Assembly Line

FlashRank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

FlashRank is an open-source search engine project on GitHub under the Apache-2.0 license (permissive), with 1k stars. It is built with CPython. Its last push was 4 months ago.

Stars
1k
License
Apache-2.0
Activity
Slowing
Latest release
0.2.9

Code on GitHub

Judgement

What it is
Building block
What it does
A small Python library that reranks search results with cross-encoder and LLM models before they go to an LLM, running on CPU without heavy dependencies.
Adopt it when
You want to improve RAG retrieval quality with reranking at low cost and latency.
Watch out
One maintainer, pre-1.0, and quiet since July 2026.
Ready for
Usable
Runs as
Library
Built with
Python and ONNX
How established
Established: started 2 years ago, latest release 0.2.9.
What the license allows
You can build it into a product you sell, as long as you keep its copyright notice.

Judged on 2026-11-03 from the project's README and GitHub data. The license and age lines are worked out directly.

Built from

Follow it down: FlashRank → CPython → GCC → LLVM project → runs on a microchip

How compilers were built, back to punched paper tape

Open-source alternatives to FlashRank

  1. 1
    Typesense typesense

    Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

    Building block Production-ready You want Algolia-style instant search for a site or app that you can self-host cheaply.

    ★ 27k GPL-3.0 C++ Active, pushed 3 days ago
  2. 2
    Sonic valeriansaliou

    🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.

    Building block Usable You need fast autocomplete and text search on a small server and can store documents elsewhere.

    ★ 21k MPL-2.0 Rust Active, pushed 3 days ago
  3. 3
    OpenSearch opensearch-project

    🔎 Open source distributed and RESTful search engine.

    Building block Production-ready You need Elasticsearch-class search under the Apache licence or run on AWS's managed OpenSearch.

    ★ 14k Apache-2.0 Java Active, pushed today
  4. 4
    Manticoresearch manticoresoftware

    Open-source search database for full-text, vector, and hybrid search with real-time indexing and SQL.

    Building block Production-ready You want a lighter Elasticsearch alternative and like querying search with SQL.

    ★ 12k GPL-3.0 C++ Active, pushed today
  5. 5
    Quickwit quickwit-oss

    Cloud-native OSS search engine for observability

    Building block Usable You need cheap, large-scale log search and want to move off Elasticsearch.

    ★ 12k Apache-2.0 Rust Active, pushed today
  6. 6
    ParadeDB paradedb

    One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.

    Building block Usable You want Elasticsearch-quality search on data already in Postgres without running a separate search cluster.

    ★ 9.5k AGPL-3.0 Rust Active, pushed today
  7. 7
    Infinity infiniflow

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

    Building block Experimental You need hybrid retrieval with tensor reranking for RAG and want it in a single engine.

    ★ 4.8k Apache-2.0 C++ Active, pushed today
  8. 8
    USearch unum-cloud

    Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

    Building block Production-ready You want to embed fast vector search into an application or database rather than run a vector database server.

    ★ 4.4k Apache-2.0 C++ Active, pushed 2 days ago

Commercial search engines for apps and sites

  1. 1
    Algolia Algolia

    18,000+ organizations trust Algolia to build intuitive, adaptive, high-performing experiences with a unified AI search & retrieval platform spanning agentic, generative, and search.

    Building block Production-ready An ecommerce or content site needs fast, polished search quickly and can pay for it.

    194 readers a month Commercial
  2. 2
    Coveo Coveo

    Generative search & relevant recommendations. The leading platform for GenAI, AI agents, commerce, customer service, workplace & website experiences.

    Complete system Production-ready A large company needs relevance-tuned search across commerce or support content, often inside Salesforce or Sitecore.

    132 readers a month Commercial
  3. 3
    Elastic Cloud Elastic NV

    Elastic Cloud is a family of Elasticsearch SaaS offerings — including hosted Elasticsearch, hosted app search, and hosted site search — that make it easy to deploy, operate, and scale Elastic products...

    Building block Production-ready You need Elasticsearch for search or logs and would rather pay Elastic than run clusters yourself.

    Commercial

Stars, license and activity come from GitHub and refresh on a rolling hourly schedule. The project's own description is quoted as written.