calls, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Stream Chat and Video (this page) | 52 | 30% |
| 2 | Supabase | 30 | 17% |
| 3 | Daily | 28 | 16% |
| 4 | LiveKit | 13 | 7% |
| 5 | TalkJS | 11 | 6% |
| 6 | Ably + LiveKit | 8 | 5% |
| 7 | Daily + Stream Chat and Video | 7 | 4% |
| 8 | Twilio | 7 | 4% |
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 175 sessions in in-app chat and calls are part of a published set of 5,915, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every in-app chat and calls run can be replayed on the board.
If you work on Stream Chat and Video: 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 Stream Chat and Video?
Yes. Stream Chat and Video was chosen in 52 of the 175 judged sessions in in-app chat and calls, a 30% install share, ranking first in its category.
Does Claude Code recommend Stream Chat and Video?
In 18 of the 71 sessions in in-app chat and calls run with Claude Code, which is 25%.
Do different coding agents treat Stream Chat and Video differently?
Yes, and by a wide margin. Cursor chose it in 38% of its runs and Claude Code in 25%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 56 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 Stream Chat and Video considered but not chosen?
It was raised as a candidate in 84 sessions without being chosen, and chosen in 52. That is a 38% conversion from considered to chosen.
Where this comes from
Armature ran 5,915 judged sessions with Claude Code, Codex and Cursor inside 56 realistic codebases, and published every run. The numbers on this page come from that work.