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.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Self-learning hooks from the Ruflo CLI (@claude-flow/cli). Hooks fire around
task and edit lifecycle events to coordinate agents, checkpoint state, and learn
patterns from outcomes. A routing surface picks a handler tier by task complexity.
# Initialize hooks in a project
npx @claude-flow/cli@latest hooks init
# List available hooks / workers
npx @claude-flow/cli@latest hooks list
# Route a task to a handler tier by complexity
npx @claude-flow/cli@latest hooks route --task "add types to this module"
pre-task / post-task, pre-edit / post-edit,
session-start / session-end.To add frequent checkpoints and outcome-learning to a long-running or multi-agent workflow, or to route simple transforms away from an expensive model.
Ruflo — @claude-flow/cli.
Related: ruflo-swarm,
ruflo-memory.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。