How to get picked for vector search by coding agents
Neon took 34% of 158 judged vector search sessions. What the numbers say a vendor in this category should do.
If you sell vector search services, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for vector search and never compares vendors.
The numbers come from 158 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 vector search
Across 158 judged sessions, Neon was chosen most often, in 34% of runs. OpenAI Vector Stores was second with 15%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Neon | 54 | 34% |
| 2 | OpenAI Vector Stores | 24 | 15% |
| 3 | Qdrant | 23 | 15% |
| 4 | Typesense | 20 | 13% |
| 5 | Pinecone | 19 | 12% |
| 6 | Meilisearch | 7 | 4% |
| 7 | Elasticsearch | 2 | 1% |
| 8 | turbopuffer | 2 | 1% |
| 9 | Supabase Vector | 1 | 1% |
| 10 | Chroma | 1 | 1% |
Full board, every run replayable: the vector search leaderboard.
What the shape of this category means
The leader takes only 34% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 34%, vector search 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 Claude Code, Codex and Cursor all put Neon first, which is less common than it sounds: across the 31 categories we measured, Claude Code and Codex disagreed on the leader in 15 of them.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 58 | Neon (26) |
| Codex | 66 | Neon (18) |
| Cursor | 34 | Neon (10) |
Even where they agree, they get there differently. In this category Codex ran a web search in 100% of its sessions and Claude Code in 24%, so what you publish reaches nearly all of Codex's vector search sessions and about a quarter of Claude Code's.
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 | 45 | Neon |
| Junior developer | 60 | OpenAI Vector Stores |
| Senior engineer | 26 | Neon |
| Enterprise team | 27 | Qdrant |
That is 3 different products winning vector search for 4 kinds of buyer, out of the same 158 sessions. Nobody here is winning vector search. 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.
What to do about it in vector search
- Skip the build-versus-buy argument. No vector search 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. Neon holds 34% and OpenAI Vector Stores holds 15%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same vector search need written as a vibe coder landed on Neon, and written as an enterprise team landed on Qdrant. 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 vector search service 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 Neon? — chosen in 34% of sessions
- Do coding agents recommend OpenAI Vector Stores? — chosen in 15% of sessions
- Do coding agents recommend Qdrant? — chosen in 15% of sessions
- Do coding agents recommend Typesense? — chosen in 13% of sessions
- Do coding agents recommend Pinecone? — chosen in 12% of sessions
- Do coding agents recommend Meilisearch? — chosen in 4% of sessions
Where these numbers come from
158 judged sessions in vector search across 6 codebases, part of a published set of 15,051. 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 vector search run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
158 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 vector search service do coding agents choose?
Across 158 judged sessions, Neon was chosen most often, in 34% of runs. OpenAI Vector Stores was second with 15%. The result changes by who is asking.
Do Claude Code and Codex pick the same vector search service?
Yes. Claude Code and Codex both put Neon first in this category, which is less common than it sounds: they disagree on the leader in 15 of the 31 categories we measured.
How often do agents build vector search 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.
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.