Find a Rust library or app for your ML job

What do you want to do?

• Run and serve models 87 projects ort, candle
• Build LLM apps and agents 150 projects rmcp, async-openai
• Train models 51 projects candle, tch-rs
• Speech and audio 41 projects whisper-rs, sherpa-onnx
• Text, embeddings and search 138 projects tokenizers, tiktoken-rs
• Images and vision 20 projects imageproc, opencv-rust
• Video 3 projects containr, rav1r
• Documents and OCR 16 projects pdf_oxide, ocrs
• Tabular data and classic ML 36 projects linfa, smartcore
• Math and science 28 projects ndarray, nalgebra
• Tensors and GPU compute 19 projects candle, cubecl
• Datasets and model formats 37 projects arrow-rs, safetensors

Or pick the kind of project

• Speech and audio 38 projects
• Computer vision 25 projects
• Inference runtimes 51 projects
• LLM clients 40 projects
• Agents and LLM apps 59 projects
• Vector databases 39 projects
• Embeddings 11 projects
• Search engines 20 projects
• Text and tokenizers 68 projects
• Model formats 7 projects
• Data formats and dataframes 25 projects
• Classical ML 40 projects
• ML frameworks 45 projects
• Tensors and math 32 projects
• Developer tools 19 projects

• numr

  The base for numerical code in Rust, in the role NumPy has in Python: n-dimensional tensors, linear algebra, FFT, statistics and autograd on CPU, CUDA and WebGPU. The backends use native kernels, with no cuBLAS, MKL or other vendor math library.

• boostr

  ML framework on numr for training and inference on CPU, CUDA and WebGPU: attention, quantization, inference scheduling and distributed execution. Models include LLaMA, Mamba2, Qwen3.5, Whisper, Kokoro, VITS, VoxCPM2, Silero VAD, CLAP and super-resolution. Loads SafeTensors and GGUF.

• oxidizr

  Trains GPT-style language models from a YAML config and a tokenized dataset: dense GQA transformers, Mamba 1, 2 and 3, MLA and MoE layers on CPU or CUDA. Runs the training loop, optimizer, checkpoints, evaluation and metrics on boostr, and builds speech corpora through voxr.

• blazr

  Inference server for LLMs, speech and embeddings: OpenAI-compatible routes with streaming, plus speech synthesis (TTS) and transcription (ASR). Serves Llama, Mistral, Qwen, Mamba2, MLA+MoE and hybrid models from SafeTensors, AWQ, GPTQ and GGUF.

• voxr

  Audio and speech on boostr: compressed-audio decode, resampling, DSP and grapheme to phoneme, with speech synthesis (Kokoro, VITS), voice cloning (VoxCPM2), transcription with word timings (Whisper), voice activity (Silero) and audio-text scoring (CLAP), on CPU or CUDA.

• splintr

  Tokenizer for Rust and Python: pure Rust by default, with 18 bundled vocabularies and four backends covering BPE, SentencePiece and WordPiece. Its output matches Hugging Face tokenizers id for id on 14 model families, including GPT-2, Qwen, Whisper, T5 and BERT.

• compressr

  Model conversion and quantization with no Python: reads SafeTensors, GGUF, TCF and PyTorch state dicts, writes SafeTensors, GGUF and TCF, and quantizes to Q2_K through Q8_0 and IQ4 formats, including Q4_K_M mixes. GPTQ, AWQ, NF4, FP8, EXL2 and ONNX input are not implemented.

• treeboost

  Gradient-boosted decision trees for tabular data: trains a baseline model in one call, with full control over boosting modes and configs, and Scalar, AVX-512, SVE2, WGPU and CUDA backends.

All 16 projects from ML Rust

All 86 Featured projects