OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Kalliope

Kalliope is a Python framework for building a personal assistant by linking input signals—such as spoken commands, scheduled events, MQTT messages or GPIO events—to modular actions called neurons.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Kalliope — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Kalliope when you want to define an assistant around event-to-action flows, especially for voice interaction or home automation on Debian-based Linux.

Who it is for

  • People building a voice-controlled personal assistant on Debian-based Linux.
  • Home automation builders who want spoken or event-based triggers to run modular actions.
  • Developers who want to compose existing neurons or create custom assistant modules.

Documented uses

  • Connect a spoken order to one or more assistant actions.
  • Trigger actions from scheduled events, MQTT messages or GPIO events.
  • Assemble an assistant from existing neurons without writing code.
  • Write and add a custom neuron for a specialized task.
Before you choose

Requirements & limits

The project is open source under the GPL-3.0 license.

  • Voice interaction requires a microphone, according to the project README.
  • The project says it runs on Debian-based Linux distributions, including Raspberry Pi.
  • Existing neurons can be composed without code; specialized functionality can be added by writing a neuron.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use a starter kit to start a Kalliope assistant

Follow a starter kit’s existing configuration and brain examples to start Kalliope.

Before you start

  • Follow Kalliope’s installation documentation.
  • Have the starter kit repository URL.

Steps

  1. Clone the starter kit repository with the command below.

    Documented command
    git clone

  2. Change into the cloned starter kit directory with cd cloned_starter_kit.

  3. Start Kalliope with kalliope start.

Expected outcome

Kalliope starts using the starter kit’s configuration and brain examples.

Guide limitations

  • Starter kits provide configurations and examples for particular languages; the documented page lists Czech, English, French, German, and Italian.
  • The starter kit instructions require Kalliope to be installed first.
Documentation 1 ↗Documentation 2 ↗
Source-based practical guide

Define a simple voice-order-to-neuron mapping

Configure an example mapping from the vocal order “say hello” to Kalliope’s say neuron.

Before you start

  • A Kalliope project configuration in YAML.
  • Kalliope runs on Debian-based Linux distributions, including Raspberry Pi; the documentation says a microphone is needed.

Steps

  1. Add a brain entry named Hello-world.

  2. Set its signal order to say hello.

  3. Attach the say neuron and set its message to Hello world!.

Expected outcome

The configuration describes a vocal order connected to a neuron that says “Hello world!”

Guide limitations

  • The example documents the configuration only; it does not specify how to run this configuration or verify speech recognition and output.
  • The documented platform scope is Debian-based Linux, including Raspberry Pi.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
kalliope-project/kalliope · Official homepage title · retained in its source language
How we review sourcesSuggest a correction