stanleyjacob

12-factor-agents

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

A2A

An open protocol enabling communication and interoperability between opaque agentic applications.

aider

aider is AI pair programming in your terminal

awesome-llm-apps

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

BlueOS

The open source platform for ROV, USV, robotic system operation, development, and expansion.

cadence

Cadence is a distributed, scalable, durable, and highly available orchestration engine to execute asynchronous long-running business logic in a scalable and resilient way.

ceph

Ceph is a distributed object, block, and file storage platform

circuit-tracer

click

Python composable command line interface toolkit

csp

csp is a high performance reactive stream processing library, written in C++ and Python

draft

C++ standards drafts

flash-attention

Fast and memory-efficient exact attention

gemini-cli

An open-source AI agent that brings the power of Gemini directly into your terminal.

glass

haproxy

HAProxy Load Balancer's development branch (mirror of git.haproxy.org)

kineto

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

lancedb

Developer-friendly, embedded retrieval engine for multimodal AI. Search More; Manage Less.

Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

nvbench

CUDA Kernel Benchmarking Library

openevolve

Open-source implementation of AlphaEvolve

OpenSearch-Dashboards

📊 Open source visualization dashboards for OpenSearch.

opentrader

🤖 Open-source crypto trading bot | 📈 DCA & GRID strategies | ✨ UI | ⭐ Star to support the project!

Qwen3

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Roo-Code

Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.

swift-build

A high-level build system based on llbuild, used by Xcode, Swift Playground, and the Swift Package Manager

swift-java

Java interopability support for Swift

thanos

Highly available Prometheus setup with long term storage capabilities. A CNCF Incubating project.

tt-metal

:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

workbench-example-hybrid-rag

An NVIDIA AI Workbench example project for Retrieval Augmented Generation (RAG)