Agent Orchestration
Plugin
claude-user-memory
Research-first development system for Claude Code CLI No API hallucinations. No coding from stale training data. Research → Plan → Implement.
Plugin Signal47/100Fair
maintained8
capable56
documented100
adopted49
Stats
207
Stars
32
Forks
Quiet
Maintenance
Shell
Language
8mo ago
Last commit
1y ago
Created
Repo: VAMFI/claude-user-memory
What's inside
Agent(9 agents)
brahma-analyzerCross-artifact consistency and coverage analysis specialist with Anthropic think protocol. Validates alignment between specifications, plans, tasks, and implementation. Use before implementation to catch conflicts early.brahma-deployerProduction deployment specialist with Anthropic safety patterns managing CI/CD pipelines, infrastructure provisioning, and safe rollout strategies. Defaults to canary deployments with auto-rollback. Use for production deployments and release management.brahma-investigatorRoot cause analysis and debugging specialist with Anthropic think protocol and 3-retry limit. Focuses on systematic problem diagnosis, error tracing, and fix validation. Use for complex bugs and system failures.brahma-monitorObservability and monitoring specialist with Anthropic's three pillars pattern (Metrics, Logs, Traces). Sets up comprehensive monitoring, SLI/SLO tracking, and incident detection. Use for system observability and proactive alerting.brahma-optimizerPerformance optimization and auto-scaling specialist with Anthropic profiling patterns. Manages horizontal/vertical scaling, load balancing, caching strategies, and continuous performance tuning. Use for scaling challenges and performance work.chief-architectMaster orchestrator for complex, multi-faceted software projects. Coordinates specialist agents (researchers, planners, implementers) to deliver cohesive solutions. Use for projects requiring 3+ capabilities or cross-domain work (frontend + backend + devops).
Command(5 commands)
/contextAnalyze and optimize context configuration. Reviews CLAUDE.md, knowledge-core.md, and active context for optimization opportunities. Helps prevent context rot (39% improvement, 84% token reduction)./implementQuick command to invoke code-implementer to execute implementation with self-correction (up to 3 intelligent retries)./planQuick command to invoke implementation-planner to create surgical, reversible implementation plans with rollback procedures./researchQuick command to invoke docs-researcher for rapid documentation research. Fetches version-accurate, authoritative sources and creates ResearchPack./workflowComplete Research → Plan → Implement workflow in one command. Invokes chief-architect to orchestrate all phases with quality gates and self-correction.
README
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.mdcustomizations (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
File tree
VAMFI/claude-user-memoryView on GitHub
.claude/
agents/
brahma-analyzer.md
brahma-deployer.md
brahma-investigator.md
brahma-monitor.md
brahma-optimizer.md
chief-architect.md
code-implementer.md
docs-researcher.md
implementation-planner.md
commands/
context.md
implement.md
plan.md
research.md
workflow.md
data/
mcp-config-template.json
hooks/
auto-format.sh
check-agent-economics.sh
run-tests.sh
suggest-context-edits.sh
update-knowledge-core.sh
validate-implementation-plan.sh
validate-research-pack.sh
integrations/
langgraph/
brahma_state.py.template
README.md
metrics/
tracker.sh
skills/
context-engineering/
skill.md
pattern-recognition/
skill.md
planning-methodology/
skill.md
quality-validation/
skill.md
research-methodology/
skill.md
templates/
agentic-substrate-personal.md.example
agents-overview.md
CLAUDE.md.template
CLAUDE.md.user-level
skills-overview.md
workflows-overview.md
validators/
api-matcher.sh
circuit-breaker.sh
.gitignore
.mcpb/
README.md
.research-brief-anthropic.md
.vamfi/
ImplementationPlan-Adaptation-Pattern-Integration.md
ResearchPack-Adaptation-Pattern-Integration.md
tests/
test_adaptation_pattern.sh
AgentHandoffProtocol-DESIGN.md
archive/
README.md
update-local-installation-v3.0-to-v3.1.sh
workflow-artifacts-2025-11-01/
ImplementationPlan.md
ResearchPack.md
build-mcpb.sh
CHANGELOG.md
CLAUDE-MEMORY-ENHANCEMENT.md
CLAUDE.md
COMPLETION-REPORT.md
CONTRIBUTING.md
CRITICAL-BUG-FIX.md
CURL-INSTALL-FIX.md
CURL-INSTALLATION-TEST.md
customize.sh
DEPLOYMENT-SUMMARY.md
diagnose-install.sh
docs/
research/
BENCHMARKING-RESEARCH-PACK.md
HUMANEVAL-BENCHMARK-APPROACH.md
validation-reports/
VALIDATION-REPORT.md
WORKFLOW-COMPLETE-REPORT.md
examples/
v2/
01-simple-api-integration.md
README.md
FRAMEWORK-COMPARISON.md
GITHUB-ISSUE-1-RESOLUTION.md
ImplementationPlan-Agentic-Substrate.md
ImplementationPlan-v4.1.md
install.sh
INSTALLATION-BEHAVIOR.md
INSTALLATION-VERIFICATION-SUMMARY.md
knowledge-core.md
knowledge-core.md.backup
LICENSE
linkedin-article.md
manifest-template.json
manifest.json
PHILOSOPHY.md
PORTABLE-PATHS-FIX.md
PROJECT-BRAHMA-DEMO8-FINAL-REPORT.md
R-and-D/
IMPLEMENTATION_PLAN.md
IMPLEMENTATION_SUMMARY.md
legacy-agents/
.CLAUDE.md
chief-architect.md
specialists/
code-implementer.md
docs-researcher.md
implementation-planner.md
legacy-deprecated/
CLAUDE_CODE_NATIVE_INSTALLER_V2.md
DIVINE_ORCHESTRATION_INSTALLER.md
README_INSTALLATION.md
legacy-docs/
01_philosophy.md
02_orchestration_workflow.md
03_knowledge_core.md
legacy-examples/
complex_task_orchestration.md
direct_specialist_usage.md
legacy-orchestration/
NATIVE_ORCHESTRATION_INSTALLER.md
ORCHESTRATION_COMPARISON.md
ORCHESTRATION_INSTALLER.md
setup.sh
ULTIMATE_CLAUDE_CODE_ORCHESTRATION.md
PHASE1_COMPLETE.md
PHASE2_PROGRESS.md
PROJECT_ANALYSIS.md
references/
claude-code-official-features-2025.md
claude-code-plugin-distribution-strategy.md
claude-code-quick-reference.md
integration-strategy.md
README.md
RESEARCH-SUMMARY.md
V2_COMPLETE.md
README.md
READY-TO-COMMIT.md
RELEASE-NOTES-V4.md
releases/
agentic-substrate-3.0.0.mcpb
agentic-substrate-3.1.0.mcpb
ResearchPack-Anthropic-Engineering-Philosophy.md
ResearchPack-v4.1.md
social-media-posts.md
TEST-REPORT.md
test-ResearchPack-LOW-SCORE.md
TROUBLESHOOTING.md
uninstall.sh
update.sh
V4-ENHANCEMENT-SUMMARY.md
V4-IMPLEMENTATION-PLAN.md
V4.1-RELEASE-NOTES.md
validate-install.sh
verify-installation.sh
WORKFLOW-FIXES-APPLIED.md
WORKFLOW-TEST-ANALYSIS.md
WORKFLOW-TEST-RESULTS.mdFAQ
claude-user-memory is a Claude Code plugin with hand-picked skills for agent orchestration work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is claude-user-memory?
- Research-first development system for Claude Code CLI No API hallucinations. No coding from stale training data. Research → Plan → Implement.
- How do I install claude-user-memory?
- Run these in Claude Code: . Then prompt normally.
- Does claude-user-memory auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is claude-user-memory free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.