Directory MCP server

TCAM Memory System

Resilient 4-Layer Memory Architecture for TCAM v1.4 (Triadic Cognitive Augmentation Model)

Overview

The TCAM Memory System implements a fault-tolerant memory architecture where each layer operates independently, ensuring that system failures in one layer do not cascade to others. Memory operations are handled by a dedicated Memory Service running on Qwen 3.5 9B (local LLM).

Architecture

Four Independent Layers

• L1: Chronicle - Immutable historical record (file system, markdown)
• L2: Active Stream - Volatile working memory (Cloud LLM context + Redis)
• L3: Hive Mind - Semantic memory (Qdrant vector DB + Mem0)
• L4: Agent Codex - Personal knowledge base (file system, markdown)

Memory Service

Dedicated process running on Qwen 3.5 9B for:

• Truth extraction from dialogue
• Chronicle inscription
• Hive Mind indexing
• Agent Codex updates
• Sleeping cycle orchestration

Technology Stack

• TypeScript/Node.js - Core implementation
• Qwen 3.5 9B - Local LLM for memory operations
• Mem0 - Automatic fact extraction
• Qdrant - Vector database for semantic search
• Redis - Fast state persistence (LangGraph checkpointer)
• LangGraph - Multi-agent orchestration
• Jest - Testing framework
• fast-check - Property-based testing

Project Structure

.
├── src/                    # Source code
├── tests/                  # Test files
├── data/                   # Chronicle storage
├── codex/                  # Agent Codex (L4)
├── docs/                   # Documentation
└── .kiro/specs/           # Specification documents

Getting Started

Prerequisites

• Node.js 18+
• Ollama (for Qwen 3.5 9B)
• Docker (for Qdrant and Redis)

Installation

# Install dependencies
npm install --legacy-peer-deps

# Pull Qwen 3.5 9B model
ollama pull qwen2.5:9b-instruct-q4_K_M

# Pull embedding model
ollama pull nomic-embed-text

# Start Qdrant (using setup script)
# Windows PowerShell:
.\scripts\setup-qdrant.ps1

# Linux/Mac:
bash scripts/setup-qdrant.sh

# Or manually with Docker:
docker run -d --name qdrant -p 6333:6333 -p 6334:6334 -v qdrant_storage:/qdrant/storage qdrant/qdrant

# Start Redis
docker run -d --name redis -p 6379:6379 redis

# Build and install globally
npm run build
npm install -g . --legacy-peer-deps

CLI Usage

# Interactive main menu
anots

# Real-time monitoring dashboard (Terminal UI)
anots dashboard

# Chat with Axiom (TCAM Node C)
anots axiom

# Start MCP server (19 tools for IDE integration)
anots mcp:start

# Start REST API server
anots api:start

# Start API with Axiom chat endpoint
anots api:start --axiom

# Search memory
anots memory:search "your query"

# Import conversation (JSON/Markdown)
anots import conversation.json --type general

# System status
anots status

# Configuration wizard
anots setup

# Show all commands
anots --help

Dashboard Features

The Terminal UI dashboard (anots dashboard) provides:

• Real-time memory layer health monitoring
• System statistics (chapters, sessions, memories)
• Activity log with timestamps
• Keyboard shortcuts (F1-F3, R, Q)
• Auto-refresh every 2 seconds
• Cyberpunk aesthetic with 90s BBS vibes

Verify Setup

# Check Qdrant
curl http://localhost:6333/health

# Check Redis
redis-cli ping

# Check Ollama
ollama list

Development

# Build
npm run build

# Run tests
npm test

# Run tests with coverage
npm run test:coverage

# Lint
npm run lint

# Format code
npm run format

Importing Conversations

Import large conversation files into the ANOTS memory system:

# Import Ubik conversation
npm run import -- data/import/conversation.json --type ubik

# Import Axiom conversation
npm run import -- data/import/conversation.md --type axiom

# Preview import without writing (dry run)
npm run import -- data/import/conversation.json --dry-run

Shortened. The full README is on GitHub.