tract and microflow-rs

Both are TinyML inference engines supporting ONNX, making them competitors for resource-constrained embedded systems and other tinyML applications.

tract
70
Verified
microflow-rs
43
Emerging
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 19/25
Maintenance 0/25
Adoption 13/25
Maturity 16/25
Community 14/25
Stars: 2,818
Forks: 250
Downloads:
Commits (30d): 323
Language: Rust
License:
Stars: 171
Forks: 17
Downloads: 21
Commits (30d): 0
Language: Rust
License: Apache-2.0
No Package No Dependents
Stale 6m No Package No Dependents

About tract

sonos/tract

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Implements graph-level optimization passes (constant folding, operator fusion, quantization-aware transformations) and supports symbolic dimensions for dynamic shapes, enabling efficient inference on resource-constrained embedded systems. Built in Rust with zero external dependencies, it provides both a standalone CLI and language bindings (Python, C) for framework integration. Handles ONNX (85%+ operator coverage), TensorFlow 1.x, and NNEF formats with a production-focused subset philosophy that excludes rarely-used features like tensor sequences in favor of maintainability and performance.

About microflow-rs

matteocarnelos/microflow-rs

A robust and efficient TinyML inference engine.

Scores updated daily from GitHub, PyPI, and npm data. How scores work