# 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. Source: https://armature.tech/library/vector-search-coding-agents-playbook Published: 2026-09-08 Publisher: Armature, Inc. (https://armature.tech) --- 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](/leaderboards/vector-search). ## 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 all three agents put Neon 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 | 58 | Neon (26) | | Codex | 66 | Neon (18) | | Cursor | 34 | Neon (10) | 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 vector search 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 | 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](/library/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 vector search the clearest case is Azure AI Search: on the table in 21 sessions, chosen in none. | Product | Raised in | Chosen in | | --- | --- | --- | | Azure AI Search | 21 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 21 sessions is recorded in each transcript, one reason at a time. ## What to do about it in vector search 1. **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. 2. **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. 3. **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](/library/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](/library/audit-your-docs-for-coding-agents), [write a quickstart an agent can follow](/library/write-a-quickstart-an-agent-can-follow), and [how to measure install share](/library/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?](/library/do-coding-agents-recommend-neon) — chosen in 34% of sessions - [Do coding agents recommend OpenAI Vector Stores?](/library/do-coding-agents-recommend-openai-vector-stores) — chosen in 15% of sessions - [Do coding agents recommend Qdrant?](/library/do-coding-agents-recommend-qdrant) — chosen in 15% of sessions - [Do coding agents recommend Typesense?](/library/do-coding-agents-recommend-typesense) — chosen in 13% of sessions - [Do coding agents recommend Pinecone?](/library/do-coding-agents-recommend-pinecone) — chosen in 12% of sessions - [Do coding agents recommend Meilisearch?](/library/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 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](/library/how-we-measured-this). Every vector search run can be replayed on [the board](/leaderboards/vector-search). ## 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 agent and by who is asking. ### Do Claude Code and Codex pick the same vector search service? Yes. All three agents we tested put Neon first in this category, which is unusual: they disagree in half of the 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. ### Which vector search services do agents consider but never choose? Azure AI Search (raised in 21 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable. ## Read next - [Agent discoverability: the complete guide](https://armature.tech/library/agent-discoverability) (Markdown: https://armature.tech/library/agent-discoverability.md) - [How coding agents choose tools](https://armature.tech/library/how-coding-agents-choose-tools) (Markdown: https://armature.tech/library/how-coding-agents-choose-tools.md) - [Do coding agents recommend Neon?](https://armature.tech/library/do-coding-agents-recommend-neon) (Markdown: https://armature.tech/library/do-coding-agents-recommend-neon.md) - [Do coding agents recommend OpenAI Vector Stores?](https://armature.tech/library/do-coding-agents-recommend-openai-vector-stores) (Markdown: https://armature.tech/library/do-coding-agents-recommend-openai-vector-stores.md) - [Do coding agents recommend Qdrant?](https://armature.tech/library/do-coding-agents-recommend-qdrant) (Markdown: https://armature.tech/library/do-coding-agents-recommend-qdrant.md) --- Armature helps software products get discovered and used by coding agents. Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech