Skip to main content

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.

There are two modes you can choose to run the Parlant server:

  1. As a configurable server, controlled by a CLI and API
  2. Importing the SDK in a standalone script to create a runnable server

Start out by installing the parlant package:

pip install parlant

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

Configurable Server (CLI)​

parlant-server run

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

Standalone Script (SDK)​

Start out with the following code:

# my_parlant_server.py

import asyncio
import parlant.sdk as p

async def start_conversation_server():
  async with p.Server() as server:
    agent = await server.create_agent(
        name="Otto Carmen",
        description="You work at a car dealership",
    )

asyncio.run(start_conversation_server())

Then run the script:

python my_parlant_server.py

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​

Configurable Server (CLI)​

While the server is running in another terminal, try adding a global guideline using the CLI client, to see how your agent responds in a new conversation session. Note that a global guideline affects all of the agents in the server.

parlant guideline create --condition "the user greets you" --action "offer a refreshing drink"

Standalone Script (SDK)​

# my_parlant_server.py

import asyncio
import parlant.sdk as p

async def start_conversation_server():
  async with p.Server() as server:
    agent = await server.create_agent(
        name="Otto Carmen",
        description="You work at a car dealership",
    )

    # Add this:
    await agent.create_guideline(
        condition="the user greets you",
        action="offer a refreshing drink",
    )

asyncio.run(start_conversation_server())

Then re-run the script:

python my_parlant_server.py
  1. Now head over to http://localhost:8800, start a new session, and greet the agent. You should expect to be offered a refreshing drink!
Post installation demo

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.