Agent-Skills.md

Agent Skills: vector-memory

HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.

UncategorizedID: a5c-ai/babysitter/vector-memory

Repository

a5c-ai/babysitter
a5c-aiLicense: MIT
1,52087

Install this agent skill to your local

pnpm dlx add-skill https://github.com/a5c-ai/babysitter/tree/HEAD/library/methodologies/ruflo/skills/vector-memory

Skill Files

Browse the full folder contents for vector-memory.

Download Skill

Loading file tree…

library/methodologies/ruflo/skills/vector-memory/SKILL.md

Skill Metadata

Name
vector-memory
Description
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
  • Building and querying knowledge graphs for project context
  • Managing cross-session memory across project/local/user scopes
  • Fast similarity search for routing decisions

HNSW Performance

  • Search latency: ~61 microseconds
  • Query throughput: ~16,400 QPS
  • Configurable embedding dimensions (default: 128)

Knowledge Graph

  • PageRank: Importance scoring for knowledge nodes
  • Community Detection: Cluster related patterns
  • LRU Cache: Fast access to frequently used patterns
  • SQLite Backing: Persistent cross-session storage

3-Tier Memory

| Scope | Persistence | Content | |-------|------------|---------| | Project | Codebase-level | Patterns, architecture decisions, dependencies | | Local | Session-level | Context, adaptations, temporary patterns | | User | Cross-project | Preferences, learned behaviors, global patterns |

Agents Used

  • agents/optimizer/ - Memory and cache optimization

Tool Use

Invoke via babysitter process: methodologies/ruflo/ruflo-intelligence