@promptbook/utils
Advanced tools
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
Create persistent AI agents that turn your company's scattered knowledge into action - powered by the Agents Server
โ Warning: This is a pre-release version of the library. It is not yet ready for production use. Please look at latest stable release.
@promptbook/utils@promptbook/utils is one part of the promptbook ecosystem.To install this package, run:
# Install entire promptbook ecosystem
npm i ptbk
# Install just this package to save space
npm install @promptbook/utils
Comprehensive utility functions for text processing, validation, normalization, and LLM input/output handling in the Promptbook ecosystem.
The utils package provides a rich collection of utility functions that are essential for working with LLM inputs and outputs. It handles common tasks like text normalization, parameter templating, validation, and postprocessing, eliminating the need to implement these utilities from scratch in every promptbook application.
This package offers utilities across multiple domains:
The prompt template tag function helps format prompt strings for LLM interactions. It handles string interpolation and maintains consistent formatting for multiline strings and lists and also handles a security to avoid prompt injection.
import { prompt } from '@promptbook/utils';
const promptString = prompt`
Correct the following sentence:
> ${unsecureUserInput}
`;
The prompt name could be overloaded by multiple things in your code. If you want to use the promptTemplate which is alias for prompt:
import { promptTemplate } from '@promptbook/utils';
const promptString = promptTemplate`
Correct the following sentence:
> ${unsecureUserInput}
`;
There is a function templateParameters which is used to replace the parameters in given template optimized to LLM prompt templates.
import { templateParameters } from '@promptbook/utils';
templateParameters('Hello, {name}!', { name: 'world' }); // 'Hello, world!'
And also multiline templates with blockquotes
import { templateParameters, spaceTrim } from '@promptbook/utils';
templateParameters(
spaceTrim(`
Hello, {name}!
> {answer}
`),
{
name: 'world',
answer: spaceTrim(`
I'm fine,
thank you!
And you?
`),
},
);
// Hello, world!
//
// > I'm fine,
// > thank you!
// >
// > And you?
These functions are useful to count stats about the input/output in human-like terms not tokens and bytes, you can use
countCharacters, countLines, countPages, countParagraphs, countSentences, countWords
import { countWords } from '@promptbook/utils';
console.log(countWords('Hello, world!')); // 2
Splitting functions are similar to counting but they return the split parts of the input/output, you can use
splitIntoCharacters, splitIntoLines, splitIntoPages, splitIntoParagraphs, splitIntoSentences, splitIntoWords
import { splitIntoWords } from '@promptbook/utils';
console.log(splitIntoWords('Hello, world!')); // ['Hello', 'world']
Normalization functions are used to put the string into a normalized form, you can use
kebab-case
PascalCase
SCREAMING_CASE
snake_case
kebab-case
import { normalizeTo } from '@promptbook/utils';
console.log(normalizeTo['kebab-case']('Hello, world!')); // 'hello-world'
capitalize, decapitalize, removeDiacritics,...POSTPROCESS command in promptbookSometimes you need to postprocess the output of the LLM model, every postprocessing function that is available through POSTPROCESS command in promptbook is exported from @promptbook/utils. You can use:
spaceTrimextractAllBlocksFromMarkdown, <- Note: Exported from @promptbook/markdown-utilsextractAllListItemsFromMarkdown <- Note: Exported from @promptbook/markdown-utilsextractBlockextractOneBlockFromMarkdown <- Note: Exported from @promptbook/markdown-utilsprettifyPipelineStringremoveMarkdownCommentsremoveEmojisremoveMarkdownFormatting <- Note: Exported from @promptbook/markdown-utilsremoveQuotestrimCodeBlocktrimEndOfCodeBlockunwrapResultVery often you will use unwrapResult, which is used to extract the result you need from output with some additional information:
import { unwrapResult } from '@promptbook/utils';
unwrapResult('Best greeting for the user is "Hi Pavol!"'); // 'Hi Pavol!'
BOOK_LANGUAGE_VERSION - Current book language versionPROMPTBOOK_ENGINE_VERSION - Current engine versionVALUE_STRINGS - Standard value stringsSMALL_NUMBER - Small number constantrenderPromptbookMermaid - Render promptbook as Mermaid diagramdeserializeError - Deserialize error objectsserializeError - Serialize error objectsforEachAsync - Async forEach implementationisValidCsvString - Validate CSV string formatisValidJsonString - Validate JSON string formatjsonParse - Safe JSON parsingisValidXmlString - Validate XML string formatprompt - Template tag for secure prompt formattingpromptTemplate - Alias for prompt template tag$getCurrentDate - Get current date (side effect)$isRunningInBrowser - Check if running in browser$isRunningInJest - Check if running in Jest$isRunningInNode - Check if running in Node.js$isRunningInWebWorker - Check if running in Web WorkerCHARACTERS_PER_STANDARD_LINE - Characters per standard line constantLINES_PER_STANDARD_PAGE - Lines per standard page constantcountCharacters - Count characters in textcountLines - Count lines in textcountPages - Count pages in textcountParagraphs - Count paragraphs in textsplitIntoSentences - Split text into sentencescountSentences - Count sentences in textcountWords - Count words in textCountUtils - Utility object with all counting functionscapitalize - Capitalize first letterdecapitalize - Decapitalize first letterDIACRITIC_VARIANTS_LETTERS - Diacritic variants mappingstring_keyword - Keyword string type (type)Keywords - Keywords type (type)isValidKeyword - Validate keyword formatnameToUriPart - Convert name to URI partnameToUriParts - Convert name to URI partsstring_kebab_case - Kebab case string type (type)normalizeToKebabCase - Convert to kebab-casestring_camelCase - Camel case string type (type)normalizeTo_camelCase - Convert to camelCasestring_PascalCase - Pascal case string type (type)normalizeTo_PascalCase - Convert to PascalCasestring_SCREAMING_CASE - Screaming case string type (type)normalizeTo_SCREAMING_CASE - Convert to SCREAMING_CASEnormalizeTo_snake_case - Convert to snake_casenormalizeWhitespaces - Normalize whitespace charactersorderJson - Order JSON object propertiesparseKeywords - Parse keywords from inputparseKeywordsFromString - Parse keywords from stringremoveDiacritics - Remove diacritic markssearchKeywords - Search within keywordssuffixUrl - Add suffix to URLtitleToName - Convert title to name formatspaceTrim - Trim spaces while preserving structureextractParameterNames - Extract parameter names from templatenumberToString - Convert number to stringtemplateParameters - Replace template parametersvalueToString - Convert value to stringparseNumber - Parse number from stringremoveEmojis - Remove emoji charactersremoveQuotes - Remove quote characters$deepFreeze - Deep freeze object (side effect)checkSerializableAsJson - Check if serializable as JSONclonePipeline - Clone pipeline objectdeepClone - Deep clone objectexportJson - Export object as JSONisSerializableAsJson - Check if object is JSON serializablejsonStringsToJsons - Convert JSON strings to objectsdifference - Set difference operationintersection - Set intersection operationunion - Set union operationtrimCodeBlock - Trim code block formattingtrimEndOfCodeBlock - Trim end of code blockunwrapResult - Extract result from wrapped outputisValidEmail - Validate email address formatisRootPath - Check if path is root pathisValidFilePath - Validate file path formatisValidJavascriptName - Validate JavaScript identifierisValidPromptbookVersion - Validate promptbook versionisValidSemanticVersion - Validate semantic versionisHostnameOnPrivateNetwork - Check if hostname is on private networkisUrlOnPrivateNetwork - Check if URL is on private networkisValidPipelineUrl - Validate pipeline URL formatisValidUrl - Validate URL formatisValidUuid - Validate UUID format๐ก This package provides utility functions for promptbook applications. For the core functionality, see @promptbook/core or install all packages with
npm i ptbk
Rest of the documentation is common for entire promptbook ecosystem:
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.
|
Paul Smith |
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 commitmentPersonas define the character of your AI persona, its role, and how it should interact with users. It sets the tone and style of communication.
|
Paul Smith & Associรฉs |
Goal commitmentGoals 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.
|
Paul Smith & Associรฉs |
Knowledge commitmentKnowledge 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.
|
Paul Smith & Associรฉs |
Rule commitmentRules 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.
|
Paul Smith & Associรฉs |
Use commitmentsUse 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.
|
Paul Smith & Associรฉs |
Team commitmentTeam 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.
|
Paul Smith & Associรฉs |
Promptbook is an ecosystem of tools centered around the Agents Server - a production-ready platform for running persistent AI agents.
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.
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.
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:
| Project | About |
|---|---|
| โญ Agents Server | The primary way to use Promptbook. A production-ready platform where your AI agents live - create, manage, deploy, and interact with persistent agents that work on goals. Available as a hosted service or self-hosted via Docker. |
| Book language |
Human-friendly, high-level language that abstracts away low-level details of AI. It allows to focus on personality, behavior, knowledge, and rules of AI agents rather than on models, parameters, and prompt engineering.
There is also a plugin for VSCode to support .book file extension
|
| Promptbook Engine | The open-source core that powers the Agents Server. Can also be used as a standalone TypeScript/JavaScript library to embed agent capabilities into your own applications. Released as multiple NPM packages. |
Join our growing community of developers and users:
| Platform | Description |
|---|---|
| ๐ฌ Discord | Join our active developer community for discussions and support |
| ๐ฃ๏ธ GitHub Discussions | Technical discussions, feature requests, and community Q&A |
| ๐ LinkedIn | Professional updates and industry insights |
| ๐ฑ Facebook | General announcements and community engagement |
| ๐ ptbk.io | Official landing page with project information |
| ๐ธ Instagram @promptbook.studio | Visual updates, UI showcases, and design inspiration |
See detailed guides and API reference in the docs or online.
For information on reporting security vulnerabilities, see our Security Policy.
The fastest way to get started is with the Agents Server:
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:
โญ Marked packages are worth to try first
โญ ptbk - Bundle of all packages, when you want to install everything and you don't care about the size
promptbook - Same as ptbk
โญ๐งโโ๏ธ @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
โญ @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,โฆ
@promptbook/legacy-documents - Read knowledge from legacy documents like .doc, .rtf,โฆ
@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
ptbk coder is Promptbook's workflow layer for AI-assisted software changes. Instead of opening one chat and manually copy-pasting tasks, you keep a queue of coding prompts in prompts/*.md, let a coding agent execute the next ready task, and then verify the result before archiving the prompt.
Promptbook Coder is not another standalone coding model. It is an orchestration layer over coding agents such as GitHub Copilot, OpenAI Codex, Claude Code, Opencode, Cline, and Gemini CLI. The difference is that Promptbook Coder adds a repeatable repository workflow on top of them:
[ ], [x], and [-]AGENTS.mdgit add, commit, and push after each successful promptIn short: tools like Claude Code, Codex, or GitHub Copilot are the engines; Promptbook Coder is the workflow that keeps coding work structured, reviewable, and repeatable across many prompts.
ptbk coder init prepares the project for the coder workflow, seeds project-owned generic templates in prompts/templates/, creates a starter AGENTS.md context file, adds helper npm run coder:* scripts, ensures .gitignore ignores /.tmp, and configures VS Code prompt screenshots in prompts/screenshots/.ptbk coder generate-boilerplates creates prompt files in prompts/.@@@ sections with real coding tasks.ptbk coder run sends the next ready [ ] prompt to the selected coding agent.[x], records runner metadata, then stages, commits, and pushes the resulting changes.ptbk coder verify reviews completed prompts, archives finished files to prompts/done/, and appends a repair prompt when more work is needed.Prompts marked with [-] are not ready yet, prompts containing @@@ are treated as not fully written, and prompts with more ! markers have higher priority.
openai-codex, github-copilot, cline, claude-code, opencode, gemini--context AGENTS.md or inline extra instructions--thinking-level low|medium|high|xhigh for supported runners--no-wait for batch execution--ignore-git-changes--auto-push--priority to process only more important tasks first.error.logWhen working on Promptbook itself, the repository usually runs the CLI straight from source:
npx ts-node ./src/cli/test/ptbk.ts coder init
npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompts/templates/common.md
npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompts/templates/agents-server.md
npx ts-node ./src/cli/test/ptbk.ts coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md
npx ts-node ./src/cli/test/ptbk.ts coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --auto-push
npx ts-node ./src/cli/test/ptbk.ts coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --ignore-git-changes --no-wait
npx ts-node ./src/cli/test/ptbk.ts coder find-refactor-candidates
npx ts-node ./src/cli/test/ptbk.ts coder find-refactor-candidates --level xhigh
npx ts-node ./src/cli/test/ptbk.ts coder verify
ptbk coder in an external projectIf you want to use the workflow in another repository, install the package and invoke the ptbk binary. After local installation, npx ptbk ... is the most portable form; plain ptbk ... also works when your environment exposes the local binary on PATH.
npm install ptbk
ptbk coder init
npx ptbk coder generate-boilerplates
npx ptbk coder generate-boilerplates --template prompts/templates/common.md
npx ptbk coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --test npm run test
npx ptbk coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --auto-push
npx ptbk coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --test npm run test --ignore-git-changes --no-wait
npx ptbk coder find-refactor-candidates
npx ptbk coder find-refactor-candidates --level xhigh
npx ptbk coder verify
ptbk coder init also bootstraps a starter AGENTS.md, adds package.json scripts for the four main coder commands, adds the coder temp ignore to .gitignore, and configures .vscode/settings.json so pasted images from prompts/*.md land in prompts/screenshots/.
| Command | What it does |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | ------ | ---- | ----- | ------------------------------------------------------------------------ |
| ptbk coder init | Creates prompts/, prompts/done/, the project-generic template files materialized in prompts/templates/ (currently common.md), and a starter AGENTS.md; ensures .env contains CODING_AGENT_GIT_NAME, CODING_AGENT_GIT_EMAIL, and CODING_AGENT_GIT_SIGNING_KEY; adds helper coder scripts to package.json; ensures .gitignore contains /.tmp; and configures .vscode/settings.json to save pasted prompt images into prompts/screenshots/. |
| ptbk coder generate-boilerplates | Creates new prompt markdown files with fresh emoji tags so you can quickly fill in coding tasks; --template accepts either a built-in alias or a markdown file path relative to the project root. |
| ptbk coder run | Picks the next ready prompt, appends optional context, runs it through the selected coding agent, can optionally verify each attempt with a shell test command and feed failing output back for retries, then marks success or failure, commits the result, and pushes only when --auto-push is enabled. |
| ptbk coder find-refactor-candidates | Scans the repository for oversized or overpacked files and writes prompt files for likely refactors; --level <xlow | low | medium | high | xhigh | extreme> ranges from a very benevolent scan to a very aggressive sweep. |
| ptbk coder verify | Walks through completed prompts, archives truly finished work, and adds follow-up repair prompts for unfinished results. |
ptbk coder run flags| Flag | Purpose |
|---|---|
--agent <name> | Selects the coding backend. |
--model <model> | Chooses the runner model; required for openai-codex and gemini, optional for github-copilot. |
--context <text-or-file> | Appends extra instructions inline or from a file like AGENTS.md. |
--test <command> | Runs a verification command after each prompt attempt and feeds failing output back for retries. |
--thinking-level <level> | Sets reasoning effort for supported runners. |
--no-wait | Skips interactive pauses between prompts for unattended execution. |
--ignore-git-changes | Disables the clean-working-tree guard. |
--priority <n> | Runs only prompts at or above the given priority. |
--dry-run | Prints which prompts are ready instead of executing them. |
--allow-credits | Lets OpenAI Codex spend credits when required. |
--auto-push | Pushes each successful coding-agent commit to the configured remote. |
--auto-migrate | Runs testing-server database migrations after each successful prompt. |
ptbk coder init.prompts/templates/*.md if needed, then create or write prompt files in prompts/.AGENTS.md with repository-specific instructions, then pass --context AGENTS.md.--no-wait for unattended batches.ptbk coder verify so resolved prompts are archived and broken ones get explicit repair follow-ups.The following glossary is used to clarify certain concepts:
Note: This section is not a complete dictionary, more list of general AI / LLM terms that has connection with Promptbook
| Data & Knowledge Management | Pipeline Control |
|---|---|
|
|
| Language & Output Control | Advanced Generation |
|
|
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.
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.
If you have a question start a discussion, open an issue or write me an email.
See CHANGELOG.md
This project is licensed under BUSL 1.1.
We welcome contributions! See CONTRIBUTING.md for guidelines.
You can also โญ star the project, follow us on GitHub or various other social networks.We are open to pull requests, feedback, and suggestions.
Need help with Book language? We're here for you!
We welcome contributions and feedback to make Book language better for everyone!
FAQs
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
The npm package @promptbook/utils receives a total of 1,528,806 weekly downloads. As such, @promptbook/utils popularity was classified as popular.
We found that @promptbook/utils demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago.ย It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
/Security News
Socket is tracking cloned Open VSX extensions tied to GlassWorm, with several updated from benign-looking sleepers into malware delivery vehicles.
Product
Reachability analysis for PHP is now available in experimental, helping teams identify which vulnerabilities are actually exploitable.
Product
Export Socket alert data to your own cloud storage in JSON, CSV, or Parquet, with flexible snapshot or incremental delivery.