An embeddable, in-memory document database written in C++ and Go that provides a high-performance alternative to Elasticsearch with support for vector and full-text search.

A machine learning tool that automatically ranks strings extracted from binaries to help malware analysts quickly identify the most relevant information.

A framework for the Cline VS Code extension that manages large-scale project context and dependencies using a recursive, file-based tracking system and local LLM-assisted analysis.

An official observability plugin for OpenClaw that exports agent traces, tool calls, and LLM usage to the Opik platform for monitoring and evaluation.

A unified toolkit for training and deploying billion-scale neural retrievers across different languages and modalities using LLMs.

A tool that converts Jupyter Notebooks into production-ready Kubeflow Pipelines by tagging cells, removing the need to rewrite code using the KFP SDK.

A PyTorch-native agentic RL library that separates infrastructure concerns from model concerns to simplify scalable reinforcement learning experimentation.

A Laravel package that automatically transforms Eloquent models into both JSON:API endpoints and MCP servers for AI agents from a single codebase.

A local, file-backed, in-memory vector database that supports metadata filtering, cosine similarity, and local or API-based embeddings.

An efficient PyTorch library for differentiable optimization that supports explicit, implicit, and zero-order differentiation for bi-level optimization and meta-learning.

A collection of installers that bundle 254 deep learning and machine learning libraries for use within ArcGIS Pro and Server to solve geospatial AI problems.

A Helm chart that deploys the Ollama LLM server on Kubernetes, supporting CPU or GPU, model pre‑pull, custom model builds, Ingress/Gateway‑API, autoscaling, and optional Knative Service.

OSCAR is a 2-bit KV cache quantization method that uses offline spectral covariance-aware rotations to reduce memory usage by 8x while maintaining near-BF16 accuracy.

A GitHub Action that enables running AI inference via the GitHub Copilot CLI within automated workflows.

A self-attention-based framework for multivariate time series imputation that solves the speed and memory issues of RNN-based models.

A PyTorch-based module for implementing and testing Echo State Networks and Reservoir Computing, designed for research purposes and integration into deep architectures.

A Clojure library for fast tensor and neural network computations that leverages optimized native libraries for CPU and GPU acceleration.

A collection of GPU-accelerated machine learning solvers that act as a drop-in replacement for scikit-learn, providing Python and R APIs for faster model training.

A C/C++ library that extends ONNX Runtime with custom operators to handle pre- and post-processing for vision, text, and NLP models within the ONNX graph.

A toolchain for deploying optimized AI algorithms on low-cost embedded devices and microcontrollers, supporting computer vision, anomaly detection, and scenario-specific tasks.

A lightweight, pure-Python local version of the Milvus vector database designed for development, testing, and small-scale AI applications.

A modern C# framework for building reactive full-stack web applications in pure C#, eliminating the need for HTML, CSS, and JavaScript.

An MCP server that connects Claude Desktop to SQL databases, enabling natural language exploration, schema analysis, and query execution.

AtomicMemory is an open‑source, inspection‑ready memory service for LLM agents. It offers correction‑aware updates, model‑agnostic embeddings, and both managed‑cloud and self‑hosted Docker deployments. The project ships a Rust Core server, a TypeScript SDK, a CLI (`am`), adapters for LangChain, LangGraph, Vercel AI, etc., and plugins for various agent hosts. Quick start is a one‑line installer that creates a cloud profile; a `--local` flag runs the Core container on your machine. Memory can be ingested and queried via the CLI or programmatically via the SDK, and agents can be linked through an MCP server. Licensed under Apache 2.0.

A PyTorch-based quantum computing SDK for simulating, optimizing, and running quantum circuits on simulators or real hardware, featuring differentiable execution and specialized spin-qubit support.

A distributed infrastructure framework that enables individuals to manage PB-level data warehouses, large-scale scraping, and task orchestration with the capacity of a large organization.

A Kubernetes device plugin that enables the registration and scheduling of AMD GPUs as compute resources within a container cluster.

A persistent memory system for AI coding assistants that uses a structured Markdown-based memory stack to maintain project context, rules, and progress across sessions.

A GPU acceleration library for differential equation solvers that enables parallel solving across many parameters and initial conditions.

A Python library for deep learning on tabular data that provides a scikit-learn compatible API and a zoo of 15+ neural architectures.

A command-line tool that uses an LLM to translate plain-English descriptions of video and audio tasks into executable ffmpeg commands.

The official Python library for RunPod, providing an SDK to create serverless AI workers and a REST API wrapper to manage GPU cloud pods and endpoints.

Willow is a self-hostable inference server for fast language tasks including speech-to-text, text-to-speech, and LLM processing.

A version control system and Claude Agent SDK plugin that allows developers to commit, diff, and merge agent configurations and traces to prevent performance regressions.

A high-performance n-dimensional tensor library for Nim, providing tools for scientific computing, machine learning, and deep learning across CPU, CUDA, and OpenCL backends.

An MCP server that provides AI agents with a transparent and auditable way to fetch documentation via llms.txt files.

Spool is a tool for sharing and resuming AI coding agent sessions, turning them into durable web pages that allow others to read and continue the work locally.

A collection of microservice-based generative AI examples and deployment guides designed to simplify the scaling and testing of GenAI applications across diverse hardware platforms.

A Python execution engine for AI agents that records every step of a workflow, allowing users to to replay and resume from a failed step rather than restarting the entire process.

A scientific computing suite based on PaddlePaddle that uses deep learning and automatic differentiation to solve problems in physics, chemistry, and meteorology.

A heterogeneous data synchronization service that manages and executes data movement between different data sources using Flink and SeaTunnel.

A cross-platform inference engine for running highly accurate, compressed LLMs locally on devices ranging from mobile phones to web browsers.

A high-performance C library for LLM inference that uses KV cache compression to enable long-context document understanding on consumer hardware, reducing the need for chunk-based RAG.

An LLM-powered CLI tool that generates contextual, well-formatted Git commit messages by analyzing code changes and developer intent.

An open-source extension of the AWS CDK that provides well-architected infrastructure patterns for quickly deploying generative AI solutions on AWS.

A library for improving LLM performance in Retrieval Augmented Generation (RAG) by creating augmented datasets and fine-tuning models using PEFT.

Surogate is a native C++/CUDA toolkit for fast LLM training (full‑model, LoRA/QLoRA, RL, MoE, multimodal) and high‑throughput serving via OpenAI‑compatible HTTP APIs. It supports BF16, FP8, NVFP4, GGUF quantizations, multi‑GPU/CPU offload, speculative decoding, and runtime LoRA. Benchmarks show 2–7× higher token‑per‑second rates than vLLM/llama.cpp on RTX 50 and H100 hardware.

An advanced compiler and runtime augmentation framework for Transformer-like architectures that optimizes memory and compute efficiency for training and multi-modality inference.