跳到正文
cccskills
免费在 GitHub 公开

agentdb-hyperedge

Search and manage hyperedges — n-ary relationships between memories. Use for swarm membership, multi-cause incidents, or any "this involves all of (A, B, C, D)" relationship that doesn't fit a binary edge.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Hyperedge

Hyperedges connect more than two nodes — useful when a single relationship genuinely involves many participants.

When to use

  • Swarm membership — "agents A, B, C, D worked together on task T"
  • Multi-cause incidents — "outage was caused by (deploy, traffic spike, cache miss, retry storm)"
  • Group decisions — "ADR-046 was approved by reviewers (alice, bob, carol, dan)"
  • Anything where binary edges would lose information by splitting the relationship

API

agentdb_hyperedge_create(
  nodes:        [<id>, <id>, ...]
  description:  <one-liner>
  embedding?:   Float32Array
  confidence?:  0..1
  metadata?:    { ... }
)

agentdb_hyperedge_search(
  query:        <semantic | nodeId>
  topK?:        10
)

agentdb_hyperedge_delete(
  id:           <hyperedge id>
)

The agentdb_hyperedge_delete tool was added in agentdb 3.0.0-alpha.13.

Semantic search over hyperedges

Hyperedges are searchable by their description embedding — useful for "find all multi-agent collaborations on auth-related work" without enumerating every binary edge.

Don't

  • Don't use a hyperedge when a binary edge fits. Two-node "caused" links are cheaper to reason about.
  • Don't put more than ~10 nodes in one hyperedge. After that, the relationship is too broad to mean anything specific.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

中文简介正在准备中。当前显示原文说明。

ruvnet/agentdb942026年10月12日 更新

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

中文简介正在准备中。当前显示原文说明。

ruvnet/agentdb942026年10月12日 更新

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

中文简介正在准备中。当前显示原文说明。

ruvnet/agentdb942026年10月12日 更新

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.

中文简介正在准备中。当前显示原文说明。

ruvnet/agentdb942026年10月12日 更新

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

中文简介正在准备中。当前显示原文说明。

ruvnet/agentdb942026年10月12日 更新

Walk the causal graph in AgentDB to explain why two memories are connected, or trace a root cause. Use when the user asks "why did X happen", "what led to Y", or after an incident.

中文简介正在准备中。当前显示原文说明。

ruvnet/agentdb942026年10月12日 更新

查看 ruvnet 的全部技能

报告此技能的问题