The open source coding agent.

Lightweight nVidia telemetry and terminal system monitor - built for any architecture - Jetson, GB10, GB200, H100

Open standard for machine learning interoperability

LEAKED SYSTEM PROMPTS FOR CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, DEVIN, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

EmDash is a full-stack TypeScript CMS based on Astro; the spiritual successor to WordPress

Official Rust implementation of Apache Arrow

Kubernetes Native Edge Computing Framework (project under CNCF)

Lightweight Kubernetes

An MCP server for interacting with Google Colab

Streaming replication for SQLite.

OpenTelemetry Collector distribution with programmable pipelines

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

AI agents running research on single-GPU nanochat training automatically

The Interplanetary Overlay Network (ION) is NASA's open-source software implementation of Delay Tolerant Networking (DTN). ION development is managed by the Jet Propulsion Laboratory.

Specification and documentation for Agent Skills

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

Kubernetes Operator for OpenTelemetry Collector

Supercharge Your LLM with the Fastest KV Cache Layer

OpenTelemetry Python API and SDK

ICML2025: Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

SWE-bench: Can Language Models Resolve Real-world Github Issues?

get a job

A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.

🤖 Just a command runner

vCluster - Create fully functional virtual Kubernetes clusters - Each vcluster runs inside a namespace of the underlying k8s cluster. It's cheaper than creating separate full-blown clusters and it …

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity