MCP App StoreMCP App Store
from claude-memory-kit15
A production-ready memory system and workflow for Claude Code agents: daily capture, audit-driven promotion, multi-project isolation, and utilities for memory h
The Claude Memory Kit provides a four-layer persistent memory architecture for Claude Code agents. It captures daily logs, maintains a hot-cache MEMORY.md for quick context, stores role-based reference skills, and enforces canonical rules. The kit automates an end-of-day audit ritual (/close-day) that synthesizes session notes, proposes promotions to long-term memory, and can split or lint oversized reference skills. It aims to eliminate manual file editing by letting the agent capture, propose, and write changes with minimal human intervention.
Use this when you need reliable, agent-driven memory for ongoing projects: knowledge retention across sessions, automatic synthesis of daily work, project-specific isolation (projects/<name>/), or automated memory hygiene routines (memory-lint, memory-audit). Especially useful for teams or individuals running many agent sessions who want consistent, reviewable memory promotion workflows.
Best suited for Anthropic/Claude Code integrations and similar agent runtimes that support invoked skills and session hooks. It also benefits teams using local agent tooling and CLI-driven agent sessions.
Claude Memory Kit v4 is a persistent memory system for Claude Code agents with layered architecture (daily logs, hot cache, knowledge articles, rules). It features an agent-driven promotion ritual via /close-day, multi-project isolation, and zero external dependencies. No scripts were bundled for execution testing — the skill is purely instructional/architectural. The SKILL.md is well-structured with clear invariants, migration notes, and a clean quick start.
No security concerns — no remote code fetching, no credential handling, no destructive commands. Purely declarative skill describing a memory management workflow. Well-written documentation with clear versioning and changelog references.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.
draw.io Diagram Skill
Create, edit, lint, and export draw.io diagrams; includes export helpers, SVG linting, and repository QA for clean architecture and icon-based diagrams.
Heptabase CLI — Terminal access to Heptabase MCP
Command-line interface for interacting with a Heptabase knowledge base: search notes, read cards/journals, append entries, and search/read PDFs — useful for ter