Nagaagent
A simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, multi-agent collaboration, and seamless tool integration.
What is Nagaagent?
Nagaagent is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, multi-agent collaboration, and seamless tool integration.
A simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, multi-agent collaboration, and seamless tool integration.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A simple yet powerful agent framework for personal assistant
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx nagaagentConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Nagaagent
NagaAgent is an open-source Python agent framework that combines a conversational AI frontend with a multi-agent backend supporting MCP tools, knowledge graph memory via Neo4j, voice interaction, and IoT control via MQTT. It acts as a personal assistant hub where multiple specialized sub-agents collaborate on tasks, with each interaction enriching a persistent knowledge graph for future retrieval. Developers building personal AI assistants or experimenting with multi-agent orchestration can use NagaAgent as a full-stack starting point that already integrates MCP tool calling, RAG memory, streaming tool invocation, and voice/Live2D character support.
Prerequisites
- Python 3.11 (the project requires >=3.11, <3.12 strictly)
- Node.js 18+ and npm (for the frontend)
- uv package manager recommended (pip also works)
- An API key for an OpenAI-compatible LLM provider (DeepSeek, Qwen, Ollama) or Anthropic
- Optional: Neo4j database for knowledge graph memory, Docker recommended
Clone the repository
Clone NagaAgent from GitHub and navigate into the project directory.
git clone https://github.com/RTGS2017/NagaAgent.git
cd NagaAgentInstall backend dependencies
Install Python dependencies using uv (recommended) or pip. Python 3.11 specifically is required — 3.12+ is not yet supported.
# With uv (recommended)
uv sync
# Or with pip
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtConfigure your LLM API credentials
Copy the example config and edit it with your LLM provider credentials. The framework supports OpenAI-compatible APIs (DeepSeek, Qwen, Ollama) and Anthropic native format.
cp config.json.example config.json
# Then edit config.json:
{
"api": {
"api_key": "your-api-key",
"base_url": "https://api.deepseek.com",
"model": "deepseek-v3.2",
"api_format": "openai"
}
}Install frontend dependencies
Navigate into the frontend directory and install the Node.js dependencies for the chat UI.
cd frontend && npm install && cd ..Start the full stack
Launch the frontend development server. The backend services (API on port 8000, agent on 8001, MCP on 8003) start automatically.
cd frontend && npm run devEnable Neo4j knowledge graph (optional)
For persistent multi-session memory using knowledge graph extraction, start a Neo4j instance and add connection details to config.json.
docker run -d --name neo4j -p 7687:7687 -p 7474:7474 \
-e NEO4J_AUTH=neo4j/yourpassword neo4j:latest
# Then in config.json:
# "grag": { "neo4j_uri": "bolt://localhost:7687", "neo4j_user": "neo4j", "neo4j_password": "yourpassword" }Nagaagent Examples
Client configuration
Minimal config.json for NagaAgent using DeepSeek as the LLM backend.
{
"api": {
"api_key": "sk-your-deepseek-key",
"base_url": "https://api.deepseek.com",
"model": "deepseek-v3.2",
"api_format": "openai"
}
}Prompts to try
Example interactions with the NagaAgent personal assistant.
- "What is the weather in Tokyo right now?"
- "Search the web for the latest news about AI agents and summarize"
- "Remember that I prefer dark mode and short summaries for future sessions"
- "Control the living room lights via MQTT and turn them to 50% brightness"
- "Analyze this image and describe what you see"Troubleshooting Nagaagent
uv sync fails with Python version error
NagaAgent strictly requires Python 3.11 (not 3.12+). Install Python 3.11 via pyenv: pyenv install 3.11.9 && pyenv local 3.11.9, then re-run uv sync.
Frontend starts but cannot reach the backend API
The backend API server starts on port 8000. Check that no other service is using this port with: lsof -i :8000. Also confirm all Python dependencies installed without errors before starting the frontend.
Knowledge graph memory is not persisting between sessions
Neo4j must be running and the grag config block in config.json must have the correct uri, user, and password. Verify Neo4j is accessible at bolt://localhost:7687 with: cypher-shell -u neo4j -p yourpassword 'RETURN 1'.
Frequently Asked Questions about Nagaagent
What is Nagaagent?
Nagaagent is a Model Context Protocol (MCP) server that simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, multi-agent collaboration, and seamless tool integration. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Nagaagent?
Follow the installation instructions on the Nagaagent GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Nagaagent?
Nagaagent works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Nagaagent free to use?
Yes, Nagaagent is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.
Nagaagent Alternatives — Similar Coding Agents Servers
Looking for alternatives to Nagaagent? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Nagaagent in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Nagaagent?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.