OpenSkillIndex← back to search
claude-codeautomation

Babysitter vector-memory

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

install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/ruflo/skills/vector-memory" ~/.claude/skills/a5c-ai-babysitter-vector-memory && rm -rf "$T"
manifest: library/methodologies/ruflo/skills/vector-memory/SKILL.md
tags
#vector-search#knowledge-graph#memory-management#pattern-retrieval#pagerank#community-detection
source content

Vector Memory

Overview

High-performance vector search using HNSW (Hierarchical Navigable Small World) graphs for pattern storage and retrieval, combined with a knowledge graph for relational reasoning.

When to Use

  • Retrieving similar patterns from execution history
  • 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

ScopePersistenceContent
ProjectCodebase-levelPatterns, architecture decisions, dependencies
LocalSession-levelContext, adaptations, temporary patterns
UserCross-projectPreferences, learned behaviors, global patterns

Agents Used

  • agents/optimizer/
    - Memory and cache optimization

Tool Use

Invoke via babysitter process: 

methodologies/ruflo/ruflo-intelligence