best-of-ml-rust

🏆  A ranked list of awesome machine learning Rust libraries.

This curated list contains 220 awesome open-source projects with a total of 480K stars grouped into 10 categories. All projects are ranked by a project-quality score, which is calculated based on various metrics automatically collected from GitHub and different package managers. If you like to add or update projects, feel free to open an issue, submit a pull request, or directly edit the projects.yaml. Contributions are very welcome!

🧙‍♂️ Discover other best-of lists or create your own.

Contents

• Machine Learning Frameworks 87 projects
• Text Data & NLP 62 projects
• Image Data 12 projects
• Data Loading & Extraction 21 projects
• Graph Data 6 projects
• Model Interpretability 1 projects
• MLOps 3 projects
• Applications 24 projects
• Analysis 1 projects
• Other 2 projects
• Others 3 projects

Explanation

• 🥇🥈🥉  Combined project-quality score
• ⭐️  Star count from GitHub
• 🐣  New project (less than 6 months old)
• 💤  Inactive project (6 months no activity)
• 💀  Dead project (12 months no activity)
• 📈📉  Project is trending up or down
• ➕  Project was recently added
• ❗️  Warning (e.g. missing/risky license)
• 👨‍💻  Contributors count from GitHub
• 🔀  Fork count from GitHub
• 📋  Issue count from GitHub
• ⏱️  Last update timestamp on package manager
• 📥  Download count from package manager
• 📦  Number of dependent projects
•   A binding for another project.

Machine Learning Frameworks

General-purpose machine learning and deep learning frameworks.

statrs (🥇23 · ⭐ 580) - Statistical computation library for Rust. MIT

• GitHub (👨‍💻 46 · 🔀 83 · 📦 17K · 📋 150 - 27% open · ⏱️ 23.09.2024):

   git clone https://github.com/boxtown/statrs
  

burn (🥇22 · ⭐ 8.5K) - Burn is a new comprehensive dynamic Deep Learning Framework built using.. Apache-2

• GitHub (👨‍💻 140 · 🔀 420 · 📦 430 · 📋 670 - 30% open · ⏱️ 30.09.2024):

   git clone https://github.com/burn-rs/burn
  

nalgebra (🥇22 · ⭐ 3.9K · 📉) - Linear algebra library for Rust. Apache-2

• GitHub (👨‍💻 220 · 🔀 470 · 📦 42K · 📋 710 - 44% open · ⏱️ 21.07.2024):

   git clone https://github.com/dimforge/nalgebra
  

linfa (🥇22 · ⭐ 3.7K) - A Rust machine learning framework. Apache-2

• GitHub (👨‍💻 45 · 🔀 240 · 📦 520 · 📋 160 - 37% open · ⏱️ 03.07.2024):

   git clone https://github.com/rust-ml/linfa
  

candle (🥇21 · ⭐ 15K) - Minimalist ML framework for Rust. Apache-2

• GitHub (👨‍💻 150 · 🔀 890 · 📦 1.1K · 📋 680 - 45% open · ⏱️ 02.10.2024):

   git clone https://github.com/huggingface/candle
  

tvm (🥇21 · ⭐ 12K) - Open deep learning compiler stack for cpu, gpu and specialized.. Apache-2

• GitHub (👨‍💻 1K · 🔀 3.3K · 📥 4.5K · 📋 3.4K - 12% open · ⏱️ 02.10.2024):

   git clone https://github.com/apache/tvm
  

mistral.rs (🥇21 · ⭐ 3.6K · ➕) - Blazingly fast LLM inference. MIT

• GitHub (👨‍💻 25 · 🔀 250 · 📥 830 · 📋 240 - 27% open · ⏱️ 02.10.2024):

   git clone https://github.com/EricLBuehler/mistral.rs
  

Peroxide (🥇21 · ⭐ 510) - Rust numeric library with R, MATLAB & Python syntax. Apache-2

• GitHub (👨‍💻 19 · 🔀 30 · 📦 200 · 📋 35 - 31% open · ⏱️ 30.07.2024):

   git clone https://github.com/Axect/Peroxide
  

tch-rs (🥈20 · ⭐ 4.2K) - Rust bindings for the C++ api of PyTorch. Apache-2

• GitHub (👨‍💻 76 · 🔀 330 · 📥 1.9K · 📦 1.9K · 📋 560 - 24% open · ⏱️ 15.09.2024):

   git clone https://github.com/LaurentMazare/tch-rs
  

rust-numpy (🥈20 · ⭐ 1.1K) - PyO3-based Rust bindings of the NumPy C-API. BSD-2

• GitHub (👨‍💻 43 · 🔀 100 · 📦 3.3K · 📋 130 - 10% open · ⏱️ 21.07.2024):

   git clone https://github.com/PyO3/rust-numpy
  

sprs (🥈20 · ⭐ 390) - sparse linear algebra library for rust. Apache-2

• GitHub (👨‍💻 36 · 🔀 44 · 📦 1.4K · 📋 150 - 29% open · ⏱️ 22.09.2024):

   git clone https://github.com/vbarrielle/sprs
  

azure-sdk-for-rust (🥈19 · ⭐ 700 · 📈) - This repository is for active development of the.. MIT

• GitHub (👨‍💻 140 · 🔀 230 · 📦 1.3K · 📋 600 - 30% open · ⏱️ 28.08.2024):

   git clone https://github.com/Azure/azure-sdk-for-rust
  

smartcore (🥈18 · ⭐ 700 · 💤) - A comprehensive library for machine learning and numerical.. Apache-2

• GitHub (👨‍💻 29 · 🔀 73 · 📦 230 · 📋 120 - 56% open · ⏱️ 04.03.2024):

   git clone https://github.com/smartcorelib/smartcore
  

argmin (🥈17 · ⭐ 990) - Numerical optimization in pure Rust. Apache-2

• GitHub (👨‍💻 40 · 🔀 77 · 📦 520 · 📋 120 - 24% open · ⏱️ 31.08.2024):

   git clone https://github.com/argmin-rs/argmin
  

faiss-rs (🥈17 · ⭐ 200) - Rust language bindings for Faiss. Apache-2

• GitHub (👨‍💻 11 · 🔀 32 · 📦 32 · 📋 36 - 25% open · ⏱️ 18.09.2024):

   git clone https://github.com/Enet4/faiss-rs
  

rust (🥈16 · ⭐ 5.1K · 💤) - Rust language bindings for TensorFlow. Apache-2

• GitHub (👨‍💻 49 · 🔀 420 · 📋 190 - 32% open · ⏱️ 03.12.2023):

   git clone https://github.com/tensorflow/rust
  

ratchet (🥈15 · ⭐ 580 · ➕) - A cross-platform browser ML framework. MIT

• GitHub (👨‍💻 14 · 🔀 31 · 📦 4 · 📋 90 - 27% open · ⏱️ 20.09.2024):

   git clone https://github.com/huggingface/ratchet
  

luminal (🥈14 · ⭐ 1.5K · ➕) - Deep learning at the speed of light. Apache-2

• GitHub (👨‍💻 10 · 🔀 90 · 📦 3 · 📋 50 - 48% open · ⏱️ 04.08.2024):

   git clone https://github.com/jafioti/luminal
  

autograph (🥉13 · ⭐ 310) - A machine learning library for Rust. Apache-2

• GitHub (👨‍💻 4 · 🔀 16 · 📦 2 · ⏱️ 19.08.2024):

   git clone https://github.com/charles-r-earp/autograph
  

instant-distance (🥉11 · ⭐ 310) - Fast approximate nearest neighbor searching in Rust,.. Apache-2

• GitHub (👨‍💻 10 · 🔀 22 · 📦 2 · 📋 7 - 28% open · ⏱️ 04.08.2024):

   git clone https://github.com/InstantDomain/instant-distance
  

kdtree-rs (🥉11 · ⭐ 230 · 💤) - K-dimensional tree in Rust for fast geospatial indexing and.. Apache-2

• GitHub (👨‍💻 16 · 🔀 43 · 📋 19 - 5% open · ⏱️ 02.02.2024):

   git clone https://github.com/mrhooray/kdtree-rs
  

rurel (🥉11 · ⭐ 140) - Flexible, reusable reinforcement learning (Q learning) implementation in.. MPL-2.0

• GitHub (👨‍💻 9 · 🔀 17 · 📦 18 · 📋 11 - 18% open · ⏱️ 25.06.2024):

   git clone https://github.com/milanboers/rurel
  

Show 65 hidden projects...

• rusoto (🥇22 · ⭐ 2.7K · 💀) - AWS SDK for Rust. MIT
• tract (🥈19 · ⭐ 2.2K) - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference. ❗Unlicensed
• pyrus-cramjam (🥈19 · ⭐ 88) - Your go-to for easy access to a plethora of compression algorithms,.. MIT
• evcxr (🥈18 · ⭐ 5.5K) - ❗Unlicensed
• xaynet (🥈18 · ⭐ 200 · 💀) - Xaynet represents an agnostic Federated Machine Learning framework.. Apache-2
• weld (🥈17 · ⭐ 3K · 💀) - High-performance runtime for data analytics applications. BSD-3
• rusty-machine (🥈17 · ⭐ 1.3K · 💀) - Machine Learning library for Rust. MIT
• juice (🥈16 · ⭐ 1.1K) - The Hacker's Machine Learning Engine. ❗Unlicensed
• rustlearn (🥈16 · ⭐ 620 · 💀) - Machine learning crate for Rust. Apache-2
• granne (🥈16 · ⭐ 310 · 💀) - Graph-based Approximate Nearest Neighbor Search. MIT
• gap_statistic (🥈16 · ⭐ 220 · 💀) - Dynamically get the suggested clusters in the data for.. Unlicense
• dfdx (🥈15 · ⭐ 1.7K · 💤) - Deep learning in Rust, with shape checked tensors and neural.. ❗Unlicensed
• onnxruntime-rs (🥈15 · ⭐ 280 · 💀) - Rust wrapper for Microsoft's ONNX Runtime (version.. Apache-2
• leaf (🥈14 · ⭐ 5.6K · 💀) - Open Machine Intelligence Framework for Hackers. (GPU/CPU). Apache-2
• Enzyme (🥈14 · ⭐ 1.3K) - High-performance automatic differentiation of LLVM and MLIR. ❗Unlicensed
• rain (🥈14 · ⭐ 750 · 💀) - Framework for large distributed pipelines. MIT
• cleora (🥈14 · ⭐ 480 · 💀) - Cleora AI is a general-purpose model for efficient, scalable.. ❗Unlicensed
• hnsw (🥈14 · ⭐ 220 · 💀) - HNSW ANN from the paper Efficient and robust approximate nearest neighbor.. MIT
• rsrl (🥈14 · ⭐ 180 · 💀) - A fast, safe and easy to use reinforcement learning framework in Rust. MIT
• hora (🥉13 · ⭐ 2.6K · 💀) - efficient approximate nearest neighbor search algorithm collections.. Apache-2
• NeuroFlow (🥉13 · ⭐ 110 · 💀) - Awesome deep learning crate. MIT
• kodama (🥉13 · ⭐ 91 · 💤) - Fast hierarchical agglomerative clustering in Rust. MIT
• bhtsne (🥉13 · ⭐ 67) - Parallel Barnes-Hut t-SNE implementation written in Rust. MIT
• gym-rs (🥉13 · ⭐ 61 · 💀) - OpenAI Gym bindings for Rust. MIT
• rust-autograd (🥉12 · ⭐ 480 · 💀) - Tensors and differentiable operations (like TensorFlow) in Rust. MIT
• L2 (🥉11 · ⭐ 190 · 💀) - l2 is a fast, Pytorch-style Tensor+Autograd library written in Rust. MIT
• rustml (🥉11 · ⭐ 65 · 💀) - Machine learning in Rust. ❗Unlicensed
• ffsvm-rust (🥉11 · ⭐ 65) - FFSVM stands for Really Fast Support Vector Machine. MIT
• rstats (🥉11 · ⭐ 47) - Statistics, Information Measures, Linear Algebra, Cholesky Matrix.. Apache-2
• black-jack (🥉11 · ⭐ 29 · 💀) - DataFrame / Series data processing in Rust. ❗️GPL-3.0
• petal-clustering (🥉11 · ⭐ 25) - DBSCAN and OPTICS clustering algorithms. Apache-2
• unda (🥉11 · ⭐ 13) - General purpose machine learning crate. Apache-2
• neuronika (🥉10 · ⭐ 1K · 💀) - Tensors and dynamic neural networks in pure Rust. Apache-2
• RustNN (🥉10 · ⭐ 330 · 💀) - A neural network crate. Apache-2
• deeplearn-rs (🥉10 · ⭐ 210 · 💀) - Neural networks in Rust. MIT
• orkhon (🥉10 · ⭐ 150 · 💀) - Orkhon: ML Inference Framework and Server Runtime. MIT
• gamma (🥉10 · ⭐ 120 · 💀) - A graph library for Rust. ❗Unlicensed
• tflite-rs (🥉10 · ⭐ 110) - Apache-2
• rten (🥉10 · ⭐ 110 · ➕) - ONNX neural network inference engine. ❗Unlicensed
• alumina (🥉10 · ⭐ 100 · 💀) - A deep learning library for rust. ❗Unlicensed
• torchrs (🥉10 · ⭐ 77 · 💀) - Deep Learning in Rust with the PyTorch API. BSD-2
• rustdef (🥉10 · ⭐ 28 · 💀) - Jupyter extension for Rust. MIT
• reductive (🥉10 · ⭐ 6 · 💀) - Vector quantization. Apache-2
• hal (🥉9 · ⭐ 90 · 💀) - Rust based Cross-GPU Machine Learning. MIT
• tractjs (🥉9 · ⭐ 75 · 💀) - Run ONNX and TensorFlow inference in the browser. ❗Unlicensed
• ngt-rs (🥉9 · ⭐ 36) - Rust wrappers for NGT approximate nearest neighbor search. Apache-2
• RusticSOM (🥉9 · ⭐ 33 · 💀) - Rust library for Self Organising Maps (SOM). MIT
• batched-fn (🥉9 · ⭐ 18 · 💤) - Rust server plugin for deploying deep learning models with.. Apache-2
• bayespam (🥉9 · ⭐ 13 · 💀) - A simple bayesian spam classifier written in Rust. MIT
• vpsearch (🥉8 · ⭐ 32 · 💀) - C library for finding nearest (most similar) element in a set. ❗Unlicensed
• crfsuite-rs (🥉8 · ⭐ 25 · 💀) - Rust binding to crfsuite. MIT
• cntk-rs (🥉8 · ⭐ 21 · 💀) - Wrapper around Microsoft CNTK library. Apache-2
• liblinear-rs (🥉8 · ⭐ 9 · 💀) - Rust language bindings for the LIBLINEAR C/C++ library. MIT
• mushin (🥉7 · ⭐ 390 · 💀) - Computational graphs with reverse automatic differentation in.. ❗Unlicensed
• fwumious_wabbit (🥉7 · ⭐ 130) - Fwumious Wabbit, fast on-line machine learning toolkit.. ❗Unlicensed
• cogent (🥉7 · ⭐ 44 · 💀) - Simple neural network library for classification written in Rust. ❗Unlicensed
• prophet (🥉7 · ⭐ 39 · 💀) - A simple neural net implementation. ❗Unlicensed
• rust-dl-webserver (🥉7 · ⭐ 33 · 💀) - Example of serving deep learning models in Rust with.. ❗Unlicensed
• revonet (🥉7 · ⭐ 20 · 💀) - Rust implementation of real-coded GA for solving optimization.. ❗️GPL-3.0
• drug (🥉7 · ⭐ 16 · 💀) - Differentiable Rust Graphs (neural network library). MIT
• craftml-rs (🥉7 · ⭐ 15 · 💀) - A Rust implementation of CRAFTML, an Efficient Clustering-based.. MIT
• hwt (🥉7 · ⭐ 7 · 💀) - Hamming Weight Tree from the paper Online Nearest Neighbor Search in Hamming.. MIT
• REnforce (🥉6 · ⭐ 22 · 💀) - Reinforcement learning library written in Rust. ❗Unlicensed
• fann-rs (🥉6 · ⭐ 15 · 💤) - Rust wrapper for the Fast Artificial Neural Network library. ❗️LGPL-3.0
• rust-hf-hub-loader (🥉6 · ⭐ 3 · 💀) - Apache-2

Text Data & NLP

Libraries for processing, cleaning, manipulating, and analyzing text data as well as for diverse NLP tasks.

tiktoken (🥇25 · ⭐ 12K) - tiktoken is a fast BPE tokeniser for use with OpenAI's models. MIT

• GitHub (👨‍💻 17 · 🔀 740 · 📦 96K · 📋 230 - 18% open · ⏱️ 13.05.2024):

   git clone https://github.com/openai/tiktoken
  

tokenizers (🥇25 · ⭐ 8.9K) - Fast State-of-the-Art Tokenizers optimized for Research and.. Apache-2

• GitHub (👨‍💻 93 · 🔀 760 · 📥 65 · 📦 100K · 📋 980 - 3% open · ⏱️ 01.10.2024):

   git clone https://github.com/huggingface/tokenizers
  

aho-corasick (🥇23 · ⭐ 1K) - A fast implementation of Aho-Corasick in Rust. Unlicense

• GitHub (👨‍💻 32 · 🔀 88 · 📦 490K · 📋 67 - 4% open · ⏱️ 25.09.2024):

   git clone https://github.com/BurntSushi/aho-corasick
  

memchr (🥇23 · ⭐ 870) - Optimized string search routines for Rust. Unlicense

• GitHub (👨‍💻 43 · 🔀 97 · 📦 630K · 📋 67 - 8% open · ⏱️ 25.09.2024):

   git clone https://github.com/BurntSushi/memchr
  

ollama-rs (🥇21 · ⭐ 480 · 📈) - A Rust library allowing to interact with the Ollama API. MIT

• GitHub (👨‍💻 26 · 🔀 73 · 📦 220 · 📋 34 - 17% open · ⏱️ 01.10.2024):

   git clone https://github.com/pepperoni21/ollama-rs
  

grex (🥇20 · ⭐ 7.2K) - A command-line tool and Rust library with Python bindings for generating.. Apache-2

• GitHub (👨‍💻 10 · 🔀 170 · 📥 45K · 📦 160 · 📋 53 - 15% open · ⏱️ 01.10.2024):

   git clone https://github.com/pemistahl/grex
  

llama-rs (🥇19 · ⭐ 6.1K) - [Unmaintained, see README] An ecosystem of Rust libraries for.. Apache-2

• GitHub (👨‍💻 53 · 🔀 340 · 📥 1.2K · 📦 320 · 📋 230 - 35% open · ⏱️ 24.06.2024):

   git clone https://github.com/rustformers/llama-rs
  

fancy-regex (🥇19 · ⭐ 420) - Rust library for regular expressions using fancy features like look-.. MIT

• GitHub (👨‍💻 24 · 🔀 37 · 📦 11K · 📋 45 - 31% open · ⏱️ 19.07.2024):

   git clone https://github.com/fancy-regex/fancy-regex
  

lindera (🥇19 · ⭐ 380) - A multilingual morphological analysis library. MIT

• GitHub (👨‍💻 18 · 🔀 37 · 📥 2K · 📦 790 · 📋 84 - 13% open · ⏱️ 01.10.2024):

   git clone https://github.com/lindera-morphology/lindera
  

rust-bert (🥈18 · ⭐ 2.6K) - Rust native ready-to-use NLP pipelines and transformer-based.. Apache-2

• GitHub (👨‍💻 48 · 🔀 210 · 📦 610 · 📋 220 - 26% open · ⏱️ 29.09.2024):

   git clone https://github.com/guillaume-be/rust-bert
  

lingua-rs (🥈17 · ⭐ 880) - The most accurate natural language detection library for Rust,.. Apache-2

• GitHub (👨‍💻 6 · 🔀 40 · 📦 200 · 📋 54 - 20% open · ⏱️ 30.09.2024):

   git clone https://github.com/pemistahl/lingua-rs
  

nnsplit (🥈17 · ⭐ 690) - Toolkit to segment text into sentences or other semantic units in a.. MIT

• GitHub (👨‍💻 9 · 🔀 38 · 📦 47 · 📋 69 - 8% open · ⏱️ 24.09.2024):

   git clone https://github.com/bminixhofer/nnsplit
  

sudachi.rs (🥈17 · ⭐ 310) - Sudachi in Rust and new generation of SudachiPy. Apache-2

• GitHub (👨‍💻 15 · 🔀 32 · 📥 320 · 📦 1.3K · 📋 140 - 18% open · ⏱️ 28.06.2024):

   git clone https://github.com/WorksApplications/sudachi.rs
  

text-splitter (🥈16 · ⭐ 260) - Split text into semantic chunks, up to a desired chunk size... MIT

• GitHub (👨‍💻 6 · 🔀 15 · 📦 150 · 📋 24 - 25% open · ⏱️ 01.10.2024):

   git clone https://github.com/benbrandt/text-splitter
  

aici (🥈15 · ⭐ 1.9K) - AICI: Prompts as (Wasm) Programs. MIT

• GitHub (👨‍💻 10 · 🔀 79 · 📥 420 · 📋 75 - 45% open · ⏱️ 13.08.2024):

   git clone https://github.com/microsoft/aici
  

whatlang-rs (🥈15 · ⭐ 970 · 💤) - Natural language detection library for Rust. Try demo online:.. MIT

• GitHub (👨‍💻 24 · 🔀 54 · 📋 55 - 14% open · ⏱️ 16.03.2024):

   git clone https://github.com/greyblake/whatlang-rs
  

rust-tokenizers (🥈14 · ⭐ 290 · 💤) - Rust-tokenizer offers high-performance tokenizers for.. Apache-2

• GitHub (👨‍💻 8 · 🔀 25 · 📦 600 · 📋 11 - 36% open · ⏱️ 01.10.2023):

   git clone https://github.com/guillaume-be/rust-tokenizers
  

rust-sbert (🥈13 · ⭐ 100) - Rust port of sentence-transformers.. Apache-2

• GitHub (👨‍💻 6 · 🔀 12 · 📦 6 · 📋 5 - 20% open · ⏱️ 17.09.2024):

   git clone https://github.com/cpcdoy/rust-sbert
  

ungoliant (🥈12 · ⭐ 160 · 💤) - The pipeline for the OSCAR corpus. Apache-2

• GitHub (👨‍💻 7 · 🔀 14 · 📦 7 · 📋 43 - 41% open · ⏱️ 09.11.2023):

   git clone https://github.com/oscar-corpus/ungoliant
  

Show 43 hidden projects...

• nlprule (🥈18 · ⭐ 590 · 💀) - A fast, low-resource Natural Language Processing and Text.. Apache-2
• rs-natural (🥈15 · ⭐ 230 · 💀) - Natural Language Processing for Rust. MIT
• snips-nlu-rs (🥈14 · ⭐ 340 · 💀) - Snips NLU rust implementation. ❗Unlicensed
• rust-stemmers (🥈14 · ⭐ 110 · 💀) - A rust implementation of some popular snowball stemming.. MIT
• levenshtein-automata (🥈14 · ⭐ 62 · 💀) - MIT
• rustling (🥈13 · ⭐ 76 · 💀) - Rust implementation of Duckling. ❗Unlicensed
• tokenizations (🥈12 · ⭐ 180 · 💀) - Robust and Fast tokenizations alignment library for Rust and.. MIT
• rustling-ontology (🥈12 · ⭐ 130 · 💀) - Ontology for rustling. ❗Unlicensed
• rust-stop-words (🥈12 · ⭐ 19 · 💤) - Common stop words in a variety of languages. MIT
• spm_precompiled (🥈12 · ⭐ 18 · 💀) - Highly specialized crate to parse and use.. Apache-2
• tokengrams (🥈12 · ⭐ 15 · ➕) - Efficiently computing & storing token n-grams from large corpora. MIT
• srx (🥈12 · ⭐ 7 · 💀) - A mostly compliant Rust implementation of the Segmentation Rules.. Apache-2
• deduplicate-text-datasets (🥉11 · ⭐ 1.1K) - Apache-2
• rustfst (🥉11 · ⭐ 140) - Rust re-implementation of OpenFST - library for constructing,.. ❗Unlicensed
• finalfusion-rust (🥉11 · ⭐ 92 · 💤) - finalfusion embeddings in Rust. ❗Unlicensed
• snips-nlu-ontology (🥉11 · ⭐ 57 · 💀) - Ontology of Snips NLU. ❗Unlicensed
• word2vec (🥉11 · ⭐ 29 · 💀) - Rust interface to word2vec. MIT
• rllama (🥉10 · ⭐ 540 · 💀) - Rust+OpenCL+AVX2 implementation of LLaMA inference code. ❗️AGPL-3.0
• vtext (🥉10 · ⭐ 150 · 💀) - Simple NLP in Rust with Python bindings. Apache-2
• finalfrontier (🥉10 · ⭐ 87 · 💤) - Context-sensitive word embeddings with subwords. In.. ❗Unlicensed
• chr (🥉10 · ⭐ 40 · 💀) - A command-line tool that gives information about Unicode characters. Apache-2
• dpar (🥉9 · ⭐ 43 · 💀) - Neural network transition-based dependency parser (in Rust). Apache-2
• sentencepiece (🥉9 · ⭐ 19 · 💀) - Rust binding for the sentencepiece library. ❗Unlicensed
• rust-tfidf (🥉9 · ⭐ 17 · 💀) - Apache-2
• snips-nlu-parsers (🥉9 · ⭐ 16 · 💀) - Rust crate for entity parsing. ❗Unlicensed
• lumberjack (🥉9 · ⭐ 10 · 💀) - Read and modify constituency trees in Rust. Apache-2
• syntaxdot (🥉8 · ⭐ 71 · 💤) - Neural syntax annotator, supporting sequence labeling,.. ❗Unlicensed
• fasttext-rs (🥉8 · ⭐ 55 · 💀) - fastText Rust binding. ❗Unlicensed
• treebender (🥉8 · ⭐ 43 · 💀) - A HDPSG-inspired symbolic natural language parser written in Rust. MIT
• sticker (🥉8 · ⭐ 25 · 💀) - Succeeded by SyntaxDot: https://github.com/tensordot/syntaxdot. ❗Unlicensed
• deepfrog (🥉8 · ⭐ 19 · 💀) - An NLP-suite powered by deep learning. ❗️GPL-3.0
• awabi (🥉8 · ⭐ 9) - A morphological analyzer using mecab dictionary. MIT
• gazetteer-entity-parser (🥉7 · ⭐ 16) - Rust library for parsing and resolving entity values.. ❗Unlicensed
• alpino-tokenizer (🥉7 · ⭐ 3 · 💤) - Rust wrapper for the Alpino tokenizer. ❗Unlicensed
• seqalign (🥉7 · ⭐ 1 · 💀) - Sequence alignments. Apache-2
• word2vec-rs (🥉6 · ⭐ 78 · 💀) - pure rust implemention of word2vec. ❗Unlicensed
• ollama-rag-rs (🥉6 · ⭐ 13) - Experimenting with LLMs through Ollama and retrieval augmented.. Apache-2
• oxidized-transformers (🥉5 · ⭐ 36) - Modular Rust transformer/LLM library using Candle. ❗Unlicensed
• rsnltk (🥉5 · ⭐ 17 · 💀) - Rust-based Natural Language Toolkit using Python Bindings. ❗Unlicensed
• blingfire-rs (🥉5 · ⭐ 15 · 💀) - Rust wrapper for the BlingFire tokenization library. MIT
• wordpieces (🥉5 · ⭐ 5 · 💀) - Split tokens into word pieces. ❗Unlicensed
• rustberta-snli (🥉4 · ⭐ 12 · 💀) - A Rust implementation of a RoBERTa classification.. ❗Unlicensed
• ohnomore (🥉4 · 💀) - Explorations in lemmatization. ❗Unlicensed

Image Data

Libraries for image & video processing, manipulation, augmentation, and visualization as well as libraries for computer vision.

rerun (🥇23 · ⭐ 6.3K) - Visualize streams of multimodal data. Fast, easy to use, and simple to.. Apache-2

• GitHub (👨‍💻 61 · 🔀 300 · 📥 41K · 📦 75 · 📋 3K - 33% open · ⏱️ 02.10.2024):

   git clone https://github.com/rerun-io/rerun
  

imageproc (🥈20 · ⭐ 740) - Image processing operations. MIT

• GitHub (👨‍💻 78 · 🔀 140 · 📦 5K · 📋 230 - 25% open · ⏱️ 19.09.2024):

   git clone https://github.com/image-rs/imageproc
  

opencv-rust (🥈17 · ⭐ 2K · 📉) - Rust bindings for OpenCV 3 & 4. MIT

• GitHub (👨‍💻 51 · 🔀 150 · 📋 520 - 4% open · ⏱️ 30.09.2024):

   git clone https://github.com/twistedfall/opencv-rust
  

kornia-rs (🥉15 · ⭐ 170) - Low-level Computer Vision library in Rust. Apache-2

• GitHub (👨‍💻 8 · 🔀 15 · 📦 12 · 📋 52 - 46% open · ⏱️ 30.09.2024):

   git clone https://github.com/kornia/kornia-rs
  

Show 8 hidden projects...

• cgmath (🥇22 · ⭐ 1.1K · 💀) - A linear algebra and mathematics library for computer graphics. Apache-2
• texture-synthesis (🥈17 · ⭐ 1.8K · 💀) - Example-based texture synthesis written in Rust. Apache-2
• rustface (🥉16 · ⭐ 390) - Face detection library for the Rust programming language. ❗Unlicensed
• rust-cv-convert (🥉13 · ⭐ 43 · 💤) - Type conversion among popular Rust computer vision libraries. MIT
• cv (🥉11 · ⭐ 830 · 💀) - Rust CV mono-repo. Contains pure-Rust dependencies which attempt to.. ❗Unlicensed
• visionmagic (🥉9 · ⭐ 57 · 💤) - Collection of vision & graphics algorithms. ❗Unlicensed
• visual-odometry-rs (🥉9 · ⭐ 53 · 💀) - Visual Odometry in Rust (vors). MPL-2.0
• image-ssd (🥉6 · ⭐ 5 · 💀) - A Rust library for object detection via SSD MobileNet. MIT

Data Loading & Extraction

Libraries for loading, collecting, and extracting data from a variety of data sources and formats.

vector (🥇28 · ⭐ 18K) - A high-performance observability data pipeline. MPL-2.0

• GitHub (👨‍💻 450 · 🔀 1.5K · 📥 2.1M · 📋 7.6K - 23% open · ⏱️ 01.10.2024):

   git clone https://github.com/timberio/vector
  

rayon (🥇24 · ⭐ 11K) - Rayon: A data parallelism library for Rust. Apache-2

• GitHub (👨‍💻 150 · 🔀 480 · 📦 240K · 📋 570 - 31% open · ⏱️ 19.08.2024):

   git clone https://github.com/rayon-rs/rayon
  

arrow-rs (🥇24 · ⭐ 2.5K) - Official Rust implementation of Apache Arrow. Apache-2

• GitHub (👨‍💻 600 · 🔀 730 · 📦 6.9K · 📋 2.7K - 13% open · ⏱️ 02.10.2024):

   git clone https://github.com/apache/arrow-rs
  

rust-csv (🥇24 · ⭐ 1.7K) - A CSV parser for Rust, with Serde support. Unlicense

• GitHub (👨‍💻 53 · 🔀 220 · 📦 83K · 📋 230 - 24% open · ⏱️ 25.09.2024):

   git clone https://github.com/BurntSushi/rust-csv
  

redb (🥈23 · ⭐ 3.2K · 📈) - An embedded key-value database in pure Rust. Apache-2

• GitHub (👨‍💻 23 · 🔀 140 · 📦 650 · 📋 300 - 2% open · ⏱️ 01.10.2024):

   git clone https://github.com/cberner/redb
  

arrow (🥈22 · ⭐ 14K) - Apache Arrow is a multi-language toolbox for accelerated data.. Apache-2

• GitHub (👨‍💻 1.3K · 🔀 3.4K · 📥 410 · 📦 8 · 📋 26K - 17% open · ⏱️ 02.10.2024):

   git clone https://github.com/apache/arrow
  

lance (🥈22 · ⭐ 3.8K) - Modern columnar data format for ML and LLMs implemented in Rust... Apache-2

• GitHub (👨‍💻 70 · 🔀 210 · 📦 2.8K · 📋 980 - 42% open · ⏱️ 01.10.2024):

   git clone https://github.com/eto-ai/lance
  

synth (🥈22 · ⭐ 1.4K) - The Declarative Data Generator. Apache-2

• GitHub (👨‍💻 32 · 🔀 110 · 📥 13K · 📦 110 · 📋 160 - 50% open · ⏱️ 27.09.2024):

   git clone https://github.com/openquery-io/synth
  

arrow-datafusion (🥉21 · ⭐ 6K) - Apache DataFusion SQL Query Engine. Apache-2

• GitHub (👨‍💻 690 · 🔀 1.1K · 📦 2.7K · 📋 5.1K - 21% open · ⏱️ 02.10.2024):

   git clone https://github.com/apache/arrow-datafusion
  

delta-rs (🥉21 · ⭐ 2.2K) - A native Rust library for Delta Lake, with bindings into Python. Apache-2

• GitHub (👨‍💻 190 · 🔀 390 · 📦 400 · 📋 1.1K - 18% open · ⏱️ 30.09.2024):

   git clone https://github.com/delta-io/delta-rs
  

fst (🥉21 · ⭐ 1.8K) - Represent large sets and maps compactly with finite state transducers. Unlicense

• GitHub (👨‍💻 25 · 🔀 110 · 📦 11K · 📋 88 - 29% open · ⏱️ 25.09.2024):

   git clone https://github.com/BurntSushi/fst
  

arroyo (🥉19 · ⭐ 3.7K) - Distributed stream processing engine in Rust. Apache-2

• GitHub (👨‍💻 22 · 🔀 200 · 📥 350 · 📋 140 - 36% open · ⏱️ 01.10.2024):

   git clone https://github.com/ArroyoSystems/arroyo
  

kafka-delta-ingest (🥉11 · ⭐ 360) - A highly efficient daemon for streaming data from Kafka.. Apache-2

• GitHub (👨‍💻 17 · 🔀 77 · 📋 65 - 40% open · ⏱️ 18.09.2024):

   git clone https://github.com/delta-io/kafka-delta-ingest
  

Show 8 hidden projects...

• polars (🥇24 · ⭐ 30K · 📈) - Dataframes powered by a multithreaded, vectorized query.. ❗Unlicensed
• datafuse (🥉18 · ⭐ 7.7K) - , & . Modern alternative to Snowflake. Cost-effective and.. ❗Unlicensed
• datafrog (🥉17 · ⭐ 800 · 💀) - A lightweight Datalog engine in Rust. Apache-2
• rust-tfrecord (🥉12 · ⭐ 25 · 💀) - A Rust crate that reads and writes tfrecord files. MIT
• rust-dataframe (🥉11 · ⭐ 280 · 💀) - A Rust DataFrame implementation, built on Apache Arrow. Apache-2
• tch-serde (🥉9 · ⭐ 4 · 💀) - Serialize/Deserialize tch-rs types with serde. MIT
• flaco (🥉8 · ⭐ 15 · 💀) - (PoC) A very memory-efficient way to read data from PostgreSQL. Unlicense
• NewsAggregator (🥉7 · ⭐ 10 · 💀) - A fast, searchable, knowledge engine using various machine.. Apache-2

Graph Data

Libraries for graph processing, clustering, embedding, and machine learning tasks.

petgraph (🥇25 · ⭐ 2.9K) - Graph data structure library for Rust. Apache-2

• GitHub (👨‍💻 110 · 🔀 330 · 📦 120K · 📋 310 - 50% open · ⏱️ 08.05.2024):

   git clone https://github.com/petgraph/petgraph
  

Raphtory (🥈19 · ⭐ 340) - Scalable graph analytics database powered by a multithreaded,.. ❗️GPL-3.0

• GitHub (👨‍💻 30 · 🔀 54 · 📥 340 · 📦 14 · 📋 500 - 21% open · ⏱️ 02.10.2024):

   git clone https://github.com/Pometry/Raphtory
  

graph-rs (🥈18 · ⭐ 110) - Microsoft Graph API Client And Identity Platform Client in Rust. MIT

• GitHub (👨‍💻 16 · 🔀 29 · 📦 57 · 📋 270 - 6% open · ⏱️ 09.09.2024):

   git clone https://github.com/sreeise/graph-rs
  

GraphScope (🥉17 · ⭐ 3.3K) - GraphScope: A One-Stop Large-Scale Graph Computing System from.. Apache-2

• GitHub (👨‍💻 67 · 🔀 400 · 📥 200 · 📋 1.6K - 24% open · ⏱️ 30.09.2024):

   git clone https://github.com/alibaba/GraphScope
  

Show 2 hidden projects...

• graphlib (🥉16 · ⭐ 190 · 💀) - Simple but powerful graph library for Rust. MIT
• propagon (🥉4 · ⭐ 8 · 💀) - Fast, large scale library for computing rankings and features.. ❗Unlicensed

Model Interpretability

Libraries to visualize, explain, debug, evaluate, and interpret machine learning models.

Show 1 hidden projects...

• eval-metrics (🥇8 · ⭐ 12 · 💀) - Evaluation metrics for machine learning. ❗Unlicensed

MLOps

Libraries to design workflows, deploy, test, and maintain machine learning pipelines.

mosec (🥇17 · ⭐ 750) - A high-performance ML model serving framework, offers dynamic batching.. Apache-2

• GitHub (👨‍💻 12 · 🔀 51 · 📦 50 · 📋 98 - 13% open · ⏱️ 28.09.2024):

   git clone https://github.com/mosecorg/mosec
  

Show 2 hidden projects...

• TensorZero (🥉9 · ⭐ 140 · 🐣) - data & learning flywheel for LLM systems. Apache-2
• h2o-kubernetes (🥉8 · ⭐ 21 · 💀) - H2O Open Source Kubernetes operator and a command-line.. Apache-2

Applications

ML, NLP, or relevant applications.

qdrant (🥇28 · ⭐ 20K · 📈) - Qdrant - High-performance, massive-scale Vector Database for the.. Apache-2

• GitHub (👨‍💻 120 · 🔀 1.3K · 📥 170K · 📦 110 · 📋 1.2K - 19% open · ⏱️ 23.09.2024):

   git clone https://github.com/qdrant/qdrant
  

MeiliSearch (🥇24 · ⭐ 47K) - A lightning-fast search API that fits effortlessly into your apps,.. MIT

• GitHub (👨‍💻 190 · 🔀 1.8K · 📥 210K · 📋 2K - 7% open · ⏱️ 30.09.2024):

   git clone https://github.com/meilisearch/MeiliSearch
  

tantivy (🥇23 · ⭐ 12K) - Tantivy is a full-text search engine library inspired by Apache Lucene and.. MIT

• GitHub (👨‍💻 150 · 🔀 640 · 📦 1.6K · 📋 1K - 27% open · ⏱️ 25.09.2024):

   git clone https://github.com/tantivy-search/tantivy
  

sonic (🥈22 · ⭐ 20K) - Fast, lightweight & schema-less search backend. An alternative to.. MPL-2.0

• GitHub (👨‍💻 44 · 🔀 560 · 📥 410 · 📦 21 · 📋 260 - 23% open · ⏱️ 22.07.2024):

   git clone https://github.com/valeriansaliou/sonic
  

bloop (🥈20 · ⭐ 9.4K) - bloop is a fast code search engine written in Rust. Apache-2

• GitHub (👨‍💻 28 · 🔀 570 · 📥 53K · 📋 140 - 29% open · ⏱️ 12.06.2024):

   git clone https://github.com/BloopAI/bloop
  

LlamaEdge (🥈20 · ⭐ 1K) - The easiest & fastest way to run customized and fine-tuned LLMs.. Apache-2

• GitHub (👨‍💻 9 · 🔀 85 · 📥 250K · 📦 20 · 📋 97 - 4% open · ⏱️ 01.10.2024):

   git clone https://github.com/LlamaEdge/LlamaEdge
  

screenpipe (🥈17 · ⭐ 5.3K · 🐣) - 24/7 local AI screen & mic recording. Build AI apps that have the.. MIT

• GitHub (👨‍💻 20 · 🔀 280 · 📥 1.6K · 📋 180 - 29% open · ⏱️ 02.10.2024):

   git clone https://github.com/mediar-ai/screenpipe
  

RustQuant (🥈17 · ⭐ 1.1K · ➕) - Rust library for quantitative finance. Apache-2

• GitHub (👨‍💻 40 · 🔀 120 · 📦 18 · 📋 120 - 22% open · ⏱️ 01.10.2024):

   git clone https://github.com/avhz/RustQuant
  

weggli (🥉16 · ⭐ 2.3K · 💤) - weggli is a fast and robust semantic search tool for C and C++.. Apache-2

• GitHub (👨‍💻 10 · 🔀 130 · 📦 86 · 📋 65 - 56% open · ⏱️ 16.01.2024):

   git clone https://github.com/googleprojectzero/weggli
  

lsp-ai (🥉16 · ⭐ 2.1K · ➕) - LSP-AI is an open-source language server that serves as a backend for.. MIT

• GitHub (👨‍💻 8 · 🔀 72 · 📥 160 · 📋 45 - 33% open · ⏱️ 25.09.2024):

   git clone https://github.com/SilasMarvin/lsp-ai
  

lnx (🥉15 · ⭐ 1.2K) - Insanely fast, Feature-rich searching. lnx is the adaptable, typo tollerant.. MIT

• GitHub (👨‍💻 9 · 🔀 46 · 📋 78 - 46% open · ⏱️ 15.07.2024):

   git clone https://github.com/lnx-search/lnx
  

Toshi (🥉13 · ⭐ 4.2K · 💤) - A full-text search engine in rust. MIT

• GitHub (👨‍💻 19 · 🔀 130 · 📋 120 - 11% open · ⏱️ 12.10.2023):

   git clone https://github.com/toshi-search/Toshi
  

Show 12 hidden projects...

• ChatGPT (🥈21 · ⭐ 52K) - ChatGPT Desktop Application (Mac, Windows and Linux). ❗Unlicensed
• zombodb (🥈18 · ⭐ 4.7K) - Making Postgres and Elasticsearch work together like it's 2023. ❗Unlicensed
• chat-ai-desktop (🥈18 · ⭐ 2K · 💀) - Unofficial ChatGPT desktop app for Mac & Windows menubar.. MIT
• quickwit (🥈17 · ⭐ 8K) - Cloud-native search engine for observability. An open-source.. ❗Unlicensed
• milli (🥈17 · ⭐ 460 · 💀) - Search engine library for Meilisearch. MIT
• bayard (🥉15 · ⭐ 1.9K · 💀) - A full-text search and indexing server written in Rust. MIT
• erdos (🥉15 · ⭐ 200 · 💀) - Dataflow system for building self-driving car and robotics.. Apache-2
• hora-hora (🥉13 · ⭐ 2.6K · 💀) - efficient approximate nearest neighbor search algorithm.. Apache-2
• nerve (🥉11 · ⭐ 480 · 🐣) - Instrument any LLM to do actual stuff. ❗Unlicensed
• voy (🥉9 · ⭐ 870 · 💀) - A WASM vector similarity search written in Rust. Apache-2
• opentau (🥉8 · ⭐ 95 · 💤) - Using Large Language Models for Repo-wide Type Prediction. Apache-2
• llamacord (🥉7 · ⭐ 91 · 💀) - A Discord bot, written in Rust, that generates responses using.. ❗️GPL-3.0

Analysis

Libraries for analyzing data.

Show 1 hidden projects...

• vega (🥇16 · ⭐ 2.2K · 💀) - A new arguably faster implementation of Apache Spark from scratch in.. Apache-2

Other

Other libraries useful for ML.

Show 2 hidden projects...

• Rust-CUDA (🥇17 · ⭐ 3.1K · 💀) - Ecosystem of libraries and tools for writing and executing.. Apache-2
• zkml (🥉8 · ⭐ 340 · 💀) - Apache-2

Others

Oxen (🥇15 · ⭐ 180) - Oxen.ai's core rust library, server, and CLI. Apache-2

• GitHub (👨‍💻 16 · 🔀 11 · 📥 7.6K · 📦 1 · 📋 31 - 38% open · ⏱️ 01.10.2024):

   git clone https://github.com/Oxen-AI/Oxen
  

sail (🥉10 · ⭐ 340 · ➕) - LakeSail's computation framework with a mission to unify stream.. Apache-2

• GitHub (👨‍💻 4 · 🔀 9 · 📋 27 - 77% open · ⏱️ 02.10.2024):

   git clone https://github.com/lakehq/sail
  

Show 1 hidden projects...

• extractous (🥉7 · ⭐ 55 · 🐣) - Fast and efficient unstructured data extraction. Written in.. Apache-2

---

Related Resources

• Awesome-Rust-MachineLearning: This repository is a list of machine learning libraries written in Rust.
• best-of-ml-python: A ranked list of awesome machine learning Python libraries.
• best-of-ml-julia: A ranked list of awesome machine learning Julia libraries.

Contribution

Contributions are encouraged and always welcome! If you like to add or update projects, choose one of the following ways:

• Open an issue by selecting one of the provided categories from the issue page and fill in the requested information.
• Modify the projects.yaml with your additions or changes, and submit a pull request. This can also be done directly via the Github UI.

If you like to contribute to or share suggestions regarding the project metadata collection or markdown generation, please refer to the best-of-generator repository. If you like to create your own best-of list, we recommend to follow this guide.

For more information on how to add or update projects, please read the contribution guidelines. By participating in this project, you agree to abide by its Code of Conduct.

License