justrach/emergentDB

🧬 Self-optimizing vector database using MAP-Elites. 51x faster than ChromaDB, 82x faster than LanceDB, 100% recall. Auto-evolves optimal index configs via Quality Diversity.

41
/ 100
Emerging

This project helps operations engineers and developers managing large datasets of high-dimensional data, like text or image embeddings, to achieve lightning-fast search speeds. It takes in your data's numerical representations (embeddings) and automatically configures the best possible settings for your specific workload, outputting a highly optimized search database that can find similar items much quicker and with perfect accuracy.

Use this if you need to perform extremely fast, accurate searches on large volumes of high-dimensional numerical data without manually tuning complex database settings.

Not ideal if your data is small, not in an embedding format, or if you don't require high-performance semantic search capabilities.

semantic-search data-operations machine-learning-ops information-retrieval embedding-management
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 12 / 25

How are scores calculated?

Stars

20

Forks

3

Language

Rust

License

AGPL-3.0

Last pushed

Jan 23, 2026

Commits (30d)

0

Get this data via API

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

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