parlant

parlant

LLM agents built for control. Designed for real-world use. Deployed in minutes.

Stars: 11816

Visit
 screenshot

Parlant is a structured approach to building and guiding customer-facing AI agents. It allows developers to create and manage robust AI agents, providing specific feedback on agent behavior and helping understand user intentions better. With features like guidelines, glossary, coherence checks, dynamic context, and guided tool use, Parlant offers control over agent responses and behavior. Developer-friendly aspects include instant changes, Git integration, clean architecture, and type safety. It enables confident deployment with scalability, effective debugging, and validation before deployment. Parlant works with major LLM providers and offers client SDKs for Python and TypeScript. The tool facilitates natural customer interactions through asynchronous communication and provides a chat UI for testing new behaviors before deployment.

README:

Parlant - AI Agent Framework

Finally, LLM agents that actually follow instructions

🌐 Website β€’ ⚑ Quick Start β€’ πŸ’¬ Discord β€’ πŸ“– Examples

Deutsch | EspaΓ±ol | franΓ§ais | ζ—₯本θͺž | ν•œκ΅­μ–΄ | PortuguΓͺs | Русский | δΈ­ζ–‡

PyPI Python 3.10+ License Discord GitHub Repo stars

Trending on TrendShift

🎯 The Problem Every AI Developer Faces

You build an AI agent. It works great in testing. Then real users start talking to it and...

  • ❌ It ignores your carefully crafted system prompts
  • ❌ It hallucinates responses in critical moments
  • ❌ It can't handle edge cases consistently
  • ❌ Each conversation feels like a roll of the dice

Sound familiar? You're not alone. This is the #1 pain point for developers building production AI agents.

⚑ The Solution: Stop Fighting Prompts, Teach Principles

Parlant flips the script on AI agent development. Instead of hoping your LLM will follow instructions, Parlant ensures it.

# Traditional approach: Cross your fingers 🀞
system_prompt = "You are a helpful assistant. Please follow these 47 rules..."

# Parlant approach: Ensured compliance βœ…
await agent.create_guideline(
    condition="Customer asks about refunds",
    action="Check order status first to see if eligible",
    tools=[check_order_status],
)

βœ… Blog: How Parlant Ensures Agent Compliance

Parlant gives you all the structure you need to build customer-facing agents that behave exactly as your business requires:

  • Journeys: Define clear customer journeys and how your agent should respond at each step.

  • Behavioral Guidelines: Easily craft agent behavior; Parlant will match the relevant elements contextually.

  • Tool Use: Attach external APIs, data fetchers, or backend services to specific interaction events.

  • Domain Adaptation: Teach your agent domain-specific terminology and craft personalized responses.

  • Canned Responses: Use response templates to eliminate hallucinations and guarantee style consistency.

  • Explainability: Understand why and when each guideline was matched and followed.

πŸš€ Get Your Agent Running in 60 Seconds

pip install parlant
import parlant.sdk as p

@p.tool
async def get_weather(context: p.ToolContext, city: str) -> p.ToolResult:
    # Your weather API logic here
    return p.ToolResult(f"Sunny, 72Β°F in {city}")

@p.tool
async def get_datetime(context: p.ToolContext) -> p.ToolResult:
    from datetime import datetime
    return p.ToolResult(datetime.now())

async def main():
    async with p.Server() as server:
        agent = await server.create_agent(
            name="WeatherBot",
            description="Helpful weather assistant"
        )

        # Have the agent's context be updated on every response (though
        # update interval is customizable) using a context variable.
        await agent.create_variable(name="current-datetime", tool=get_datetime)

        # Control and guide agent behavior with natural language
        await agent.create_guideline(
            condition="User asks about weather",
            action="Get current weather and provide a friendly response with suggestions",
            tools=[get_weather]
        )

        # Add other (reliably enforced) behavioral modeling elements
        # ...

        # πŸŽ‰ Test playground ready at http://localhost:8800
        # Integrate the official React widget into your app,
        # or follow the tutorial to build your own frontend!

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

That's it! Your agent is running with ensured rule-following behavior.

🎬 See It In Action

Parlant Demo

πŸ”₯ Why Developers Are Switching to Parlant

πŸ—οΈ Traditional AI Frameworks

⚑ Parlant

  • Write complex system prompts
  • Hope the LLM follows them
  • Debug unpredictable behaviors
  • Scale by prompt engineering
  • Cross fingers for reliability
  • Define rules in natural language
  • Ensured rule compliance
  • Predictable, consistent behavior
  • Scale by adding guidelines
  • Production-ready from day one

🎯 Perfect For Your Use Case

Financial Services Healthcare E-commerce Legal Tech
Compliance-first design HIPAA-ready agents Customer service at scale Precise legal guidance
Built-in risk management Patient data protection Order processing automation Document review assistance

πŸ› οΈ Enterprise-Grade Features

  • 🧭 Conversational Journeys - Lead the customer step-by-step to a goal
  • 🎯 Dynamic Guideline Matching - Context-aware rule application
  • πŸ”§ Reliable Tool Integration - APIs, databases, external services
  • πŸ“Š Conversation Analytics - Deep insights into agent behavior
  • πŸ”„ Iterative Refinement - Continuously improve agent responses
  • πŸ›‘οΈ Built-in Guardrails - Prevent hallucination and off-topic responses
  • πŸ“± React Widget - Drop-in chat UI for any web app
  • πŸ” Full Explainability - Understand every decision your agent makes

πŸ“ˆ Join 10,000+ Developers Building Better AI

Companies using Parlant:

Financial institutions β€’ Healthcare providers β€’ Legal firms β€’ E-commerce platforms

Star History Chart

🌟 What Developers Are Saying

"By far the most elegant conversational AI framework that I've come across! Developing with Parlant is pure joy." β€” Vishal Ahuja, Senior Lead, Customer-Facing Conversational AI @ JPMorgan Chase

πŸƒβ€β™‚οΈ Quick Start Paths

🎯 I want to test it myself β†’ 5-minute quickstart
πŸ› οΈ I want to see an example β†’ Healthcare agent example
πŸš€ I want to get involved β†’ Join our Discord community

🀝 Community & Support

πŸ“„ License

Apache 2.0 - Use it anywhere, including commercial projects.


Ready to build AI agents that actually work?

⭐ Star this repo β€’ πŸš€ Try Parlant now β€’ πŸ’¬ Join Discord

Built with ❀️ by the team at Emcie

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for parlant

Similar Open Source Tools

For similar tasks

For similar jobs