MNN

High-performance local LLM inference in C/C++

llama.cpp is the foundational C/C++ library with 75K+ GitHub stars powering local LLM inference on consumer hardware. Provides optimized CPU and GPU inference for quantized models in GGUF format. Supports LLaMA, Mistral, Phi, Gemma, and most open-weight families. Features 2-8 bit quantization for reduced memory, multi-GPU support, context extension, grammar-constrained output, and an OpenAI-compatible API server. The engine behind Ollama and LM Studio.

Run LLMs locally with one command

Tool for running large language models locally on your machine with a simple CLI interface. Download and run Llama 3, Mistral, Gemma, Phi, Code Llama, and dozens of other open-source models with a single command. Features model management, GPU acceleration (NVIDIA/AMD/Apple Silicon), OpenAI-compatible API server, Modelfile for customization, and multi-model switching. Ideal for offline AI development, privacy-sensitive use cases, and local testing. 120K+ GitHub stars.

eBPF-based networking, security, and observability for Kubernetes

Cilium is a CNCF Graduated, Apache-2.0 project for Kubernetes networking, security, and observability using eBPF. It can replace kube-proxy, enforce identity-aware L3-L7 network policies, and add Hubble flow observability plus Tetragon runtime-security signals. Current source checks support GKE Dataplane V2 using Cilium/eBPF and Azure CNI Powered by Cilium for AKS.

Fast and lightweight Docker Desktop alternative for macOS

OrbStack is a macOS application that replaces Docker Desktop with lightweight container and Linux VM management. Its docs emphasize fast starts, lower CPU and memory overhead, and native macOS integration with menu bar controls, file sharing, and network access to containers by name, with exact gains depending on workload. Supports Docker, Kubernetes, and full Linux VMs.

Distributed AI compute engine for scaling Python and ML workloads

Ray is an open-source distributed computing framework built for scaling AI and Python applications from a laptop to thousands of GPUs. It provides libraries for distributed training, hyperparameter tuning, model serving, reinforcement learning, and data processing under a single unified API. Ray's public site highlights OpenAI and other enterprise users. Maintained by Anyscale with Apache-2.0 open-source licensing.

Unified framework for fine-tuning 100+ large language models

LLaMA-Factory is an open-source toolkit providing a unified interface for fine-tuning over 100 LLMs and vision-language models. It supports SFT, RLHF with PPO and DPO, LoRA and QLoRA for memory-efficient training, and continuous pre-training. The LLaMA Board web UI enables no-code configuration, while CLI and YAML workflows serve advanced users. Integrates with Hugging Face, ModelScope, vLLM, and SGLang for model deployment.

Run GitHub Actions locally for fast feedback

Act is an open-source tool that runs GitHub Actions workflows locally using Docker containers that match GitHub's execution environment. It provides instant feedback on workflow changes without pushing to a repository, supports matrix builds, secret management, and artifact handling. Act can also replace Makefiles by using workflow files as task definitions, making it useful for both CI/CD development and local task automation across development teams.

Drop-in authentication for modern JavaScript apps

Clerk is a complete authentication and user management platform for React, Next.js, and modern JavaScript frameworks. It provides pre-built UI for sign-in, sign-up, user profiles, organizations, MFA, passkeys, JWT sessions, webhooks, and billing. The Hobby plan supports up to 50,000 monthly retained users per app, with Pro, Business, and Enterprise tiers for growing teams.