parlant
A new customer-facing LLM-agent framework to increase accuracy and reliability
Stars: 1526
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 is an LLM-first conversational AI agent framework designed to give control freaks the precision they need over their AI agents. 🔧 🎛️ It's operated using an easy-to-use CLI 📟 and native client SDKs in Python and TypeScript 📦.
IMPORTANT NOTE: We're looking for more contributors to help get customer-facing agents under control! To be a part of this effort, join our Discord server and tell us about your relevant skills and how you wish to help.
Parlant is used to deliver complex AI agents that reliably follow your business rules in use cases such as:
- 🏦 Regulated financial services
- 🏥 Healthcare communications
- 📜 Legal assistance
- 🛡️ Compliance-focused use cases
- 🎯 Brand-sensitive customer service
- 🤝 Personal advocacy and representation
Developers and data-scientists are using Parlant to:
- 🤖 Create custom-tailored conversational agents quickly and easily
- 👣 Define behavioral guidelines for agents to follow (Parlant ensures they are followed reliably)
- 🛠️ Attach tools with specific guidance on how to properly use them in different contexts
- 📖 Manage their agents’ glossary to ensure strict interpretation of terms in a conversational context
- 👤 Add customer-specific information to deliver personalized interactions
Parlant transforms how AI agents make decisions in customer-facing use cases.
It moves beyond traditional prompt engineering and flow charts. Instead, you provide it with contextual atomic guidelines, and it adapts your instructions to each conversation in real-time. By intelligently matching and activating relevant behavioral guidelines for each specific context, your agents end up consistently following your business rules while maintaining much more natural conversations with your customers than you could achieve with predefined semantic graphs or flow charts.
graph TD
API(Parlant REST API) -->|React to Session Trigger| Engine[AI Response Engine]
Engine -->|Load Domain Terminology| GlossaryStore
Engine -->|Match Guidelines| GuidelineProposer
Engine -->|Infer & Call Tools| ToolCaller
Engine -->|Tailor Guided Message| MessageGeneratorWhen an agent needs to respond to a customer, Parlant's engine evaluates the situation, checks relevant guidelines, gathers necessary information through your tools, and continuously re-evaluates its approach based on your guidelines as new information emerges. When it's time to generate a message, Parlant implements self-critique mechanisms to ensure that the agent's responses precisely align with your intended behavior as given by the contextually-matched guidelines.
📚 More technical docs on the architecture and API are available under docs/.
Parlant comes pre-built with responsive session (conversation) management, a detection mechanism for incoherence and contradictions in guidelines, content-filtering, jailbreak protection, an integrated sandbox UI for behavioral testing, native API clients in Python and TypeScript, and other goodies.
$ pip install parlant
$ parlant-server
$ # Open the sandbox UI at http://localhost:8800 and play
Parlant is the right tool for the job if you're building an LLM-based chat agent, and:
- 🎯 Your use case places a high importance on behavioral precision and consistency, particularly in customer-facing scenarios
- 🔄 Your agent is expected to undergo continuous behavioral refinements and changes, and you need a way to implement those changes efficiently and confidently
- 📈 You're expected to maintain a growing set of behavioral guidelines, and you need to maintain them coherently and with version-tracking
- 💬 Conversational UX and user-engagmeent is an important concern for your use case, and you want to easily control the flow and tone of conversations
In a word: Guidance. 🧭🚦🤝
Parlant's engine revolves around solving one key problem: How can we reliably guide customer-facing agents to behave in alignment with our needs and intentions.
Hence Parlant's fundamentally different approach to agent building: Managed Guidelines:
$ parlant guideline create \
--agent-id MY_AGENT_ID \
--condition "the customer wants to return an item" \
--action "get the order number and item name and then help them return it"By giving structure to behavioral guidelines, and granularizing guidelines (i.e. making each behavioral guideline a first-class entity in the engine), Parlant's engine is able to offer unprecedented control, quality, and efficiency in building LLM-based agents:
- 🛡️ Reliability: Running focused self-critique in real-time, per guideline, to ensure it is actually followed
- 💡 Explainability: Providing feedback around its interpretation of guidelines in each real-life context, which helps in troubleshooting and improvement
- 🔧 Maintainability: Helping you maintain a coherent set of guidelines by detecting and alerting you to possible contradictions (gross or subtle) in your instructions
- Coherence checks: Catch conflicts by having Parlant evaluate new guidelines against existing ones before they're applied
- See changes instantly: Modify behavior on the fly by updating guidelines directly — no retraining or redeployment needed
- Track changes in Git: Manage agent behavior like code by storing configuration as JSON in your repo. Review, rollback, branch, and merge just like any other code
- Clean architecture: Separate concerns by keeping business logic in tools and conversation patterns in guidelines. Each piece does what it does best
- Reliable at scale: Parlant filters and selects guidelines per context, allowing you to scale your agent's complexity and use-cases while maintaining consistent, focused behavior
- Debug with ease: Troubleshoot effectively by tracing which guidelines were applied and why for any given response. leveraging Parlant's highly descriptive and explainable log outputs
- Test before deploy: Validate changes using the built-in chat UI to test new behaviors before they reach customers
- OpenAI (also via Azure)
- Gemini
- Meta Llama 3 (via Together AI or Cerebras)
- Anthropic (also via AWS Bedrock)
To start learning and building with Parlant, visit our documentation portal.
Need help? Ask us anything on Discord. We're happy to answer questions and help you get up and running!
Adding a guideline for an agent—for example, to ask a counter-question to get more info when a customer asks a question:
parlant guideline create \
--agent-id CUSTOMER_SUCCESS_AGENT_ID \
--condition "a free-tier customer is asking how to use our product" \
--action "first seek to understand what they're trying to achieve"In Parlant, Customer-Agent interaction happens asynchronously, to enable more natural customer interactions, rather than forcing a strict and unnatural request-reply mode.
Here's a basic example of a simple client (using the TypeScript client SDK):
import { ParlantClient } from 'parlant-client';
const client = ParlantClient({ environment: SERVER_ADDRESS });
session_id = "...";
// Post customer message
const customerEvent = await client.sessions.createEvent(session_id, {
kind: "message",
source: "customer",
message: "How do you use this product?",
});
// Wait for and get the agent's reply
const [agentEvent] = (await client.sessions.listEvents(session_id, {
kinds: "message",
source: "ai_agent",
minOffset: customerEvent.offset,
waitForData: 60 // Wait up to 60 seconds for an answer
}));
// Print the agent's reply
const { agentMessage } = agentEvent.data as { message: string };
console.log(agentMessage);
// Inspect the details of the message generation process
const { trace } = await client.sessions.inspectEvent(
session_id,
agentEvent.id
);We use the Linux-standard Developer Certificate of Origin (DCO.md), so that, by contributing, you confirm that you have the rights to submit your contribution under the Apache 2.0 license (i.e., that the code you're contributing is truly yours to share with the project).
Please consult CONTRIBUTING.md for more details.
Can't wait to get involved? Join us on Discord and let's discuss how you can help shape Parlant. We're excited to work with contributors directly while we set up our formal processes!
Otherwise, feel free to start a discussion or open an issue here on GitHub—freestyle 😎.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for parlant
Similar Open Source Tools
parlant
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.
AppFlowy
AppFlowy.IO is an open-source alternative to Notion, providing users with control over their data and customizations. It aims to offer functionality, data security, and cross-platform native experience to individuals, as well as building blocks and collaboration infra services to enterprises and hackers. The tool is built with Flutter and Rust, supporting multiple platforms and emphasizing long-term maintainability. AppFlowy prioritizes data privacy, reliable native experience, and community-driven extensibility, aiming to democratize the creation of complex workplace management tools.
llama-github
Llama-github is a powerful tool that helps retrieve relevant code snippets, issues, and repository information from GitHub based on queries. It empowers AI agents and developers to solve coding tasks efficiently. With features like intelligent GitHub retrieval, repository pool caching, LLM-powered question analysis, and comprehensive context generation, llama-github excels at providing valuable knowledge context for development needs. It supports asynchronous processing, flexible LLM integration, robust authentication options, and logging/error handling for smooth operations and troubleshooting. The vision is to seamlessly integrate with GitHub for AI-driven development solutions, while the roadmap focuses on empowering LLMs to automatically resolve complex coding tasks.
reductstore
ReductStore is a high-performance time series database designed for storing and managing large amounts of unstructured blob data. It offers features such as real-time querying, batching data, and HTTP(S) API for edge computing, computer vision, and IoT applications. The database ensures data integrity, implements retention policies, and provides efficient data access, making it a cost-effective solution for applications requiring unstructured data storage and access at specific time intervals.
supervisely
Supervisely is a computer vision platform that provides a range of tools and services for developing and deploying computer vision solutions. It includes a data labeling platform, a model training platform, and a marketplace for computer vision apps. Supervisely is used by a variety of organizations, including Fortune 500 companies, research institutions, and government agencies.
pathway
Pathway is a Python data processing framework for analytics and AI pipelines over data streams. It's the ideal solution for real-time processing use cases like streaming ETL or RAG pipelines for unstructured data. Pathway comes with an **easy-to-use Python API** , allowing you to seamlessly integrate your favorite Python ML libraries. Pathway code is versatile and robust: **you can use it in both development and production environments, handling both batch and streaming data effectively**. The same code can be used for local development, CI/CD tests, running batch jobs, handling stream replays, and processing data streams. Pathway is powered by a **scalable Rust engine** based on Differential Dataflow and performs incremental computation. Your Pathway code, despite being written in Python, is run by the Rust engine, enabling multithreading, multiprocessing, and distributed computations. All the pipeline is kept in memory and can be easily deployed with **Docker and Kubernetes**. You can install Pathway with pip: `pip install -U pathway` For any questions, you will find the community and team behind the project on Discord.
aide
Aide is an Open Source AI-native code editor that combines the powerful features of VS Code with advanced AI capabilities. It provides a combined chat + edit flow, proactive agents for fixing errors, inline editing widget, intelligent code completion, and AST navigation. Aide is designed to be an intelligent coding companion, helping users write better code faster while maintaining control over the development process.
data-formulator
Data Formulator is an AI-powered tool developed by Microsoft Research to help data analysts create rich visualizations iteratively. It combines user interface interactions with natural language inputs to simplify the process of describing chart designs while delegating data transformation to AI. Users can utilize features like blended UI and NL inputs, data threads for history navigation, and code inspection to create impressive visualizations. The tool supports local installation for customization and Codespaces for quick setup. Developers can build new data analysis tools on top of Data Formulator, and research papers are available for further reading.
kitops
KitOps is a packaging and versioning system for AI/ML projects that uses open standards so it works with the AI/ML, development, and DevOps tools you are already using. KitOps simplifies the handoffs between data scientists, application developers, and SREs working with LLMs and other AI/ML models. KitOps' ModelKits are a standards-based package for models, their dependencies, configurations, and codebases. ModelKits are portable, reproducible, and work with the tools you already use.
promptflow
**Prompt flow** is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring. It makes prompt engineering much easier and enables you to build LLM apps with production quality.
psychic
Psychic is a tool that provides a platform for users to access psychic readings and services. It offers a range of features such as tarot card readings, astrology consultations, and spiritual guidance. Users can connect with experienced psychics and receive personalized insights and advice on various aspects of their lives. The platform is designed to be user-friendly and intuitive, making it easy for users to navigate and explore the different services available. Whether you're looking for guidance on love, career, or personal growth, Psychic has you covered.
promptmage
PromptMage simplifies the process of creating and managing LLM workflows as a self-hosted solution. It offers an intuitive interface for prompt testing and comparison, incorporates version control features, and aims to improve productivity in both small teams and large enterprises. The tool bridges the gap in LLM workflow management, empowering developers, researchers, and organizations to make LLM technology more accessible and manageable for the next wave of AI innovations.
AI-Studio
MindWork AI Studio is a desktop application that provides a unified chat interface for Large Language Models (LLMs). It is free to use for personal and commercial purposes, offers independence in choosing LLM providers, provides unrestricted usage through the providers API, and is cost-effective with pay-as-you-go pricing. The app prioritizes privacy, flexibility, minimal storage and memory usage, and low impact on system resources. Users can support the project through monthly contributions or one-time donations, with opportunities for companies to sponsor the project for public relations and marketing benefits. Planned features include support for more LLM providers, system prompts integration, text replacement for privacy, and advanced interactions tailored for various use cases.
danswer
Danswer is an open-source Gen-AI Chat and Unified Search tool that connects to your company's docs, apps, and people. It provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for configuring Personas (AI Assistants) and their Prompts. Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc. By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already supported?" or "Where's the pull request for feature Y?"
doc2plan
doc2plan is a browser-based application that helps users create personalized learning plans by extracting content from documents. It features a Creator for manual or AI-assisted plan construction and a Viewer for interactive plan navigation. Users can extract chapters, key topics, generate quizzes, and track progress. The application includes AI-driven content extraction, quiz generation, progress tracking, plan import/export, assistant management, customizable settings, viewer chat with text-to-speech and speech-to-text support, and integration with various Retrieval-Augmented Generation (RAG) models. It aims to simplify the creation of comprehensive learning modules tailored to individual needs.
psychic
Finic is an open source python-based integration platform designed to simplify integration workflows for both business users and developers. It offers a drag-and-drop UI, a dedicated Python environment for each workflow, and generative AI features to streamline transformation tasks. With a focus on decoupling integration from product code, Finic aims to provide faster and more flexible integrations by supporting custom connectors. The tool is open source and allows deployment to users' own cloud environments with minimal legal friction.
For similar tasks
wechat-bot
WeChat Bot is a simple and easy-to-use WeChat robot based on chatgpt and wechaty. It can help you automatically reply to WeChat messages or manage WeChat groups/friends. The tool requires configuration of AI services such as Xunfei, Kimi, or ChatGPT. Users can customize the tool to automatically reply to group or private chat messages based on predefined conditions. The tool supports running in Docker for easy deployment and provides a convenient way to interact with various AI services for WeChat automation.
webwhiz
WebWhiz is an open-source tool that allows users to train ChatGPT on website data to build AI chatbots for customer queries. It offers easy integration, data-specific responses, regular data updates, no-code builder, chatbot customization, fine-tuning, and offline messaging. Users can create and train chatbots in a few simple steps by entering their website URL, automatically fetching and preparing training data, training ChatGPT, and embedding the chatbot on their website. WebWhiz can crawl websites monthly, collect text data and metadata, and process text data using tokens. Users can train custom data, but bringing custom open AI keys is not yet supported. The tool has no limitations on context size but may limit the number of pages based on the chosen plan. WebWhiz SDK is available on NPM, CDNs, and GitHub, and users can self-host it using Docker or manual setup involving MongoDB, Redis, Node, Python, and environment variables setup. For any issues, users can contact [email protected].
parlant
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.
douyin-chatgpt-bot
Douyin ChatGPT Bot is an AI-driven system for automatic replies on Douyin, including comment and private message replies. It offers features such as comment filtering, customizable robot responses, and automated account management. The system aims to enhance user engagement and brand image on the Douyin platform, providing a seamless experience for managing interactions with followers and potential customers.
council
Council is an open-source platform designed for the rapid development and deployment of customized generative AI applications using teams of agents. It extends the LLM tool ecosystem by providing advanced control flow and scalable oversight for AI agents. Users can create sophisticated agents with predictable behavior by leveraging Council's powerful approach to control flow using Controllers, Filters, Evaluators, and Budgets. The framework allows for automated routing between agents, comparing, evaluating, and selecting the best results for a task. Council aims to facilitate packaging and deploying agents at scale on multiple platforms while enabling enterprise-grade monitoring and quality control.
TEN-Agent
TEN Agent is an open-source multimodal agent powered by the world’s first real-time multimodal framework, TEN Framework. It offers high-performance real-time multimodal interactions, multi-language and multi-platform support, edge-cloud integration, flexibility beyond model limitations, and real-time agent state management. Users can easily build complex AI applications through drag-and-drop programming, integrating audio-visual tools, databases, RAG, and more.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.