Letter M Journey

Specification and documentation for the Model Context Protocol.

Universal memory layer for AI Agents

A cloud-native vector database, storage for next generation AI applications.

Machine Learning automation and tracking

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP server chaos into governed, auditable tool access with Keycloak/Entra integration.

MatrixHub is an open-source, self-hosted, Hugging Face-compatible AI model registry and distribution layer for enterprise inference. It accelerates vLLM and SGLang on Kubernetes with pull-once-serve-all caching, air-gapped delivery, RBAC and multi-tenancy, and cross-region replication.

The open source, cloud native tool for API Mocking and Testing

Apache Maven is a software project management and comprehension tool. Based on the concept of a project object model (POM), Maven can manage a project's build, reporting and documentation from a central piece of information.

The project establishes open standards for packaging, distributing and running AI artifacts in the cloud-native environment.

Monokle helps you achieve high-quality Kubernetes deployments throughout the entire application lifecycle — from code to cluster. It enables your team to define Kubernetes configuration policies to ensure consistent, secure, and compliant application deployments every time. In addition to policy enforcement, Monokle’s ecosystem of tools make your team’s daily YAML configuration workflows easier. Monokle is created and maintained by Kubeshop.

Mocking, debugging proxy and chaos engineering for HTTP, gRPC, GraphQL, LLM, MCP, Kafka, TCP and more.

Machine Learning automation and tracking

MLflow is an open source AI engineering platform for agents, LLMs, and ML models. It provides a comprehensive suite of tools to manage the machine learning lifecycle, enabling teams to build, debug, evaluate, monitor, and deploy production-quality AI applications while controlling costs and managing access to models and data.

A high performance multithreaded event-based key/value cache store intended to be used in a distributed system.

GPU optimized techniques for training transformer models at-scale

A cloud-native vector database, storage for next generation AI applications.

A high performance multithreaded event-based key/value cache store intended to be used in a distributed system.

Mocking, debugging proxy and chaos engineering for HTTP, gRPC, GraphQL, LLM, MCP, Kafka, TCP and more.

Mermin is a Kubernetes-native network observability tool that uses eBPF exports OpenTelemetry Flow Traces, to provide deep visibility into your cluster’s network communications with zero application changes required.

As an instrumentation facade, Micrometer allows you to instrument your code with dimensional metrics with a vendor-neutral interface and decide on the observability system as a last step. Instrumenting your core library code with Micrometer allows the libraries to be included in applications that ship data to different backends.

The goal of the open source Monocle project is to help GenAI developers trace their applications. Hosted in incubation as a Sandbox project in LF AI & Data.

A network load-balancer implementation for Kubernetes using standard routing protocols

An easy to install, single node local Kubernetes.

Self-service, remote installation of Windows, CentOS, ESXi and Ubuntu on real servers turns your data center into a bare-metal cloud.

Open source security lake platform for AWS

Metarget is a framework providing automatic constructions of vulnerable cloud native infrastructures.

GPU optimized techniques for training transformer models at-scale