Spin up a coordinated multi-agent swarm (hierarchical or mesh topology) to work a complex, multi-file task on a ruOS desktop. Use when a task needs 3+ agents working in parallel with anti-drift coordination; skip for single-file edits.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Multi-agent swarm orchestration from the Ruflo CLI (@claude-flow/cli).
Initialize a swarm with a topology and a max-agent count, then let coordinated
agents work the task. Hierarchical topology is the anti-drift default for coding.
# Initialize a swarm (hierarchical is the anti-drift default for coding)
npx @claude-flow/cli@latest swarm init --topology hierarchical --max-agents 8 --strategy specialized
# Check status / health
npx @claude-flow/cli@latest swarm status
hierarchical (anti-drift, leader-coordinated), mesh
(peer-to-peer), plus ring/star/adaptive.max-agents at 6–8 for tight coordination on coding tasks.Complex features, cross-module refactors, or audits that fan out across many files. For a one-line lookup or a single-file edit, don't spin up a swarm.
Ruflo — @claude-flow/cli.
Related: ruflo-memory,
ruflo-hooks.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Self-learning pre/post-task hooks and model/task routing from the Ruflo CLI, on a ruOS desktop. Use to add coordination, formatting, and learning around Claude Code operations, or to route work by complexity/cost.
日本語の概要は準備中です。原文の説明を表示しています。
Store and semantically search agent memory with ONNX vector embeddings on a ruOS desktop, using the Ruflo CLI. Use to persist patterns/decisions across sessions and recall them by meaning rather than exact key.
日本語の概要は準備中です。原文の説明を表示しています。
Persistent, adaptive vector memory for agents on a ruOS desktop — a Rust-native vector database with local semantic embeddings, HNSW retrieval, and graph relationships. Use to remember and recall across sessions with no database server or API key.
日本語の概要は準備中です。原文の説明を表示しています。