How to get picked for in-app chat and calls by coding agents
Stream Chat and Video took 30% of 175 judged in-app chat and calls sessions. What the numbers say a vendor in this category should do.
If you sell in-app communication providers, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for in-app chat and calls and never compares vendors.
The numbers come from 175 judged sessions with Claude Code, Codex and Cursor, spread across 6 realistic codebases, with every session read by a judge.
What coding agents choose for in-app chat and calls
Across 175 judged sessions, Stream Chat and Video was chosen most often, in 30% of runs. Supabase was second with 17%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Stream Chat and Video | 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% |
| 9 | LiveKit + Stream Chat and Video | 6 | 3% |
| 10 | Daily + Twilio | 3 | 2% |
Full board, every run replayable: the in-app chat and calls leaderboard.
What the shape of this category means
The leader takes only 30% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 30%, in-app chat and calls is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category all three agents put Stream Chat and Video first, which is less common than it sounds: across the eighteen categories we measured, Claude Code and Codex disagreed on the leader in nine of them.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 71 | Stream Chat and Video (18) |
| Codex | 72 | Stream Chat and Video (22) |
| Cursor | 32 | Stream Chat and Video (12) |
Even where they agree, they get there differently. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so what you publish reaches one of them in half its in-app chat and calls sessions and the other in almost none.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 60 | Supabase |
| Junior developer | 58 | Daily |
| Senior engineer | 29 | Stream Chat and Video |
| Enterprise team | 28 | Twilio |
That is 4 different products winning in-app chat and calls for 4 kinds of buyer, out of the same 175 sessions. Nobody here is winning in-app chat and calls. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In this category agents never chose to build it themselves. Every session ended with a product. That is good news: you are in a straight vendor comparison, and the levers that work are the ones you control.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In in-app chat and calls the clearest case is Sendbird: on the table in 57 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Sendbird | 57 sessions | 0 |
| Agora | 56 sessions | 0 |
| Vonage Video API | 38 sessions | 0 |
| Pusher | 34 sessions | 0 |
| Firebase | 31 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 216 sessions is recorded in each transcript, one reason at a time.
What to do about it in in-app chat and calls
- Skip the build-versus-buy argument. No in-app chat and calls session in this experiment ended with the agent writing its own implementation. Every one adopted a product, so the whole contest is against the other names in the table above.
- Aim at second place first. Stream Chat and Video holds 30% and Supabase holds 17%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same in-app chat and calls need written as a vibe coder landed on Supabase, and written as an enterprise team landed on Twilio. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every in-app communication provider on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Stream Chat and Video? — chosen in 30% of sessions
- Do coding agents recommend Supabase? — chosen in 17% of sessions
- Do coding agents recommend Daily? — chosen in 16% of sessions
- Do coding agents recommend LiveKit? — chosen in 7% of sessions
- Do coding agents recommend TalkJS? — chosen in 6% of sessions
- Do coding agents recommend Azure Communication Services? — chosen in 1% of sessions
Where these numbers come from
175 judged sessions in in-app chat and calls across 6 codebases, part of a published set of 5,915. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every in-app chat and calls run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
175 judged sessions across 6 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What in-app communication provider do coding agents choose?
Across 175 judged sessions, Stream Chat and Video was chosen most often, in 30% of runs. Supabase was second with 17%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same in-app communication provider?
Yes. All three agents we tested put Stream Chat and Video first in this category, which is unusual: they disagree in half of the categories we measured.
How often do agents build in-app chat and calls themselves instead of installing something?
Never, in this category. Every one of the sessions ended with the agent adopting a product rather than writing the code itself.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which in-app communication providers do agents consider but never choose?
Sendbird (raised in 57 sessions, chosen in none), Agora (raised in 56 sessions, chosen in none), Vonage Video API (raised in 38 sessions, chosen in none), Pusher (raised in 34 sessions, chosen in none), Firebase (raised in 31 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
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.