# Start the MCP server
python src/agent/host.py

# Required
Python 3.10+
Ollama (for embeddings: ollama pull embeddinggemma)

# Optional
UV package manager (faster than pip)

# Clone the repository
git clone https://github.com/MasihMoafi/A-Modular-Kingdom.git
cd A-Modular-Kingdom

# Install dependencies
uv sync
# or: pip install -r requirements.txt

# Pull required Ollama model
ollama pull embeddinggemma

# Start host.py MCP server
python src/agent/host.py

// Add to claude_desktop_config.json
{
  "mcpServers": {
    "a-modular-kingdom": {
      "command": "python",
      "args": ["/full/path/to/A-Modular-Kingdom/src/agent/host.py"]
    }
  }
}

# Use the included chat interface
python src/agent/main.py

# Connect via MCP in your own agent
from mcp import StdioServerParameters

server_params = StdioServerParameters(
    command="python",
    args=["/path/to/host.py"]
)
# Use with ToolCollection.from_mcp(server_params)

# Via MCP tool
query_knowledge_base(
    query="How does authentication work?",
    version="v2",  # or "v1", "v3"
    doc_path="./src"  # optional
)

# Save with explicit scope
save_memory(content="Always validate user input", scope="global_rules")

# Or use prefix shortcuts
save_memory(content="#global:rule:Never use eval()")
save_memory(content="#project:context:Uses FastAPI backend")

# Auto-inference from keywords
save_memory(content="User prefers Python 3.12")  # → global_preferences

# Search with priority (global → project)
search_memories(query="coding standards", top_k=5)

# Install with sentence-transformers (no Ollama required)
pip install rag-mem[local]

# Set embedding provider (add to your shell profile or script)
export MEMORY_MCP_EMBED_PROVIDER=sentence-transformers
export MEMORY_MCP_EMBED_MODEL=all-MiniLM-L6-v2

from memory_mcp.config import Settings
from memory_mcp.rag import RAGPipeline
from memory_mcp.memory import MemoryStore

# RAG - index and search any codebase
pipeline = RAGPipeline(Settings(), document_paths=["./src"])
pipeline.index()
results = pipeline.search("how does authentication work")

# Memory - persistent storage across sessions
store = MemoryStore(Settings())
store.add("User prefers dark mode")
results = store.search("preferences")

memory-mcp init                      # Initialize config
memory-mcp serve --docs ./documents  # Start MCP server
memory-mcp index ./path/to/files     # Index documents

pip install rag-mem
ollama pull nomic-embed-text
# No env vars needed - Ollama is the default

{
  "mcpServers": {
    "a-modular-kingdom": {
      "command": "python",
      "args": ["/path/to/src/agent/host.py"]
    }
  }
}

// gemini-extension.json
{
  "mcpServers": {
    "unified_knowledge_agent": {
      "command": "python",
      "args": ["/path/to/src/agent/host.py"]
    }
  }
}

from smolagents import ToolCallingAgent, ToolCollection
from mcp import StdioServerParameters

# Connect to MCP server
params = StdioServerParameters(
    command="python",
    args=["/path/to/host.py"]
)

with ToolCollection.from_mcp(params) as tools:
    agent = ToolCallingAgent(tools=list(tools.tools))
    result = agent.run("Search the codebase for auth logic")

┌─────────────────────────────────────┐
│     Your AI Application             │
│  (Agents, Chatbots, Workflows)      │
└────────────┬────────────────────────┘
             │ MCP Protocol
┌────────────▼────────────────────────┐
│      A-Modular-Kingdom              │
│  ┌─────────┐ ┌─────────┐ ┌────────┐│
│  │   RAG   │ │ Memory  │ │ Tools  ││
│  │ V1/V2/V3│ │ Scoped  │ │ 8+     ││
│  └─────────┘ └─────────┘ └────────┘│
│           host.py (MCP Server)      │
└─────────────────────────────────────┘

# Run all tests
pytest tests/ -v

# Run specific test suites
pytest tests/test_rag_v2.py -v
pytest tests/test_rag_v3.py -v
pytest tests/test_memory_global.py -v

# Run benchmarks
python tests/benchmark_rag.py

docker build -f Dockerfile.test -t rag-mem-test .
docker run --rm rag-mem-test

# Fork and clone
git clone https://github.com/MasihMoafi/A-Modular-Kingdom.git
cd A-Modular-Kingdom

# Create branch
git checkout -b feature/your-feature

# Install dev dependencies
uv sync

# Make changes and test
pytest tests/

# Commit with descriptive message
git commit -m "feat: add new tool"

# Push and create PR
git push origin feature/your-feature