OpenSkillIndex ← back to search

claude-code development

Babysitter memory-summarization

Conversation summarization for memory compression and context 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 "$T/library/specializations/ai-agents-conversational/skills/memory-summarization" ~/.claude/skills/a5c-ai-babysitter-memory-summarization && rm -rf "$T"

manifest: library/specializations/ai-agents-conversational/skills/memory-summarization/SKILL.md

tags

#memory-management #conversation-summarization #context-compression #llm-summarization

source content

Memory Summarization Skill

Capabilities

Implement conversation summarization strategies
Configure rolling summary updates
Design hierarchical summarization
Implement token-aware summarization
Create extractive and abstractive summaries
Design summary quality evaluation

Target Processes

conversational-memory-system
long-term-memory-management

Implementation Details

Summarization Strategies

Rolling Summary: Update summary with new messages
Hierarchical: Multi-level summarization
Token-Budget: Fit within token limits
Extractive: Key message selection
Abstractive: LLM-generated summaries

Configuration Options

LLM for summarization
Summary token budget
Update frequency
Summary template
Quality thresholds

Best Practices

Balance detail vs compression
Preserve key information
Monitor summary quality
Test with long conversations
Handle context window limits

Dependencies

langchain-core
LLM provider