Rvf Manage

This manages RVF (Ruflo Vector Format) files, which are how Claude Flow packages up agent memory with embeddings, metadata, and causal relationships for moving between projects or backing up. You can export patterns you've taught an agent, import from Claude Code's native memories, or migrate formats when things upgrade. The practical bit is the transfer commands that let you pull knowledge from one project into another, which beats re-teaching the same context. It's using 384-dimensional ONNX embeddings under the hood, so the vectors are reasonably portable. Most useful when you've built up project-specific knowledge you don't want to lose or need to replicate across environments.

skills.sh installs: 741
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill rvf-manage --agent claude-code

Installs into .claude/skills of the current project.

Files

RVF Management

Manage RVF files for portable, transferable agent memory.

When to use

When you need to export agent memory to RVF format for backup, transfer between projects, or share knowledge between teams.

Steps

List memories — call mcp__plugin_ruflo-core_ruflo__memory_list to see all stored memories
Export — npx @claude-flow/cli@latest memory export -o <file> [-n <namespace>] [-f json|csv|binary] (vectors included by default; --include-vectors false to drop them). Pick the output path inside the project, never an existing file you have not read
Import — npx @claude-flow/cli@latest memory import -i <file> [-n <namespace>] (merges and skips duplicates by default), or call mcp__plugin_ruflo-core_ruflo__memory_import_claude to pull in Claude Code auto-memories
Migrate — call mcp__plugin_ruflo-core_ruflo__memory_migrate for format upgrades
Stats — call mcp__plugin_ruflo-core_ruflo__memory_stats for storage metrics