claude-user-memory

Name: claude-user-memory
Author: VAMFI

Verified

Autonomous agent substrate for Claude Code CLI. Research→Plan→Implement workflows with quality gates, TDD enforcement, and multi-agent coordination. 4.8-5.5x faster development. Built on Anthropic's engineering research.

193stars

29forks

Shell

Installation

# Add to your Claude Code skills
git clone https://github.com/VAMFI/claude-user-memory

Getting Started

Guides for using ai agents skills like claude-user-memory.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 5/30/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-05-30T15:44:49.146Z",
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is claude-user-memory?

claude-user-memory is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by VAMFI. Autonomous agent substrate for Claude Code CLI. Research→Plan→Implement workflows with quality gates, TDD enforcement, and multi-agent coordination. 4.8-5.5x faster development. Built on Anthropic's engineering research. It has 193 GitHub stars.

Is claude-user-memory safe to use?

Yes. claude-user-memory passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install claude-user-memory?

Clone the repository with "git clone https://github.com/VAMFI/claude-user-memory" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is claude-user-memory written in?

claude-user-memory is primarily written in Shell. It is open-source under VAMFI on GitHub, so you can review or fork the full source.

Are there alternatives to claude-user-memory?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claude-user-memory against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

agent-audit formax

Agentic Substrate v4.1

Research-first development system for Claude Code CLI

No API hallucinations. No coding from stale training data. Research → Plan → Implement.

Quick Start

# Install
git clone https://github.com/VAMFI/claude-user-memory.git
cd claude-user-memory
./install.sh

# Use
/workflow Add Redis caching to ProductService

What You Get

9 Agents - Orchestration, research, planning, implementation, debugging, deployment
5 Skills - Auto-invoked capabilities for research, planning, validation, patterns, context
5 Commands - /workflow, /research, /plan, /implement, /context
Quality Gates - Research ≥80, Plans ≥85, Tests passing, 3-retry circuit breaker
Memory - Knowledge graph persists across sessions

Usage

Full automation:

/workflow Add authentication with JWT tokens

Step-by-step:

/research Redis for Node.js v5.0
/plan Redis caching implementation
/implement

Direct agents:

@chief-architect Build payment system
@docs-researcher Research Stripe API
@brahma-deployer Deploy v2.5.0

How It Works

Research (< 2 min) - Fetch version-accurate docs before coding
Plan (< 3 min) - Create minimal-change blueprint with rollback
Implement (< 10 min) - Execute with TDD + self-correction
Learn - Auto-capture patterns to knowledge graph

Quality gates block bad inputs. Circuit breaker stops infinite loops.

Installation

Cross-Platform: Works on macOS, Linux, Windows (WSL), and most Unix systems

Requirements: Minimal - bash and git only. Optional: python3/python for enhanced features

Installs to: ~/.claude/

Preserves:

All data in ~/.claude/data/
Your CLAUDE.md customizations (smart-merged)
Modified files (detected by checksum)
Knowledge files and patterns

Upgrade:

./install.sh

Your data and customizations are automatically preserved.

Update:

./update.sh    # Selective update (only changed files)

Configuration

./customize.sh                              # Interactive menu
./customize.sh --enable-mcp memory         # Enable MCP servers
./customize.sh --list-mcps                 # View configuration

Uninstall

./uninstall.sh --dry-run    # Preview what will be removed
./uninstall.sh              # Remove (preserves data)

Documentation

Agents Overview - All 9 agents
Skills Overview - Auto-invoked capabilities
Workflows Overview - Development patterns
Installation Behavior - Data preservation details
Release Notes - v4.0/4.1 features

Research Foundation

Built on Anthropic research (2024-2025):

Extended Thinking: 54% improvement on complex tasks
Multi-Agent Orchestration: 90.2% performance improvement
Contextual Retrieval: 49-67% better accuracy

License

MIT License - See LICENSE

Version: 4.1.0 Released: November 22, 2025 Status: Production-Ready

Research → Plan → Implement → Learn