# parlant
**Repository Path**: cloud-aios/parlant
## Basic Information
- **Project Name**: parlant
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: develop
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-09-19
- **Last Updated**: 2025-09-19
## Categories & Tags
**Categories**: Uncategorized
**Tags**: ๅๅ่ฎพ่ฎก
## README
## ๐ฏ The Problem Every AI Developer Faces
You build an AI agent. It works great in testing. Then real users start talking to it and...
- โ It ignores your carefully crafted system prompts
- โ It hallucinates responses in critical moments
- โ It can't handle edge cases consistently
- โ 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.
## โก 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**.
```python
# Traditional approach: Cross your fingers ๐ค
system_prompt = "You are a helpful assistant. Please follow these 47 rules..."
# Parlant approach: Ensured compliance โ
await agent.create_guideline(
condition="Customer asks about refunds",
action="Check order status first to see if eligible",
tools=[check_order_status],
)
```
[โ
Blog: How Parlant Ensures Agent Compliance](https://www.parlant.io/blog/how-parlant-guarantees-compliance)
#### Parlant gives you all the structure you need to build customer-facing agents that behave exactly as your business requires:
- **[Journeys](https://parlant.io/docs/concepts/customization/journeys)**:
Define clear customer journeys and how your agent should respond at each step.
- **[Behavioral Guidelines](https://parlant.io/docs/concepts/customization/guidelines)**:
Easily craft agent behavior; Parlant will match the relevant elements contextually.
- **[Tool Use](https://parlant.io/docs/concepts/customization/tools)**:
Attach external APIs, data fetchers, or backend services to specific interaction events.
- **[Domain Adaptation](https://parlant.io/docs/concepts/customization/glossary)**:
Teach your agent domain-specific terminology and craft personalized responses.
- **[Canned Responses](https://parlant.io/docs/concepts/customization/canned-responses)**:
Use response templates to eliminate hallucinations and guarantee style consistency.
- **[Explainability](https://parlant.io/docs/advanced/explainability)**:
Understand why and when each guideline was matched and followed.
## ๐ Get Your Agent Running in 60 Seconds
```bash
pip install parlant
```
```python
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, 72ยฐF 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
# ...
# ๐ 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.
## ๐ฌ See It In Action
## ๐ฅ Why Developers Are Switching to Parlant
|
### ๐๏ธ **Traditional AI Frameworks**
|
### โก **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
|
## ๐ฏ 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 |
## ๐ ๏ธ Enterprise-Grade Features
- **๐งญ Conversational Journeys** - Lead the customer step-by-step to a goal
- **๐ฏ Dynamic Guideline Matching** - Context-aware rule application
- **๐ง Reliable Tool Integration** - APIs, databases, external services
- **๐ Conversation Analytics** - Deep insights into agent behavior
- **๐ Iterative Refinement** - Continuously improve agent responses
- **๐ก๏ธ Built-in Guardrails** - Prevent hallucination and off-topic responses
- **๐ฑ React Widget** - [Drop-in chat UI for any web app](https://github.com/emcie-co/parlant-chat-react)
- **๐ Full Explainability** - Understand every decision your agent makes
## ๐ Join 10,000+ Developers Building Better AI
**Companies using Parlant:**
_Financial institutions โข Healthcare providers โข Legal firms โข E-commerce platforms_
[](https://star-history.com/#emcie-co/parlant&Date)
## ๐ What Developers Are Saying
> _"By far the most elegant conversational AI framework that I've come across! Developing with Parlant is pure joy."_ **โ Vishal Ahuja, Senior Lead, Customer-Facing Conversational AI @ JPMorgan Chase**
## ๐โโ๏ธ Quick Start Paths
## ๐ค Community & Support
- ๐ฌ **[Discord Community](https://discord.gg/duxWqxKk6J)** - Get help from the team and community
- ๐ **[Documentation](https://parlant.io/docs/quickstart/installation)** - Comprehensive guides and examples
- ๐ **[GitHub Issues](https://github.com/emcie-co/parlant/issues)** - Bug reports and feature requests
- ๐ง **[Direct Support](https://parlant.io/contact)** - Direct line to our engineering team
## ๐ License
Apache 2.0 - Use it anywhere, including commercial projects.
---
**Ready to build AI agents that actually work?**
โญ **Star this repo** โข ๐ **[Try Parlant now](https://parlant.io/)** โข ๐ฌ **[Join Discord](https://discord.gg/duxWqxKk6J)**
_Built with โค๏ธ by the team at [Emcie](https://emcie.co)_
