Chanakya is an advanced, open-source, and self-hostable voice assistant designed for privacy, power, and flexibility. It can leverage local AI/ML models to help keep data under your control and supports connecting to third-party MCP servers through configuration. A network of intelligent agents collaborates to complete tasks, provide insights, and maintain ongoing workflows.
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 Assistant.
2026-10-28
Estrellas
212
Herramientas
—
Disponibilidad
—
Chanakya Flask app on http://127.0.0.1:5513
AIR service on http://127.0.0.1:5512
Conversation layer on http://127.0.0.1:5514
Optional A2A bridge on http://127.0.0.1:18770
The most important setup rule is simple: create the repo-root .env and mcp_config_file.json before starting the stack. The startup scripts read those files immediately.
Quick Start
1. Prerequisites
Python 3.11 is the safest default for local development.
python3.11 -m venv available on your machine.
uvx available if you use the example MCP config as-is.
If you prefer conda for day-to-day development, that is still fine. The only hard requirement is that the systemd installer expects a repo-root .venv.
3. Create .env before starting anything
Start from the checked-in template:
cp .env.example .env
Then edit .env for your machine and credentials. Use .env.example as the source of truth for supported variables.
The startup scripts source this file automatically and export ENV_FILE_PATH for child processes. If this file is missing, the services start without your intended runtime configuration.
4. Create mcp_config_file.json before starting anything
Then edit it for your environment if needed. Use mcp_config_file.example.json as the source of truth for the default MCP server layout. The checked-in example includes both local Python-backed MCP servers and uvx-launched servers.
5. Start the stack
Core stack:
./scripts/start_chanakya_air.sh core
Core stack plus A2A components:
./scripts/start_chanakya_air.sh core+a2a
Open the main UI at http://127.0.0.1:5513.
6. Stop the stack
./scripts/stop_chanakya_air.sh
What The Startup Script Does
./scripts/start_chanakya_air.sh starts the current local stack in this order:
AIR service
Chanakya conversation layer
Optional A2A services for core+a2a
Chanakya Flask app
It also:
reads .env from the repo root unless ENV_FILE_PATH is already set
writes PID files and logs under build/runtime/
prints the service URLs after startup
Use ./scripts/stop_chanakya_air.sh to stop everything cleanly.
Required Configuration
.env
Start from .env.example and copy it into place:
cp .env.example .env
Then edit .env with your local values. Replace all placeholder values marked with <...>:
Variable
Description
Example
OPENAI_BASE_URL
Your LM Studio or OpenAI-compatible server endpoint
http://127.0.0.1:1234/v1
OPENAI_API_KEY
API key for your model server
lm-studio (or your key)
DATABASE_URL
Path to your SQLite database
sqlite:////home/user/chanakya_data/chanakya.db
The defaults in .env.example use placeholder values and will not work out of the box.
Common variables used in local development include:
apps/AI-Router-AIR/: FastAPI service used by the local stack on port 5512
apps/chanakya_conversation_layer/: separate conversation-layer package and tests
scripts/: startup, shutdown, database, and service-management scripts
If you are changing runtime behavior, the most relevant files are usually:
apps/chanakya/core/app.py
apps/chanakya/core/chat_service.py
apps/chanakya/core/store.py
apps/chanakya/agent/runtime.py
apps/chanakya/templates/
apps/chanakya/static/js/air_voice.js
Common Problems
The stack starts but behaves incorrectly
Check these first:
.env exists at the repo root and has the expected model credentials.
mcp_config_file.json exists at the repo root.
The virtual environment includes all three editable installs.
build/runtime/*.log shows all services stayed up after startup.
A service starts with the wrong environment
The startup scripts source the repo-root .env automatically. If you want a different env file, set ENV_FILE_PATH before invoking the script.
MCP tools are missing
Confirm that:
the tool exists in mcp_config_file.json
its command is installed on your machine
you restarted the stack after editing the MCP config
Related Files
mcp_config_file.example.json: starting point for MCP server configuration
scripts/start_chanakya_air.sh: standard local stack entrypoint
scripts/stop_chanakya_air.sh: standard shutdown entrypoint
scripts/install-autostart-ubuntu.sh: systemd installer for Linux
C
Chanakya Local Friend
samosa-ai-com·212 estrellas·
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 Assistant.
Herramientas
Herramientas
Aún no hay lista de herramientas. Los servidores remotos la reciben tras la primera comprobación de estado.
Preguntas frecuentes
Preguntas
¿Cómo instalo Chanakya Local Friend?
Copia en esta página la configuración stdio para Cursor, Claude Desktop, Claude Code o VS Code. Usa la instalación del publicador, no un proxy de PlugMCP.
Este registro no indica ninguna variable de entorno obligatoria.
¿Qué transporte usa Chanakya Local Friend?
Chanakya Local Friend se ejecuta localmente por stdio.
¿Cuándo se comprobó Chanakya Local Friend por última vez?
Última comprobación: 2026-10-28. 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 Assistant.