Tensorflow.js tasks API
test
Using this library you can detect objects from a video, images, with few lines of code
Object detection using ORT and the yoloe-26-seg model. This model can detect multiple objects per image, each having a tag, pixel-level mask, and a boundingbox. It's pretrained, it has a vocabulary of 4000+ objects.
Real-time object detection node using YOLO and ONNX
Object tracking library - Rust port of Python norfair
YOLO object detection wrapper for OpenCV and ONNX in Rust
Natural language command parsing via LLM APIs (OpenAI, Claude, Ollama)
Sovereign ML pipelines for media — Pure-Rust ONNX inference with typed pipelines (scene classification, shot boundary detection, aesthetic scoring, object detection, face embedding) built atop OxiONNX.
Computer vision utilities for the Axonml ML framework
Safety-critical cognitive safety library for AI agents. 4-tier architecture (Resource Body, Kernel, Working Memory, Sifter) with formal verification primitives, detection layer, and integration primitives.
A unified, high-performance computer vision tracking library.
AXON — the formal cognitive language: a deterministic, proof-carrying AI runtime. Native Rust lexer/parser/type-checker/IR generator (re-exported from axon-frontend) plus the runtime: typed channels (π-calculus mobility, capability extrusion), algebraic effects via Free Monad CPS handlers, lease kernel + reconcile loop, the Epistemic Security Kernel, Trust Types, Proof-Carrying Code (independently verifiable proof objects), and the closed-catalog extension mechanism. Crate publishes as `axon-lang`; library import is `use axon::*` so existing call sites keep working unchanged.
A from-scratch deep learning library in Rust — tensors, autograd, NEON SIMD, Metal GPU, and working models
Multi-object tracking using Labeled Multi-Bernoulli filters - Rust port of multisensor-lmb-filters
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.