HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
unum-cloud
USearch
C++2023–2026
unum-cloud / USearch

USearch

One proximity graph for vector search, sparse products & attention across RAM, VRAM & NVMe, over dense vectors, sequences, shapes & geospatial sets in 14 languages 🔍

23Distinct people
38Mentions
0Explicit recommenders
4.4KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

One proximity graph for vector search, sparse products & attention across RAM, VRAM & NVMe, over dense vectors, sequences, shapes & geospatial sets in 14 languages 🔍

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 1:56:48 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by year38 dated mentions

Observed mentions: 2023-05-03 15:33:56 UTC to 2026-03-07 06:17:08 UTC.

0510152023-01-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 12 mentions; 3 submissions, 9 comments20232024-01-01 00:00:00 UTC to 2025-01-01 00:00:00 UTC (exclusive): 14 mentions; 3 submissions, 11 comments20242025-01-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 8 mentions; 1 submissions, 7 comments2026-01-01 00:00:00 UTC to 2027-01-01 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 comments. Incomplete calendar period.2026*

* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
20232023-01-01 00:00:00 UTC2024-01-01 00:00:00 UTC1239
20242024-01-01 00:00:00 UTC2025-01-01 00:00:00 UTC14311
20252025-01-01 00:00:00 UTC2026-01-01 00:00:00 UTC817
2026 (partial)2026-01-01 00:00:00 UTC2027-01-01 00:00:00 UTC404

What Hacker News says

12 sources
The hardest (still missing) part of efficient cosine computation distance computation is picking a good epsilon for the `sqrt` calculation and avoiding "division by zero" problems. We have an open issue about it in USearch and a related one in SimSIMD itself, so if you have any suggestions, please share your insights - they would impact millions of devices using the library (directly on servers and mobile, and through projects like ClickHouse and some of the Google repos): https://github.com/unum-cloud/usearch/issues/320
In Python, C, Assembly – Faster Cosine Similarity

Show HN: USearch Images demo in 200 lines of Python

Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably all other vector search engines combined: C++, C, Python, Java, JavaScript, Rust, Obj-C, Swift, C#, GoLang, and even slightly outdated bindings for Wolfram. Need to refresh that last one! UForm v2 [2]: Imagine a much smaller OpenAI CLIP but more efficient and tra
Read the rest
ined on balanced multilingual datasets, with equal exposure to languages from English, Chinese, and Hindi to Arabic, Hebrew, and Armenian. UForm now supports 21 languages, is so tiny that you can run it in the browser, and outputs small 256-dimensional embeddings. Perfect for rapid image and video searches. It's already available on Hugging-Face as "unum-cloud/uform-vl-multilingual-v2". UCall [3]: It started as a FastAPI alternative focusing on JSON-RPC (instead of REST protocols), offering 70x the bandwidth and 1/50th the latency. It was good but not enough, so we've added REST and TLS support, broadening its appeal. I've merged that code, and it is yet to be tested. Early benchmarks suggest that we still hit the same 150'000-250'000 requests/s on a single CPU core in Python by reusing HTTPS connections. StringZilla [4]: This project lets you sift through multi-gigabyte or terabyte strings with minimal use of RAM and maximal use of SIMD and SWAR techniques. All these projects are engineered for scalability and efficiency, even on tight budgets. Our demo, for instance, works on hundreds of gigabytes of images using just a few gigabytes of RAM and no GPUs for AI inference. That is a toy example with a small, noisy dataset, and I look forward to showing a much larger setup. Interestingly, even this tiny setup illustrates issues common to UForm and much larger OpenAI CLIP models - the quality of Multi-Modal alignment [5]. It also shows how different/accurate the search results are across different languages. Synthetic benchmarks suggest massive improvements for some low-resource languages (like Armenian and Hebrew) and more popular ones (like Hindi and Arabic) [6]. Still, when we look at visual demos like this, I can see a long road ahead for us and the broader industry, making LLMs Multi-Modal in 2024 :) All of the projects and the demo code are available under an Apache license, so feel free to use them in your commercial projects :) PS: The demo looks much nicer with just Unsplash dataset of 25'000 images, but it's less representative of modern AI datasets, too small, and may not be the best way to honestly show our current weaknesses. The second dataset - Conceptual Captions - is much noisier, and quite ugly. [1]: https://github.com/unum-cloud/usearch [2]: https://github.com/unum-cloud/uform [3]: https://github.com/unum-cloud/ucall [4]: https://github.com/ashvardanian/stringzilla [5]: https://ashvardanian.com/posts/searching-stable-marriages/#e... [6]: https://www.unum.cloud/blog/2023-08-17-uform-graphcore
9 points · Open discussion
> It doesn't appear to query CPUID Yes, I'm actually looking for a good way to do it for other projects as well. I've looked into a couple more libs, and here is the best I've come up with so far: https://github.com/unum-cloud/usearch/blob/f942b6f334b31716f... > Your substring routines have multiplicative worst case Yes, that is true. It's a very simple stupid trick, just happens to work well for me :) > It seems quite likely that your confirmation step We have a different library internally at Unum, that avoids this shortcoming. It has a few thousand lines of C++ templates with SIMD intrinsics... and it's definitely more efficient, but the margins aren't always high. So I kept the pure C version with inlined functions as minimal and simple as possible. > It would actually be possible to hook Stringzilla up to `memchr`'s benchmark suite i
Read the rest
f you were interested. :-) Yes, that would be a fun thing to do! I haven't had time to look into `memchr` yet, but would expect great perf from your lib as well. For me the State of the Art is Intel HyperScan. Probably the most advanced SIMD library overall, not just for strings. I was very impressed with their perf ~5 years ago. But the repo is 200 K LOC... So get ready to invest a weekend :) That said, I'm a bit slammed with work right now, including open-source. Hoping to ship a new major release in UCall this week, and a minor one in USearch :)
In Stringzilla: Fastest string sort, search, split, and shuffle using SIMD
We don't use BLAS. Why? BLAS helps with matrix-matrix multiplications, if you feel lazy and don't want to write the matrix tiling code manually. They bring essentially nothing of value in vector-vector operations, as compilers can properly auto-vectorize simple dot products... Moreover, they generally only target single and double precision, while we often prefer half or quarter precision. All in all, meaningless dependency. What do we use? I wrote a tiny package called SimSIMD. It's idea is to utilize less common SIMD instructions, especially in mixed-typed computations, that are hard for compilers to optimize. It was also a fun exercise to evaluate the performance of new SVE instruction on recent Arm CPUs, like the Graviton 3. You can find the code, the benchmarks, and the results in the repo: https://github.com/ashvardanian/simsimd Sti
Read the rest
ll, even without SimSIMD, USearch seems to be one of the faster implementations of vector search. You can find the benchmarks in the first table here: https://github.com/unum-cloud/usearch#memory-efficiency-down...
In USearch: Smaller and faster single-file vector search engine
On the second paragraph: That’s exactly how it worked originally. You can create composite embeddings, and then define some hybrid similarity measure to compute both physical proximity, sentiment of writing, and some categorical tags. Coding it and experimenting with metrics, however, was much harder then. There was no Numba and I had to implement every experiment in C++, without JIT-ing: https://github.com/unum-cloud/usearch/releases/tag/v0.19.0
In From Dating to Vector Search – “Stable Marriages” on a Global Scale
Always pleasure to see short implementations, but I’d still take HNSW over such approach. Its core implementation can also be quite compact. In our case with USearch [1] its about 2k LOC, even with a custom implementation of priority queues and custom numeric types like uint40_t for indexes beyond 4B points. Obviously, together with bindings for Rust, Python, JavaScript, Java, Objective-C, Swift, and Wolfram it gets slightly larger, but on the bright side, you can pass JIT-compiled functions and store/search elements of different dimensionality, which allows much broader applicability [2]. [1]: https://github.com/unum-cloud/usearch [2]: https://ashvardanian.com/posts/abusing-vector-search
In FANN: Vector Search in 200 Lines of Rust

Show HN: USearch – Smaller and Faster Single-File Vector Search Engine

Last week was insane for vector search. Weaviate raised $50M, and Pinecone raised $100M... That's a lot and makes you believe that vector search is hard. But it's not. I have spent the last couple of days implementing a single-file vector search engine from scratch, which is at least the tenth in the twenty years of my career. But this time, it's different. Instead of inventing a brand new algorithm and doing some crazy optimizations on the GPU, I: 1. took the standard HNSW algorithm, 2. fitted into 1000 lines of C++11 for portability, 3. added quantization and hardware-accelerated metrics, 4. wrapped for Python, JavaScript, Rust, and Java, and 5. open-sourced it! It was fun, and to my surprise, it performed well, reaching 300K QPS on Amazon c7g instances. I never had to use third-party vector search products, but the first testers of U
Read the rest
Search suggested 3x performance improvement over their existing solutions. My colleagues and friends are also adding bindings for GoLang and the Wolfram language. We will soon add Windows support, a standalone server, and a distributed version based on UCall we shared a month ago. There are, of course, but you can already use it! One of the apparent use cases is Semantic Search platforms. The example at the end of the GitHub page shows how to use USearch, UCall, and the UForm transformers together to build up a text-to-image semantic search platform in just 20 lines of Python. Try it and join the development! We also have a lot of open positions, especially for those who want to work with us on next-get algorithms and AI infra rather than polishing and repackaging existing ideas :)
21 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.