ruvnet — 9 Open-Source AI Agent Skills

ruvnet is the author of 9 open-source AI agent skills and MCP servers spanning mcp-server, agent-tool, claude-skill, with a combined 70,706+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 63/100) and security-graded — 8 verified safe.

Top skills by ruvnet

• ruflo — 🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI sys (68.3k★ · quality 62/100 · security: safe)
• agentic-flow — Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it le (794★ · quality 65/100 · security: safe)
• metaharness — 🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loo (595★ · quality 65/100 · security: safe)
• open-claude-code — Nightly Claude Code CLI Decompile — Reverse Engineered & Rebuilt (477★ · quality 71/100 · security: safe)
• agent-harness-generator — 🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loo (343★ · quality 68/100 · security: safe)
• rudevolution — ruDevolution — The first decompiler that understands code semantically, recovers original names with AI, proves every transformation with cr (124★ · quality 63/100 · security: safe)
• sublinear-time-solver — Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neumann series, push, and hybrid random-walk algorithm (88★ · quality 62/100 · security: safe)
• obsidian-brain — Obsidian plugin bridging your vault with the RuVector Brain — DiskANN semantic search, AIDefence scanning, pi.ruv.io federated sync, DPO pai (15★ · quality 67/100 · security: safe)

View ruvnet on GitHub · Explore audited agent skills