REPOGEO REPORT · LITE

spotify/voyager

Default branch main · commit 2a2f1f13 · scanned 6/24/2026, 7:27:10 AM

GitHub: 1,578 stars · 78 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE

33 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

2 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface spotify/voyager, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Reposition the README's opening to explicitly state its ANN purpose and disambiguate from GraphQL

Why:

CURRENT

**_Voyager_** is a library for performing fast approximate nearest-neighbor searches on an in-memory collection of vectors.

COPY-PASTE FIX

**_Voyager_** is Spotify's high-performance, production-ready library for **approximate nearest-neighbor (ANN) search** on vector embeddings, with bindings for Python and Java. **Note: This project is NOT a GraphQL federation gateway.**

mediumtopics#2

Add 'similarity-search' to repository topics

Why:

CURRENT

hnsw, hnswlib, java, machine-learning, nearest-neighbor-search, python

COPY-PASTE FIX

hnsw, hnswlib, java, machine-learning, nearest-neighbor-search, python, similarity-search

mediumreadme#3

Add a 'Key Features' section to highlight benefits and use cases

Why:

COPY-PASTE FIX

### Key Features
*   Fast Approximate Nearest-Neighbor (ANN) search for vector embeddings.
*   Bindings for both Python and Java with full feature parity.
*   Built on the efficient HNSW algorithm, with production optimizations from Spotify.
*   Designed for ease of use, simplicity, and deployability in large-scale systems.
*   Proven in production at Spotify, powering user-facing features with hundreds of millions of queries daily.
*   Ideal for recommendation systems, semantic search, and data clustering.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface spotify/voyager

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

ScaNN

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

ScaNN · recommended 2×
Faiss · recommended 1×
Annoy · recommended 1×
hnswlib · recommended 1×
NMSLIB · recommended 1×

CATEGORY QUERY
Need a simple Python library for efficient similarity search on large vector datasets.
you: not recommended
AI recommended (in order):
1. Faiss
2. Annoy
3. ScaNN
4. hnswlib
5. NMSLIB
AI recommended 5 alternatives but never named spotify/voyager. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are good approximate nearest-neighbor solutions with bindings for both Java and Python?
you: not recommended
AI recommended (in order):
1. Faiss (daniel-shuy/faiss-java)
2. Hnswlib (stephenh/hnswlib-jna)
3. Annoy (spotify/annoy-java)
4. ScaNN
5. NMSLIB (stephenh/nmslib-java)
AI recommended 5 alternatives but never named spotify/voyager. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of spotify/voyager?
pass
AI did not name spotify/voyager — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts spotify/voyager in production, what risks or prerequisites should they evaluate first?
pass
AI named spotify/voyager explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo spotify/voyager solve, and who is the primary audience?
pass
AI named spotify/voyager explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of spotify/voyager. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/spotify/voyager.svg)](https://repogeo.com/en/r/spotify/voyager)

HTML

<a href="https://repogeo.com/en/r/spotify/voyager"><img src="https://repogeo.com/badge/spotify/voyager.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

spotify/voyager — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite