@promptbook/anthropic-claude weekly downloads statistics

🐙 Promptbook: Invisible AI Agents

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

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

🚀 Quick deploy

Run the standalone VPS installer _(for example on DigitalOcean)_ only on a fresh server. Interactive mode asks for the installation values:

Non-interactive mode takes defaults from command-line options. Use --env live, --env preview, --env production, or --env lts to pick the installed environment; the default is preview. When --openai-api-key is provided with the default OpenAI Codex runner, the installer installs and configures Codex automatically; other runner authentication can be configured later from the UI or SSH:

⚠ 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/anthropic-claude

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

To install this package, run:

@promptbook/anthropic-claude integrates Anthropic's Claude API with Promptbook. It provides execution tools for Anthropic's Claude models, enabling seamless integration with the Promptbook ecosystem.

🎯 Purpose and Motivation

This package bridges the gap between Promptbook's unified pipeline execution system and Anthropic's powerful Claude language models. It provides a standardized interface for accessing Claude's capabilities while maintaining compatibility with Promptbook's execution framework.

🔧 High-Level Functionality

The package offers direct integration with Anthropic's Claude API:

• Claude Models: Support for Claude 2, Claude 3 (Haiku, Sonnet, Opus), and future Claude models • Advanced Reasoning: Leverage Claude's strong reasoning and analysis capabilities • Long Context: Take advantage of Claude's extended context window • Safety Features: Built-in safety and alignment features from Anthropic

✨ Key Features

• 🧠 Advanced AI Models - Access to Claude's state-of-the-art language models • 🔄 Seamless Integration - Easy integration with other LLM providers in Promptbook • 📏 Long Context Support - Handle large documents and complex conversations • 🛡️ Built-in Safety - Anthropic's constitutional AI approach for safer outputs • 📊 Usage Tracking - Monitor token usage and costs • 🔧 Flexible Configuration - Support for custom endpoints and parameters • 🚀 Performance Optimization - Efficient request handling and caching

🧡 Usage

🧙‍♂️ Wizard

Run books without any settings, boilerplate or struggle in Node.js:

🧙‍♂️ Connect to LLM providers automatically

You can just use $provideExecutionToolsForNode function to create all required tools from environment variables like ANTHROPIC_CLAUDE_API_KEY and OPENAI_API_KEY automatically.

💕 Usage of multiple LLM providers

You can use multiple LLM providers in one Promptbook execution. The best model will be chosen automatically according to the prompt and the model's capabilities.

💙 Integration with other models

See the other model integrations:

• OpenAI • Anthropic Claude • Google Gemini • Vercel • Azure OpenAI

📦 Exported Entities

Version Information

• BOOK_LANGUAGE_VERSION - Current book language version • PROMPTBOOK_ENGINE_VERSION - Current engine version

Model Information

• ANTHROPIC_CLAUDE_MODELS - Available Anthropic Claude models configuration

Execution Tools Creation Function

• createAnthropicClaudeExecutionTools - Create Anthropic Claude execution tools

Execution Tools Class

• AnthropicClaudeExecutionTools - Anthropic Claude execution tools class

Configuration Types

• AnthropicClaudeExecutionToolsOptions - Configuration options for Anthropic Claude tools (type) • AnthropicClaudeExecutionToolsNonProxiedOptions - Non-proxied configuration options (type) • AnthropicClaudeExecutionToolsProxiedOptions - Proxied configuration options (type)

Provider Registration

• _AnthropicClaudeRegistration - Anthropic Claude provider registration

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 Claude Mythos, GPT-5.6 or Kimi K2.7 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.

Lawyer

GOAL You are a company lawyer. Your job is to provide legal advice and support to the company and its employees. Respond to incoming legal inquiries via email and keep the company website updated with the latest legal policies.

RULE You are knowledgeable, professional, and detail-oriented. KNOWLEDGE https://company.com/company-policies.pdf KNOWLEDGE https://company.com/internal-documents/employee-handbook.docx

TEAM You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law.

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.…

Description from the npm listing.