Installation

Installation

Parlant (available on both GitHub and PyPI) works on multiple platforms (Windows, Mac, and Linux), so you should find the installation to be nice and easy.

Please note that Python 3.10 and up is required.

pip install parlant

Once installed, choose your provider and run the server. Here's an example with OpenAI:

export OPENAI_API_KEY="..."
parlant-server run --openai

Parlant supports multiple providers, such as OpenAI, Gemini, Anthropic, DeepSeek, and multiple open-source model APIs (such as TogetherAI and Cerebras). For a full and updated list of supported providers and how to use them, please explore the help section.

parlant-server run --help

Verifying Your Installation

To test your installation, head over to http://localhost:8800 and start a new session with the default agent (a clean-slate model). You can configure this default agent or add more agents later.

Creating Your First Guideline

While the server is running in another terminal, try adding a guideline for the default agent using the CLI client, to see how it responds in a new conversation session.

1. # Get the default agent's ID from this list
   parlant agent list

   parlant guideline create \
         --tag agent:<INSERT_AGENT_ID_HERE>
         --condition "the user greets you" \
         --action "offer a refreshing drink"

2. Now head over to http://localhost:8800, start a new session, and greet the agent. You should expect to be offered a refreshing drink!

Installing Client SDK(s)

For creating a frontend app that interacts with the Parlant server, we recommend installing our native client SDKs. We currently support Python and TypeScript (also works with JavaScript).

# For building a frontend client in Python
pip install parlant-client
# For building a frontend client in TypeScript/JavaScript
npm install parlant-client

For other languages—they are coming soon! Meanwhile you can use the REST API directly.