Directory
Published directory entries matching your search.
NASGym is a proof-of-concept OpenAI Gym environment for Neural Architecture Search. It implements reinforcement learning steps for NAS and encodes networks using the Neural Structure Code from BlockQNN. A network is modeled as a list of NSCs, an action adds a layer, and the reward is accuracy after early-stop training. CIFAR-10 is the default dataset. The code and documentation may contain minor bugs.
NNI is an open source AutoML toolkit developed by Microsoft. It automates tasks across the machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning for machine learning workflows.
open-gpu-kernel-modules is the open source repository for NVIDIA's Linux GPU kernel modules. It provides the module source code, alongside documentation covering build instructions, supported CPU architectures, compatible toolchains, and build configuration options.
Oryx 2 is a realization of the lambda architecture built on Apache Spark and Apache Kafka, specialized for real-time large scale machine learning. It is a framework for building applications and includes packaged end-to-end applications for collaborative filtering, classification, regression and clustering. The repository was archived by the owner on May 3, 2022, and is read-only.
Ouroboros is an open-source, general-purpose AI agent whose identity, durable memory, and history continue across tasks and restarts. It coordinates a live swarm of specialist agents, works on external projects, and can rewrite its own code, architecture, prompts, tools, and dependencies. It runs as a native desktop app or a headless CLI, keeping its repository, memory, and history on the local machine.
redroid is a multi-architecture GPU-accelerated Android in Cloud solution that boots Android instances on Linux hosts including Docker, podman and k8s. It supports arm64 and amd64 and is intended for cloud gaming, virtualized phones and automation testing. Android images from 8.1 through 16 are available.
Semantic Cache Router is a distributed semantic cache and stateful routing system hosted on GitHub. It includes documentation covering the problem it addresses, its solutions, key strengths, and system architecture.
Swarms is a Python framework for building multi-agent systems, described as an enterprise-grade multi-agent orchestration framework. It provides harnesses for sequential, concurrent and hierarchical architectures, and is installed via pip, uv or Docker.
SwarmVault is a local-first tool that turns documents, code, transcripts, notes and URLs into a markdown wiki and a local knowledge graph for AI agents. It follows a three-layer architecture based on a pattern described by Andrej Karpathy. A first run requires no API keys, using a built-in heuristic provider that runs locally and offline.
timm is a collection of PyTorch image encoders and backbones, including train, eval, inference and export scripts with pretrained weights. It covers architectures such as ResNet, EfficientNet, Vision Transformer, MobileNet and ConvNeXt.
torchvision is a package of popular datasets, model architectures and common image transformations for computer vision. The repository holds documentation, benchmarks, examples, packaging, references and tests alongside the torchvision code. Installation instructions point to official guidance for stable torch and torchvision versions; building from source is covered on the contributing page.
Creates or edits images with generative models and visual controls.
Vega is an AutoML algorithm tool chain developed by Noah's Ark Laboratory. It covers hyperparameter optimization, data augmentation, network architecture search, model compression and fully train functions, and supports PyTorch, TensorFlow and MindSpore backends.
Zetane Viewer is a free tool for visualizing machine learning and artificial neural network models, including architecture and internal data such as feature maps, weights, biases and layer output tensors. The viewer supports .ONNX and .ZTN files and is available for Windows, Linux and Mac. It can also be launched from existing scripts or notebooks via the Zetane Python API.
