Chanakya Voice Assistant

v1.0.0Communicationstable

Chanakya is an advanced, open-source, and self-hostable voice assistant designed for privacy, power, and flexibility. It leverages local AI/ML models to ensure your data stays with you. It Integrates with 1000+ third-party MCP servers including Home

chanakya-local-friendmcpai-integration
Share:
215
Stars
0
Downloads
0
Weekly
0/5

What is Chanakya Voice Assistant?

Chanakya Voice Assistant is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to chanakya is an advanced, open-source, and self-hostable voice assistant designed for privacy, power, and flexibility. it leverages local ai/ml models to ensure your data stays with you. it integrates ...

Chanakya is an advanced, open-source, and self-hostable voice assistant designed for privacy, power, and flexibility. It leverages local AI/ML models to ensure your data stays with you. It Integrates with 1000+ third-party MCP servers including Home

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Chanakya is an advanced, open-source, and self-hostable voic

Use Cases

Build privacy-focused voice assistant for local deployment.
Integrate with 1000+ MCP servers for extended functionality.
Run completely locally with personal data protection.
Rishabh-Bajpai

Maintainer

LicenseNOASSERTION
Languagepython
Versionv1.0.0
UpdatedMay 11, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx chanakya-local-friend

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Chanakya Voice Assistant

Chanakya Local Friend is an open-source, fully self-hostable voice assistant framework built on Python that runs entirely on your local machine using LM Studio or any OpenAI-compatible model server — so your data never leaves your hardware. It orchestrates a network of intelligent agents through a pre-configured set of 14 MCP tools covering web search, code execution, filesystem access, Git, weather, maps, timers, and more. Developers and privacy-conscious users who want a capable, offline-first AI assistant with MCP extensibility and agent-to-agent (A2A) communication deploy Chanakya as their local alternative to cloud-hosted assistants.

Prerequisites

  • Python 3.11+ installed
  • LM Studio (or any OpenAI-compatible local model server) running at a known base URL
  • Git installed to clone the repository
  • uv or pip for Python package management
  • An MCP-compatible client or the built-in Chanakya web interface
1

Clone the repository and create a virtual environment

Clone the Chanakya repository and set up an isolated Python 3.11 virtual environment for the project.

git clone https://github.com/Rishabh-Bajpai/Chanakya-Local-Friend.git
cd Chanakya-Local-Friend
python3.11 -m venv .venv
source .venv/bin/activate
2

Install core dependencies

Install the main package and the two sub-application packages (AI Router and Conversation Layer) in editable mode.

python -m pip install --upgrade pip
python -m pip install -e .[dev]
python -m pip install -e ./apps/AI-Router-AIR
python -m pip install -e ./apps/chanakya_conversation_layer
3

Configure environment variables

Create a .env file with your local model server details, database path, and service ports. Point OPENAI_BASE_URL to your LM Studio instance.

OPENAI_BASE_URL=http://127.0.0.1:1234/v1
OPENAI_API_KEY=lm-studio
DATABASE_URL=sqlite:////path/to/chanakya.db
CHANAKYA_CORE_AGENT_BACKEND=local
CHANAKYA_PORT=5513
AIR_SERVER_PORT=5512
CONVERSATION_LAYER_PORT=5514
4

Start the Chanakya stack

Use the provided startup script to launch the core services. Optionally include A2A (agent-to-agent) components for multi-agent workflows.

# Core services only
./scripts/start_chanakya_air.sh core

# Core + A2A components
./scripts/start_chanakya_air.sh core+a2a
5

Configure MCP tools

The 14 built-in MCP tools (web search, code execution, filesystem, Git, weather, maps, timers, etc.) are configured in mcp_config_file.json. Edit this file to enable, disable, or add MCP server integrations, then restart the stack.

6

Add to Claude Desktop (optional)

If you want to use Chanakya's MCP capabilities from Claude Desktop, add the server to your configuration.

{
  "mcpServers": {
    "chanakya-local-friend": {
      "command": "npx",
      "args": ["chanakya-local-friend"],
      "env": {
        "OPENAI_BASE_URL": "http://127.0.0.1:1234/v1",
        "OPENAI_API_KEY": "lm-studio"
      }
    }
  }
}

Chanakya Voice Assistant Examples

Client configuration

claude_desktop_config.json entry for connecting to a running Chanakya Local Friend instance.

{
  "mcpServers": {
    "chanakya-local-friend": {
      "command": "npx",
      "args": ["chanakya-local-friend"],
      "env": {
        "OPENAI_BASE_URL": "http://127.0.0.1:1234/v1",
        "OPENAI_API_KEY": "lm-studio"
      }
    }
  }
}

Prompts to try

Example prompts leveraging Chanakya's built-in MCP tools running entirely locally.

- "Search the web for the latest news on open-source LLMs."
- "Run this Python script locally and show me the output."
- "What's the weather in Berlin right now?"
- "List the files in my ~/Documents folder."
- "Set a timer for 25 minutes and notify me when it's done."

Troubleshooting Chanakya Voice Assistant

Connection refused when the stack tries to reach the local model server

Ensure LM Studio (or your OpenAI-compatible server) is running and listening on the URL you set in OPENAI_BASE_URL. The default LM Studio address is http://127.0.0.1:1234/v1.

MCP tools are not available after changing mcp_config_file.json

Changes to mcp_config_file.json only take effect after restarting the Chanakya stack. Stop all services and run the startup script again.

Package install errors for the sub-applications

Ensure you are using Python 3.11 specifically (not 3.12+), as some dependencies require it. Activate the .venv and confirm with 'python --version' before running pip install.

Frequently Asked Questions about Chanakya Voice Assistant

What is Chanakya Voice Assistant?

Chanakya Voice Assistant is a Model Context Protocol (MCP) server that chanakya is an advanced, open-source, and self-hostable voice assistant designed for privacy, power, and flexibility. it leverages local ai/ml models to ensure your data stays with you. it integrates with 1000+ third-party mcp servers including home It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Chanakya Voice Assistant?

Follow the installation instructions on the Chanakya Voice Assistant GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Chanakya Voice Assistant?

Chanakya Voice Assistant works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Chanakya Voice Assistant free to use?

Yes, Chanakya Voice Assistant is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "chanakya-local-friend": { "command": "npx", "args": ["-y", "chanakya-local-friend"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Chanakya Voice Assistant?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides