ruvnet

An innovative system to enhance AI assistants with a flexible, standardized API for agentic behaviors.

Codex variant from ruvnet exploring single-agent coding workflows with OpenAI Codex.

Agentic engineering toolkit for AI-powered data analysis workflows.

An agentic marketing swarm framework for AI-driven campaigns and content workflows.

Self-Aware Feedback Loop Algorithm — Python framework for building self-improving AI agents with reflective memory.

Quantum-resistant DAG-based anonymous communication protocol, built end-to-end with Claude Code via a TDD implementation plan.

Structured prompting methodology for AI-assisted development: specification, pseudocode, architecture, refinement, completion.

rUv's custom AI-driven IDE built around the SPARC methodology — spec-first development where the AI is a first-class collaborator.

Diffusion-based code refinement model — iteratively denoises code drafts toward correctness via a learned diffusion process.

AI-Driven Decentralized Organization template using Supabase and LangChain.js — governance, treasury, and operations run partly by agents.

rUv's JavaScript port of Drupal patterns — node-based content modeling and rendering in the Node.js ecosystem.

rUv's multi-agent code orchestration system — agents collaborate over a shared mesh of code understanding, edits, and tests.

Knowledge distillation system that extracts domain-specific knowledge and trains compact models while maintaining high performance.

Navigation system using quantum magnetometers for precise positioning in GPS-denied environments — research-stage prototype.

Open source UI for Meta Llama Stack apps and agents — chat-first frontend wired to the Llama Stack inference and agents API.

rUv's framework for AI agents focused on security — automated reconnaissance, vulnerability triage, and exploit explanation.

Web app that captures media streams from webcam, desktop, or specific apps — samples frames at intervals and uses AI to analyze and summarize.

rUv's framework for AI agents that generate research reports — query, synthesize, cite, format. Outputs structured Markdown ready to publish.

Dynamic MCP registry using Cookiecutter templates — spin up custom MCP servers from parameterized scaffolds on demand.

AI-powered game engine for dynamic, personalized experiences in evolving worlds — ethical, accessible, inclusive design from the ground up.

Vector memory that gets smarter every time your agent uses it — feedback-aware retrieval that learns which results actually helped.

rUv's reflective engineering agent — pauses to reason about its own reasoning before each move, then commits to actions with explicit justification.

rUv's MCP federation implementation following the official spec — proper message framing, transport, and full protocol lifecycle for distributed agent registries.

ANS Protocol from the OWASP GenAI Security Project — secure discovery and interaction framework for AI agents across organizations.

Rust + WASM solver for asymmetric diagonally dominant systems — Neumann series, push, and hybrid random-walk algorithms with npm CLI and HTTP API.

Steganography framework for embedding and extracting agentic commands in audio and video media using ultrasonic frequencies — covert agent-to-agent comms.

rUv's tool for symbolic note-taking — captures structured knowledge with named relations between concepts for graph-based recall.

First decompiler that understands code semantically — recovers original names with AI, proves every transformation with cryptographic witness chains.

Command-line tool for configurable web automation with AI-assisted template creation — drive any site from a YAML config.

Competitive agentic platform built entirely on MCP — deploy autonomous AI swarms, train networks, compete in coding challenges, earn rUv tokens.

rUv's virtual machine built for the agentic age, in Rust — a secure, deterministic runtime for executing AI-generated code with isolation.

rUv's voice-driven AI bot — real-time speech-to-speech agent for hands-free interaction with LLMs.

Platform that makes AI conversations smarter and more responsive — interprets what an AI is saying mid-stream instead of waiting for the full response.

rUv's Fast Augmented Context Tools — lean retrieval pattern that skips vector search by caching static tokens in Claude Sonnet 4 and fetching live facts on demand.

rUv's framework for building self-managing applications — decentralized agents that coordinate without a central planner.

Declarative self-learning JavaScript — TypeScript port of DSPy for programmatically optimizing LLM pipelines via examples instead of prompt tweaking.

Hyper-efficient prompt language designed to optimize LLM interactions — uses logographic scripts and symbolic constructs to compress prompts ~10x.

rUv's nightly decompile and reverse-engineered rebuild of the Claude Code CLI — open-source attempt to recreate the proprietary tool.

Blazing-fast, memory-safe neural-network library for Rust — brings the classic Fast Artificial Neural Network library into the modern world.

rUv's tool for easily switching between alternative low-cost AI models in Claude Code and the Agent SDK — keep your prompts, swap the brain.

rUv's high-performance, real-time, self-learning vector graph memory database written in Rust — designed for agentic AI memory at scale.

Ruflo Multi-agent AI orchestration for Claude Code Orchestrate 100+ specialized AI agents across machines, teams, and trust boundaries. Ruflo adds coordinated swarms, self-learning memory, federated comms, and enterprise security to Claude Code — so agents don't just run, they collaborate. Why Ruflo? Claude Flow is now Ruflo — named by rUv, who loves Rust, flow states, and building things that feel inevitable. The "Ru" is the Ruv. The "flo" is the flow. Underneath, WASM kernels written in Rust p

RuView transforms commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection without cameras or wearables. It uses Channel State Information (CSI) from WiFi to detect breathing, heart rate, and body position through walls using edge AI on inexpensive ESP32 hardware.

rUv's AI-powered development methodology — the rUv approach: prompts, patterns, and skills for shipping with AI agents.