wizenheimer/comet

A Vector Store written in Go - Supports hybrid retrieval over BM25, Flat, HNSW, IVF, PQ and IVFPQ Index with Quantization, Metadata Filtering, Reranking, Reciprocal Rank Fusion, Soft Deletes, Index Rebuilds and much much more

34
/ 100
Emerging

This tool helps developers who need to build custom, high-performance search functionalities directly into their applications. It takes in collections of data, including numerical vectors (like embeddings), text, and associated attributes, and outputs highly relevant search results quickly. This is ideal for backend engineers or machine learning engineers who are creating advanced search features for their users.

107 stars.

Use this if you are a developer looking to integrate a custom, high-performance, and deeply understandable hybrid search solution directly into your Go-based application, requiring fine-grained control over search internals and indexing strategies.

Not ideal if you need a managed, plug-and-play vector database service, or if you are not comfortable with Go programming and building search infrastructure from scratch.

information-retrieval application-development search-engine-design data-indexing backend-engineering
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

107

Forks

2

Language

Go

License

MIT

Last pushed

Oct 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/wizenheimer/comet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.