‹ 首页

route-by-query-shape

@bitterbot-ai · 收录于 今天 · 上游提交 今天

When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.

适合你,如果想让智能体在关系型查询时自动使用知识图谱

/ 通过 npx 安装 校验哈希
npx oh-my-skill add bitterbot-ai/bitterbot-desktop/route-by-query-shape
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- bitterbot-ai/bitterbot-desktop/route-by-query-shape
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify bitterbot-ai/bitterbot-desktop/route-by-query-shape
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
2425GitHub stars
~258上下文体积 · 单文件
索引托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · 867a130

route-by-query-shape

When you ask Bitterbot a relationship question — "who did I talk to about Q4?", "who worked with me on Foo?" — the vector-based memory_search often misses because the answer lives in entity relationships, not in chunk text. The graph backend gets these right.

This interceptor watches memory_search calls, detects relationship-shaped queries, extracts the salient entity, and re-routes the call to the graph backend before it executes.

What you'll see

For relationship questions, the agent will hit the knowledge graph rather than searching through unstructured text. Expect noticeably better hit rates on "who did X with Y" style questions.

Implementation

Built-in interceptor route-by-query-shape:relationship lives in src/agents/skills/builtin-interceptors/route-by-query-shape.ts. Fires up to 12 times per session.

按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。