✨ Promptbook: AI Agents

Create persistent AI agents that turn your company's scattered knowledge into action — powered by the Agents Server

[](https://www.npmjs.com/package/promptbook) [](https://packagequality.com/#?package=promptbook)

🌟 New Features

• Gemini 3 Support

⚠ Warning: This is a pre-release version of the library. It is not yet ready for production use. Please look at latest stable release.

📦 Package @promptbook/types

• Promptbooks are divided into several packages, all are published from single monorepo.
• This package @promptbook/types is one part of the promptbook ecosystem.

To install this package, run:

# Install entire promptbook ecosystem
npm i ptbk

npm i -D @promptbook/types

Comprehensive TypeScript type definitions for all Promptbook entities, enabling type-safe development and excellent IDE support throughout the Promptbook ecosystem.

🎯 Purpose and Motivation

This package centralizes all TypeScript type definitions used throughout the Promptbook ecosystem. It enables developers to write type-safe code when working with promptbooks, pipelines, LLM providers, and other Promptbook components, providing excellent IntelliSense and compile-time error checking.

🔧 High-Level Functionality

The package provides type definitions for:

• Pipeline Structures: Complete type definitions for promptbook JSON structures
• Execution Types: Types for pipeline execution, results, and error handling
• LLM Provider Types: Configuration and option types for all supported providers
• Command Types: Type definitions for all promptbook commands
• Utility Types: Helper types for common patterns and data structures
• Component Types: React component prop types for UI components

✨ Key Features

• 📝 Complete Type Coverage - Types for all Promptbook entities and APIs
• 🔒 Type Safety - Compile-time validation and error prevention
• 💡 Excellent IntelliSense - Rich IDE support with autocomplete and documentation
• 🏗️ Structural Types - Detailed types for promptbook JSON structures
• 🔧 Provider-Agnostic - Generic types that work across all LLM providers
• 📊 Execution Types - Comprehensive types for pipeline execution and results
• 🎨 Component Types - React component prop types for UI development
• 🔄 Version Compatibility - Types that evolve with the Promptbook ecosystem

Usage Example

import type { PipelineJson } from '@promptbook/types';
import { compilePipeline } from '@promptbook/core';

const promptbook: PipelineJson = compilePipeline(
    spaceTrim(`

        # ✨ Example prompt

        -   OUTPUT PARAMETER {greeting}


        ## 💬 Prompt

        \`\`\`text
        Hello
        \`\`\`

        -> {greeting}

    `),
);

📦 Exported Type Categories

Agent and Book Types

• AgentBasicInformation - Basic agent information structure (type)
• AgentModelRequirements - Model requirements for agents (type)
• string_book - Book content string type (type)
• BookCommitment - Book commitment structure (type)
• CommitmentDefinition - Commitment definition interface (type)
• ParsedCommitment - Parsed commitment structure (type)

Component Types

• AvatarChipProps - Avatar chip component props (type)
• AvatarChipFromSourceProps - Avatar chip from source props (type)
• AvatarProfileProps - Avatar profile component props (type)
• AvatarProfileFromSourceProps - Avatar profile from source props (type)
• BookEditorProps - Book editor component props (type)
• ChatProps - Chat component props (type)
• LlmChatProps - LLM chat component props (type)
• ChatMessage - Chat message structure (type)
• ChatParticipant - Chat participant information (type)

Collection and Pipeline Types

• PipelineCollection - Pipeline collection interface (type)
• PipelineJson - Complete pipeline JSON structure (type)
• PipelineString - Pipeline string format (type)
• PipelineInterface - Pipeline interface definition (type)
• TaskJson - Task JSON structure (type)
• PromptTaskJson - Prompt task structure (type)
• ScriptTaskJson - Script task structure (type)
• SimpleTaskJson - Simple task structure (type)
• DialogTaskJson - Dialog task structure (type)
• CommonTaskJson - Common task properties (type)

Command Types

• Command - Base command interface (type)
• CommandParser - Command parser interface (type)
• PipelineBothCommandParser - Pipeline both command parser (type)
• PipelineHeadCommandParser - Pipeline head command parser (type)
• PipelineTaskCommandParser - Pipeline task command parser (type)
• CommandParserInput - Command parser input (type)
• CommandType - Command type enumeration (type)
• CommandUsagePlace - Command usage context (type)
• BookVersionCommand - Book version command (type)
• ExpectCommand - Expect command structure (type)
• ForeachCommand - Foreach command structure (type)
• ForeachJson - Foreach JSON structure (type)
• FormatCommand - Format command structure (type)
• FormfactorCommand - Formfactor command structure (type)
• JokerCommand - Joker command structure (type)
• KnowledgeCommand - Knowledge command structure (type)
• ModelCommand - Model command structure (type)
• ParameterCommand - Parameter command structure (type)
• PersonaCommand - Persona command structure (type)
• PostprocessCommand - Postprocess command structure (type)
• SectionCommand - Section command structure (type)
• UrlCommand - URL command structure (type)
• ActionCommand - Action command structure (type)
• InstrumentCommand - Instrument command structure (type)

Execution Types

• ExecutionTools - Execution tools interface (type)
• LlmExecutionTools - LLM execution tools interface (type)
• LlmExecutionToolsConstructor - LLM execution tools constructor (type)
• PipelineExecutor - Pipeline executor interface (type)
• PipelineExecutorResult - Execution result structure (type)
• ExecutionTask - Execution task structure (type)
• PreparationTask - Preparation task structure (type)
• task_status - Task status type (type)
• AbstractTask - Abstract task interface (type)
• Task - Task interface (type)
• ExecutionReportJson - Execution report structure (type)
• ExecutionPromptReportJson - Execution prompt report structure (type)
• ExecutionReportString - Execution report string (type)
• ExecutionReportStringOptions - Report formatting options (type)
• PromptResult - Prompt execution result (type)
• CompletionPromptResult - Completion prompt result (type)
• ChatPromptResult - Chat prompt result (type)
• EmbeddingPromptResult - Embedding prompt result (type)
• Usage - Usage tracking structure (type)
• UsageCounts - Usage counts structure (type)
• UncertainNumber - Uncertain number type (type)
• AvailableModel - Available model information (type)
• AbstractTaskResult - Abstract task result (type)
• EmbeddingVector - Embedding vector type (type)

LLM Provider Configuration Types

• AnthropicClaudeExecutionToolsOptions - Anthropic Claude configuration (type)
• AnthropicClaudeExecutionToolsNonProxiedOptions - Anthropic Claude non-proxied options (type)
• AnthropicClaudeExecutionToolsProxiedOptions - Anthropic Claude proxied options (type)
• OpenAiExecutionToolsOptions - OpenAI configuration (type)
• OpenAiAssistantExecutionToolsOptions - OpenAI Assistant configuration (type)
• OpenAiCompatibleExecutionToolsOptions - OpenAI Compatible configuration (type)
• OpenAiCompatibleExecutionToolsNonProxiedOptions - OpenAI Compatible non-proxied options (type)
• OpenAiCompatibleExecutionToolsProxiedOptions - OpenAI Compatible proxied options (type)
• AzureOpenAiExecutionToolsOptions - Azure OpenAI configuration (type)
• GoogleExecutionToolsOptions - Google configuration (type)
• DeepseekExecutionToolsOptions - Deepseek configuration (type)
• OllamaExecutionToolsOptions - Ollama configuration (type)
• VercelExecutionToolsOptions - Vercel configuration (type)
• VercelProvider - Vercel provider type (type)

Parameter and Data Types

• ParameterJson - Parameter definition structure (type)
• InputParameterJson - Input parameter structure (type)
• IntermediateParameterJson - Intermediate parameter structure (type)
• OutputParameterJson - Output parameter structure (type)
• CommonParameterJson - Common parameter properties (type)
• Parameters - Parameter collection type (type)
• InputParameters - Input parameters type (type)
• Expectations - Expectation validation structure (type)
• ExpectationUnit - Expectation unit type (type)
• ExpectationAmount - Expectation amount type (type)
• PersonaJson - Persona definition structure (type)
• PersonaPreparedJson - Prepared persona structure (type)
• KnowledgeSourceJson - Knowledge source structure (type)
• KnowledgeSourcePreparedJson - Prepared knowledge source structure (type)
• KnowledgePiecePreparedJson - Prepared knowledge piece structure (type)

Utility and Helper Types

• string_prompt - Prompt string type (type)
• string_template - Template string type (type)
• string_text_prompt - Text prompt string type (type)
• string_chat_prompt - Chat prompt string type (type)
• string_system_message - System message string type (type)
• string_completion_prompt - Completion prompt string type (type)
• string_parameter_name - Parameter name type (type)
• string_parameter_value - Parameter value type (type)
• string_reserved_parameter_name - Reserved parameter name type (type)
• ReservedParameters - Reserved parameters type (type)
• string_model_name - Model name type (type)
• string_url - URL string type (type)
• string_filename - Filename string type (type)
• string_absolute_filename - Absolute filename type (type)
• string_relative_filename - Relative filename type (type)
• string_dirname - Directory name type (type)
• string_absolute_dirname - Absolute directory name type (type)
• string_relative_dirname - Relative directory name type (type)
• number_tokens - Token count type (type)
• number_usd - USD amount type (type)
• ModelVariant - Model variant enumeration (type)
• ScriptLanguage - Script language enumeration (type)
• TaskType - Task type enumeration (type)
• SectionType - Section type enumeration (type)
• ModelRequirements - Model requirements type (type)
• CompletionModelRequirements - Completion model requirements (type)
• ChatModelRequirements - Chat model requirements (type)
• EmbeddingModelRequirements - Embedding model requirements (type)

Remote Server Types

• RemoteServerOptions - Remote server configuration (type)
• AnonymousRemoteServerOptions - Anonymous remote server options (type)
• ApplicationRemoteServerOptions - Application remote server options (type)
• ApplicationRemoteServerClientOptions - Application remote server client options (type)
• RemoteClientOptions - Remote client configuration (type)
• Identification - User identification structure (type)
• ApplicationModeIdentification - Application mode identification (type)
• AnonymousModeIdentification - Anonymous mode identification (type)
• LoginRequest - Login request structure (type)
• LoginResponse - Login response structure (type)
• RemoteServer - Remote server interface (type)

Storage and Scraper Types

• PromptbookStorage - Storage interface (type)
• FileCacheStorageOptions - File cache storage options (type)
• IndexedDbStorageOptions - IndexedDB storage options (type)
• Scraper - Scraper interface (type)
• ScraperConstructor - Scraper constructor type (type)
• ScraperSourceHandler - Scraper source handler (type)
• ScraperIntermediateSource - Scraper intermediate source (type)
• ScraperAndConverterMetadata - Scraper and converter metadata (type)
• Converter - Content converter interface (type)

Additional Types

• Prompt - Prompt interface (type)
• CompletionPrompt - Completion prompt interface (type)
• ChatPrompt - Chat prompt interface (type)
• EmbeddingPrompt - Embedding prompt interface (type)
• NonEmptyArray - Non-empty array type (type)
• NonEmptyReadonlyArray - Non-empty readonly array type (type)
• IntermediateFilesStrategy - Intermediate files strategy (type)
• string_promptbook_version - Promptbook version string type (type)

💡 This package provides TypeScript types for promptbook applications. For runtime functionality, see @promptbook/core or install all packages with npm i ptbk

Rest of the documentation is common for entire promptbook ecosystem:

📖 The Book Whitepaper

Promptbook lets you create persistent AI agents that work on real goals for your company. The Agents Server is the heart of the project — a place where your AI agents live, remember context, collaborate in teams, and get things done.

Nowadays, the biggest challenge for most business applications isn't the raw capabilities of AI models. Large language models such as GPT-5.2 and Claude-4.5 are incredibly capable.

The main challenge lies in managing the context, providing rules and knowledge, and narrowing the personality.

In Promptbook, you define your agents using simple Books — a human-readable language that is explicit, easy to understand and write, reliable, and highly portable. You then deploy them to the Agents Server, where they run persistently and work toward their goals.

Aspects of great AI agent

We have created a language called Book, which allows you to write AI agents in their native language and create your own AI persona. Book provides a guide to define all the traits and commitments.

You can look at it as "prompting" (or writing a system message), but decorated by commitments.

Commitments are special syntax elements that define contracts between you and the AI agent. They are transformed by Promptbook Engine into low-level parameters like which model to use, its temperature, system message, RAG index, MCP servers, and many other parameters. For some commitments (for example RULE commitment) Promptbook Engine can even create adversary agents and extra checks to enforce the rules.

Persona commitment

Personas define the character of your AI persona, its role, and how it should interact with users. It sets the tone and style of communication.

Goal commitment

Goals define what the agent should actively work toward. Unlike a chatbot that only responds when asked, an agent with goals takes initiative and works on tasks persistently on the Agents Server.

Knowledge commitment

Knowledge Commitment allows you to provide specific information, facts, or context that the AI should be aware of when responding.

This can include domain-specific knowledge, company policies, or any other relevant information.

Promptbook Engine will automatically enforce this knowledge during interactions. When the knowledge is short enough, it will be included in the prompt. When it is too long, it will be stored in vector databases and RAG retrieved when needed. But you don't need to care about it.

Rule commitment

Rules will enforce specific behaviors or constraints on the AI's responses. This can include ethical guidelines, communication styles, or any other rules you want the AI to follow.

Depending on rule strictness, Promptbook will either propagate it to the prompt or use other techniques, like adversary agent, to enforce it.

Use commitments

Use commitments grant the agent real capabilities — tools it can use to interact with the outside world. USE EMAIL lets the agent send emails, USE BROWSER lets it access and read web content, USE SEARCH ENGINE lets it search the web, and many more.

These are what turn a chatbot into a persistent agent that actually does work.

Team commitment

Team commitment allows you to define the team structure and advisory fellow members the AI can consult with. This allows the AI to simulate collaboration and consultation with other experts, enhancing the quality of its responses.

Promptbook Ecosystem

Promptbook is an ecosystem of tools centered around the Agents Server — a production-ready platform for running persistent AI agents.

Agents Server

The Agents Server is the primary way to use Promptbook. It is a web application where your AI agents live and work. You can create agents, give them knowledge and rules using the Book language, organize them into teams, and let them work on goals persistently. The Agents Server provides a UI for managing agents, an API for integrating them into your applications, and can be self-hosted via Docker or deployed on Vercel.

Promptbook Engine

The Promptbook Engine is the open-source core that powers everything. It parses the Book language, applies commitments, manages LLM provider integrations, and executes agents. The Agents Server is built on top of the Engine. If you need to embed agent capabilities directly into your own application, you can use the Engine as a standalone TypeScript/JavaScript library via NPM packages.

💜 The Promptbook Project

Promptbook project is an ecosystem centered around the Agents Server — a platform for creating, deploying, and running persistent AI agents. Following is a list of the most important pieces of the project:

🌐 Community & Social Media

Join our growing community of developers and users:

🖼️ Product & Brand Channels

Promptbook.studio

📚 Documentation

See detailed guides and API reference in the docs or online.

🔒 Security

For information on reporting security vulnerabilities, see our Security Policy.

📦 Deployment & Packages

The fastest way to get started is with the Agents Server:

• 🐋 Docker image — Self-host the Agents Server with full control over your data
• ☁️ Hosted Agents Server — Start creating agents immediately, no setup required

NPM Packages (for developers embedding the Engine)

If you want to embed the Promptbook Engine directly into your application, the library is divided into several packages published from a single monorepo. You can install all of them at once:

npm i ptbk

Or you can install them separately:

⭐ Marked packages are worth to try first

• ⭐ ptbk - Bundle of all packages, when you want to install everything and you don't care about the size

• promptbook - Same as ptbk

• ⭐🧙‍♂️ @promptbook/wizard - Wizard to just run the books in node without any struggle

• @promptbook/core - Core of the library, it contains the main logic for promptbooks

• @promptbook/node - Core of the library for Node.js environment

• @promptbook/browser - Core of the library for browser environment

• ⭐ @promptbook/utils - Utility functions used in the library but also useful for individual use in preprocessing and postprocessing LLM inputs and outputs

• @promptbook/markdown-utils - Utility functions used for processing markdown

• @promptbook/javascript - Execution tools for javascript inside promptbooks

• @promptbook/openai - Execution tools for OpenAI API, wrapper around OpenAI SDK

• @promptbook/anthropic-claude - Execution tools for Anthropic Claude API, wrapper around Anthropic Claude SDK

• @promptbook/vercel - Adapter for Vercel functionalities

• @promptbook/google - Integration with Google's Gemini API

• @promptbook/deepseek - Integration with DeepSeek API

• @promptbook/ollama - Integration with Ollama API

• @promptbook/azure-openai - Execution tools for Azure OpenAI API

• @promptbook/fake-llm - Mocked execution tools for testing the library and saving the tokens

• @promptbook/remote-client - Remote client for remote execution of promptbooks

• @promptbook/remote-server - Remote server for remote execution of promptbooks

• @promptbook/pdf - Read knowledge from .pdf documents

• @promptbook/documents - Integration of Markitdown by Microsoft

• @promptbook/documents - Read knowledge from documents like .docx, .odt,…

• @promptbook/legacy-documents - Read knowledge from legacy documents like .doc, .rtf,…

• @promptbook/website-crawler - Crawl knowledge from the web

• @promptbook/editable - Editable book as native javascript object with imperative object API

• @promptbook/templates - Useful templates and examples of books which can be used as a starting point

• @promptbook/types - Just typescript types used in the library

• @promptbook/color - Color manipulation library

• @promptbook/cli - Command line interface utilities for promptbooks

📚 Dictionary

The following glossary is used to clarify certain concepts:

General LLM / AI terms

• Prompt drift is a phenomenon where the AI model starts to generate outputs that are not aligned with the original prompt. This can happen due to the model's training data, the prompt's wording, or the model's architecture.
• Pipeline, workflow scenario or chain is a sequence of tasks that are executed in a specific order. In the context of AI, a pipeline can refer to a sequence of AI models that are used to process data.
• Fine-tuning is a process where a pre-trained AI model is further trained on a specific dataset to improve its performance on a specific task.
• Zero-shot learning is a machine learning paradigm where a model is trained to perform a task without any labeled examples. Instead, the model is provided with a description of the task and is expected to generate the correct output.
• Few-shot learning is a machine learning paradigm where a model is trained to perform a task with only a few labeled examples. This is in contrast to traditional machine learning, where models are trained on large datasets.
• Meta-learning is a machine learning paradigm where a model is trained on a variety of tasks and is able to learn new tasks with minimal additional training. This is achieved by learning a set of meta-parameters that can be quickly adapted to new tasks.
• Retrieval-augmented generation is a machine learning paradigm where a model generates text by retrieving relevant information from a large database of text. This approach combines the benefits of generative models and retrieval models.
• Longtail refers to non-common or rare events, items, or entities that are not well-represented in the training data of machine learning models. Longtail items are often challenging for models to predict accurately.

Note: This section is not a complete dictionary, more list of general AI / LLM terms that has connection with Promptbook

💯 Core concepts

• 📚 Collection of pipelines
• 📯 Pipeline
• 🙇‍♂️ Tasks and pipeline sections
• 🤼 Personas
• ⭕ Parameters
• 🚀 Pipeline execution
• 🧪 Expectations - Define what outputs should look like and how they're validated
• ✂️ Postprocessing - How outputs are refined after generation
• 🔣 Words not tokens - The human-friendly way to think about text generation
• ☯ Separation of concerns - How Book language organizes different aspects of AI workflows

Advanced concepts

🔍 View more concepts

� Agents Server

The Agents Server is the primary way to use Promptbook. It is a production-ready platform where you create, deploy, and manage persistent AI agents that work toward goals. Agents remember context across conversations, collaborate in teams, and follow the rules and knowledge you define in the Book language.

• Hosted at gallery.ptbk.io — start creating agents immediately
• Self-hosted via Docker — full control over your data and infrastructure
• API for integrating agents into your own applications

🚂 Promptbook Engine

The Engine is the open-source core that powers the Agents Server. If you need to embed agent capabilities directly into your TypeScript/JavaScript application, you can use it as a standalone library.

➕➖ When to use Promptbook?

➕ When to use

• When you want to deploy persistent AI agents that work on goals for your company
• When you need agents with specific personalities, knowledge, and rules tailored to your business
• When you want agents that collaborate in teams and consult each other
• When you need to integrate AI agents into your existing applications via API
• When you want to self-host your AI agents with full control over data and infrastructure
• When you are writing an app that generates complex things via LLM — like websites, articles, presentations, code, stories, songs,...
• When you want to version your agent definitions and test multiple versions
• When you want to log agent execution and backtrace issues

See more

➖ When not to use

• When a single simple prompt already works fine for your job
• When OpenAI Assistant (GPTs) is enough for you
• When you need streaming (this may be implemented in the future, see discussion)
• When you need to use something other than JavaScript or TypeScript (other languages are on the way, see the discussion)
• When your main focus is on something other than text — like images, audio, video, spreadsheets (other media types may be added in the future, see discussion)
• When you need to use recursion (see the discussion)

See more

🐜 Known issues

• 🤸‍♂️ Iterations not working yet
• ⤵️ Imports not working yet

🧼 Intentionally not implemented features

• ➿ No recursion
• 🏳 There are no types, just strings

❔ FAQ

If you have a question start a discussion, open an issue or write me an email.

• ❔ Why not just use the OpenAI SDK / Anthropic Claude SDK / ...?
• [❔ How is it different from the OpenAI`s GPTs?](https://github.com/webgptorg/promptbook/discussions/118)
• ❔ How is it different from the Langchain?
• ❔ How is it different from the DSPy?
• ❔ How is it different from anything?
• ❔ Is Promptbook using RAG (Retrieval-Augmented Generation)?
• ❔ Is Promptbook using function calling?

📅 Changelog

See CHANGELOG.md

📜 License

This project is licensed under BUSL 1.1.

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

You can also ⭐ star the project, follow us on GitHub or various other social networks.We are open to pull requests, feedback, and suggestions.

🆘 Support & Community

Need help with Book language? We're here for you!

• 💬 Join our Discord community for real-time support
• 📝 Browse our GitHub discussions for FAQs and community knowledge
• 🐛 Report issues for bugs or feature requests
• 📚 Visit ptbk.io for more resources and documentation
• 📧 Contact us directly through the channels listed in our signpost

We welcome contributions and feedback to make Book language better for everyone!