* [Netron v9.3.0](https://github.com/lutzroeder/netron) – Viewer for neural network, deep learning, and machine learning models.

* [Apache TVM v0.27.0](https://github.com/apache/tvm) – Python-first machine learning compilation framework that generates minimum deployable modules and supports universal deployment across targets.

* [KnowNote v1.3.0](https://github.com/mrsibe/KnowNote) – Local-first Electron desktop app that builds a conversational knowledge base from documents with provider-based LLM chat and RAG retrieval plus source traceability.

* [Cog v0.23.0](https://github.com/replicate/cog) – Tool for packaging machine learning models in production-ready containers.

* [pg\_onnx v1.31.0](https://github.com/kibae/pg_onnx) – ONNX Runtime integration enabling machine learning inference within PostgreSQL databases.

* [Crater v1.3.0](https://github.com/raids-lab/crater) – Cloud-native Kubernetes platform for AI training and inference with GPU resource management, containerized development environments, and workflow orchestration.

* [FiftyOne v1.22.1](https://github.com/voxel51/fiftyone) – FiftyOne is a tool for visualizing and labeling datasets, evaluating computer vision models, and improving data and model quality.

* [Label Studio 1.23.2](https://github.com/HumanSignal/label-studio) – Multi-type data labeling and annotation tool with a straightforward UI.

* [WebLLM v0.2.86](https://github.com/mlc-ai/web-llm) – High-performance in-browser LLM inference engine using WebGPU for hardware-accelerated, serverless model inference.

* [go-tflite v1.0.10](https://github.com/mattn/go-tflite) – Go binding for TensorFlow Lite, providing model loading, interpreter setup, and tensor input/output access with optional Edge TPU support.

* [RAGFlow v1.0.0-rc1](https://github.com/infiniflow/ragflow) – RAG engine combining large language models with document understanding for accurate question answering and citation.

* [tensai v0.0.35](https://github.com/mattn/tensai) – Tiny machine-learning framework for Go, implementing forward passes, backpropagation, and optimization with optional SIMD and WebGPU acceleration.

* [Born v0.9.24](https://github.com/born-ml/born) – Production-ready ML framework for Go with zero dependencies, type-safe tensors, automatic differentiation, and single-binary deployment.