Directory
Published directory entries matching your search.
libonnx is a lightweight, portable pure C99 ONNX inference engine for embedded devices with hardware acceleration support. Its .c and .h files can be dropped into a project and compiled with it. Models are loaded from a file into a context, and inference runs on input tensors via onnx_run. It is based on ONNX version v1.17.0 with opset 24 support, and some operators are not implemented.
Collection of infrastructure and tools for research in neural network interpretability.
Mem0 is a drop-in memory infrastructure tool for AI agents and applications. It provides persistent context for AI systems, is built for production use, and is available as a public repository on GitHub.
MLEM is an open source tool designed to package, serve, and deploy machine learning models on any platform. The project's primary repository is currently archived, with maintainers noting plans to resurrect it in the future.
MLReef is an open source ML-Ops platform for collaborating, reproducing and sharing machine learning work. The repository notes it is no longer supported or updated there, with work continuing on GitLab. Described sections include data management with versioned data hosting, containerized code repositories, experiment tracking and ML pipelines on Kubernetes, cloud or bare metal.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Machine learning model serving framework with dynamic batching and pipelined stages, provides an easy-to-use Python interface.
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.
NCNN is a neural network inference framework optimized for mobile, embedded, and desktop deployment. It has no third-party runtime dependencies and runs across CPU and Vulkan GPU backends. Tools such as pnnx convert PyTorch and ONNX models to ncnn, allowing deployment to phones, PCs, browsers, and edge devices. The project is used in several Tencent applications.
NDScala is a Scala 3 library for N-dimensional and multi-dimensional arrays (tensors), described as comparable to NumPy ndarray or PyTorch Tensor, with type safety over shapes, array and axis labels and numeric data types. The repository includes materials on shape-safe neural network training and an ONNXScala component.
Easy-to-use library to boost AI inference.
Neuraxle is an AutoML library that supports hyperparameter tuning via pipeline abstractions to build clean deep learning production pipelines. Pipeline steps can have associated hyperparameter spaces, and the library is compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks, and MLOps environments.
An Easy-to-Use and High-Performance AI deployment framework.
Nos is an open-source module for running AI workloads on Kubernetes, intended to increase GPU utilization, cut infrastructure costs and improve workload performance. It provides dynamic GPU partitioning and elastic resource quota management.
Neural networks framework in pure C: training and inference, no dependencies.
onWatch is an open-source tool developed by onllm-dev that tracks AI API quotas for services including Synthetic, Z.ai, Anthropic Claude Code, Codex, GitHub Copilot and Antigravity in real time. It functions as a lightweight background daemon that uses less than 50MB of RAM, stores data in SQLite, and provides a Material Design 3 dashboard. The tool does not collect telemetry.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
OpenLIT is an open-source agent harness engineering platform built on OpenTelemetry. It provides tracing, evaluations, guardrails, prompt and context management, and cost and GPU monitoring for the harness around AI agents and coding agents. It is free to self-host under Apache 2.0 and is described as working with many models, frameworks and harnesses.
Turns your ML code into microservices with web API, interactive GUI, and more.
Parris, the automated infrastructure setup tool for machine learning algorithms.
pgvecto.rs is an open-source tool that provides scalable, low-latency, hybrid-enabled vector search for PostgreSQL. It is designed to enhance vector search capabilities without modifying the core database system, per its official GitHub repository.
Open-source vector similarity search for Postgres.
pyhsmm is a Python library for approximate unsupervised inference in Bayesian Hidden Markov Models and explicit-duration Hidden semi-Markov Models, focusing on the HDP-HMM and HDP-HSMM with weak-limit approximations. Extensions include autoregressive models, switching linear dynamical systems and factorial models. The package is stated as no longer maintained and was last tested with Python 3.7.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
