Infinity
InfiniFlowInfinity is a database built for LLM applications that indexes dense vectors, sparse vectors, tensors and full text in one engine and fuses them into a single hybrid query. Multi-vector tensor reranking sits alongside BM25 and HNSW retrieval, and structured data is queried in the same system. It is written in C++20 and self-hosted.
Verified 2026-08-18 via the GitHub API and the LICENSE body.
Openness
5 high confidence- license
- Apache-2.0(OSI)
- source
- public
- core-gated
- ungated
Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.
- https://github.com/infiniflow/infinity/blob/main/LICENSE recorded 2026-08-18
LICENSE file is the verbatim Apache-2.0 text
- https://api.github.com/repos/infiniflow/infinity recorded 2026-08-18
Repo metadata - license spdx_id Apache-2.0, private false, archived false, default branch main - for infiniflow/infinity.
- https://github.com/infiniflow/infinity/blob/main/README.md recorded 2026-08-18
README describes an AI-native database providing hybrid search over dense vectors, sparse vectors, tensors, full text and structured data, with a published benchmark, with no paid tier, enterprise edition or license-key-gated build beside it.
Adoption
2 low confidence4,675 GitHub stars, which lands in the 1K-10K stars band of the stars scale, level 2. The `infinity-sdk` package on PyPI is the Python client for a running server rather than the engine, and at about 11K monthly downloads it would band the client, not the product. No deployment figure is published, so the stars scale applies with its cap of 3.
- https://api.github.com/repos/infiniflow/infinity recorded 2026-08-18
Repo metadata - stargazers_count = 4,675 - for infiniflow/infinity.
Capability
4 medium confidenceBanded on the category feature matrix as complete retrieval system, distributed or cluster-capable. Placed one band below the vespa anchor, on a matrix that bands on how much of the persist-index-retrieve path a product provides itself, at what scale and over how many retrieval modes.
- https://github.com/infiniflow/infinity/blob/main/README.md recorded 2026-08-18
README still documents an AI-native database providing hybrid search over dense vectors, sparse vectors, tensors, full text and structured data, with a published benchmark.
Verified 2026-08-18