mcp-memory-optimizer
CommunityChunk and recall large analyses instantly.
Authoraiguy611
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Efficiently manage large LLM analysis results in MCP memory by chunking, content-addressable storage, and semantic retrieval. This approach minimizes token bloat, enables selective loading, and supports long-running multi-agent workflows by preserving and restoring work across sessions.
Core Features & Use Cases
- Smart semantic chunking up to 2500 tokens with 100-token overlap to preserve context.
- Hash-based keys and agent-scoped metadata for deduplication and provenance.
- Efficient retrieval that loads only relevant chunks via semantic search.
- Agent persistence: store work, shut down, and later rehydrate results.
- Patterns: storing large codebase analyses, multi-agent memory sharing, and incremental research timelines.
Quick Start
Analyze your content to estimate chunking, chunk it into semantic pieces with an agent ID, and store the results in MCP memory.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: mcp-memory-optimizer Download link: https://github.com/aiguy611/cc-tools/archive/main.zip#mcp-memory-optimizer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.