infiniflow/infinity

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

69
/ 100
Established

Supports structured data filtering alongside vector and text search, with advanced reranking via RRF, weighted sum, and ColBERT. Built as a single-binary deployment with no external dependencies, embedding directly as a Python module for seamless LLM application integration. Achieves 0.1ms query latency on million-scale datasets and 1ms full-text search on 33M documents via SIMD-optimized indexing (AVX2).

4,437 stars. Actively maintained with 42 commits in the last 30 days.

No Package No Dependents
Maintenance 23 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

4,437

Forks

416

Language

C++

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

42

Get this data via API

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

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