unsubbed.co

Parlant

The conversational control layer for customer-facing AI agents

Apache-2.0 Free emcie-co/parlant · 18K parlant.io Python 1 deploy option

Overview

The conversational control layer for customer-facing AI agents - Parlant is a context-engineering framework optimized for controlling customer interactions. The conversational control layer for customer-facing AI agents The project has 18K+ GitHub stars and is licensed under Apache-2.0.

Key Features

Source: GitHub README

  • Guidelines —
  • Relationships —
  • Journeys —
  • Canned Responses —
  • Tools —
  • Glossary —
  • Explainability —

Getting Started

Source: GitHub README

pip install parlant
import parlant.sdk as p

async with p.Server():
    agent = await server.create_agent(
        name="Customer Support",
        description="Handles customer inquiries for an airline",
    )

    # Evaluate and call tools only under the right conditions
    expert_customer = await agent.create_observation(
        condition="customer uses financial terminology like DTI or amortization",
        tools=[research_deep_answer],
    )

    # When the expert observation holds, always respond
    # with depth. Set the guideline to automatically match
    # whenever the observation it depends on holds...
    expert_answers = await agent.create_guideline(
        matcher=p.MATCH_ALWAYS,
        action="respond with technical depth",
        dependencies=[expert_customer],
    )

    beginner_answers = await agent.create_guideline(
        condition="customer seems new to the topic",
        action="simplify and use concrete examples",
    )

    # When both match, beginners wins. Neither expert-level
    # tool-data nor instructions can enter the agent's context.
    await beginner_answers.exclude(expert_customer)

Normalized Features

Source: tool-features-normalized.json

charts, pip.

Deploy

Docker

Self-host with Docker Compose

Coolify

One-click via Coolify panel
elestio

Elestio

Managed hosting from $9/mo
pikapods

PikaPods

Simple managed hosting

Features

Analytics & Reporting

  • Charts & Graphs

Category

AI & Machine Learning (93)

Replaces

chatbase
Chatbase
6 tools
decagon
Decagon
5 tools
Rasa
4 tools
voiceflow
Voiceflow
100 tools

Related AI & Machine Learning Tools

View all 93 →

OpenClaw

320K

Personal AI assistant you run on your own devices. 25+ messaging channels, voice, cron jobs, browser control, and a skills system.

ai ml MIT
O

Ollama

166K

Run open-source LLMs locally — get up and running with DeepSeek, Qwen, Gemma, Llama, and more with a single command.

ai ml MIT

Open WebUI

128K

Run AI on your own terms. Connect any model, extend with code, protect what matters—without compromise.

ai assistants MIT Easy to deploy

OpenCode

124K

The open-source AI coding agent — free models included, or connect Claude, GPT, Gemini, and 75+ other providers.

ai ml MIT

Zed

77K

A high-performance code editor built from scratch in Rust by the creators of Atom — GPU-accelerated rendering, built-in AI, real-time multiplayer, and no Electron.

ai ml

OpenHands

69K

The open-source, model-agnostic platform for cloud coding agents — automate real software engineering tasks with sandboxed execution, SDK, CLI, and enterprise-grade security.

ai ml