rUv

Multi-agent orchestration for Claude Code, coordinating 100+ agents with swarms, self-learning memory, and federation.

Estimates human pose, breathing, and presence from commodity WiFi signals, with no cameras or wearables.

Real-time vector graph memory database written in Rust, built for self-learning agentic AI memory at scale.

Swaps low-cost alternative AI models into Claude Code and the Agent SDK while keeping your prompts unchanged.

Five-stage prompting method for AI-assisted development, running from specification through to completion.

Virtual machine written in Rust that runs AI-generated code in a deterministic, isolated runtime.

Prompt language that compresses LLM prompts about tenfold using logographic scripts and symbolic constructs.

Quantum-resistant protocol for anonymous communication built on a DAG, implemented in Rust.

Nightly decompiled and reverse-engineered rebuild of the Claude Code CLI as an open-source project.

Memory-safe neural network library for Rust that modernizes the classic Fast Artificial Neural Network library.

Rust platform that interprets what an AI is saying mid-stream instead of waiting for the full response.

TypeScript port of DSPy for optimizing LLM pipelines programmatically from examples instead of prompt tweaking.

Framework for building self-managing applications from decentralized agents that coordinate without a central planner.

Retrieval pattern that skips vector search by caching static tokens in the model and fetching live facts on demand.

Python framework for building self-improving AI agents around a self-aware feedback loop with reflective memory.

Rust and WASM solver for asymmetric diagonally dominant linear systems with an npm CLI and HTTP API.

Rust decompiler that recovers original names with AI and proves each transformation with cryptographic witness chains.

Vector memory for agents with feedback-aware retrieval that learns which results actually helped.

Agentic swarm framework for running AI-driven marketing campaigns and content workflows.

Note-taking tool that captures structured knowledge with named relations between concepts for graph-based recall.

Framework for security-focused AI agents that automate reconnaissance, vulnerability triage, and exploit explanation.

Agentic platform built on MCP where users deploy AI swarms, compete in coding challenges, and earn rUv tokens.

Hides agent-to-agent commands inside audio and video at ultrasonic frequencies, then pulls them back out.

AI-powered game engine for dynamic, personalized experiences in evolving worlds, written in Rust and Node.js.

Secure discovery and interaction protocol for AI agents across organizations, part of the OWASP GenAI Security Project.

Command-line web automation tool that drives sites from YAML configs with AI-assisted template creation.

Agentic engineering toolkit in Python for building AI-powered data analysis workflows.

Speech-to-speech agent handling real-time spoken conversation with LLMs, implemented in Python.

Dynamic MCP registry that spins up custom MCP servers from parameterized Cookiecutter scaffolds on demand.

Multi-agent orchestration system where coding agents collaborate over a shared mesh of edits and tests.

Implements MCP federation against the official spec, covering message framing, transport, and the full lifecycle.

Coding agent that reasons about its own reasoning before each move and commits to actions with explicit justification.

JavaScript port of Drupal patterns bringing node-based content modeling and rendering to the Node.js ecosystem.