v0.14.0

KaibanJS v0.14.0 🚀

🙌 Special Thanks

This release was made possible thanks to:

• Aitor Roma (@aitorroma) from Nimbox360 team
• @anthonydevs17
• The Nimbox360 team

New Tool

import { JinaUrlToMarkdown } from '@kaibanjs/tools';

🌐 Jina URL to Markdown Tool

• Advanced web scraping and content extraction powered by Jina.ai
• Converts web content into clean, LLM-ready markdown format
• Handles complex websites with dynamic content and anti-bot mechanisms
• Configurable output with multiple format options
• Check the docs

🎯 Use Cases

The new Jina tool enables powerful content processing scenarios:

• Extract clean, structured content from any website
• Create AI-ready training data from web sources
• Build knowledge bases from online documentation
• Process and analyze web content at scale

Example combinations:

• Generate summaries from scraped web content
• Create research reports from multiple web sources
• Build custom knowledge bases for AI agents
• Extract and process documentation for training

We're excited to see what content processing workflows you'll create! Share your use cases and feedback with us on GitHub.

v0.13.0

KaibanJS v0.13.0 🚀

Structured Output with Zod

const task = new Task({
  description: "Extract article metadata",
  expectedOutput: "Get the article's title and list of tags", 
  outputSchema: z.object({                                    
    title: z.string(),
    tags: z.array(z.string())
  })
});

New Feature: Structured Output 🎯

• Define exact output structures for your agent tasks
• Runtime validation using Zod schemas
• Automatic error recovery and correction
• Full integration with workflowLogs for monitoring
• Check the docs

Key Capabilities

• ✨ Type-safe outputs with Zod schemas
• 🔄 Automatic validation and correction
• 📊 Complex data structure support
• 🛡️ Runtime type safety
• 📝 Detailed validation feedback

Use Cases

These new structured output capabilities enable:

• Data extraction with guaranteed formats
• Complex form filling with validation
• API response formatting
• Structured report generation

Some example applications:

• Extract product information in consistent formats
• Generate standardized meeting summaries
• Create structured API responses
• Process form submissions with validation

Contributors

Special thanks to @anthonydevs17 for their significant contributions to this feature! 🙏
Thanks also to @harris0n.

We're excited to see what structured workflows you'll create! Share your schemas and feedback with us on GitHub.

v0.12.0

KaibanJS v0.12.0 🚀

import { ZapierWebhook, MakeWebhook } from '@kaibanjs/tools';

New Tools

🔄 Zapier Webhook Tool

• Seamless integration with Zapier's automation platform
• Trigger any Zap with structured data
• Schema validation for reliable data transfer
• Perfect for multi-app automation workflows

Check the docs

⚡ Make Webhook Tool

• Powerful Make (formerly Integromat) integration
• Execute complex scenarios with a single call
• Structured data handling with schema validation
• Secure webhook communication

Check the docs

🎯 Use Cases

These new webhook tools enable powerful automation scenarios:

• Cross-platform notifications and alerts
• Data synchronization between systems
• Automated task creation and management
• Multi-step workflow orchestration

Some example combinations:

• Send AI-generated summaries to team channels
• Automate report generation and distribution
• Create tasks from AI analysis results
• Trigger complex workflows based on AI decisions

We're excited to see what automated workflows you'll create! Share your automations and feedback with us on GitHub.

v0.11.0

KaibanJS v0.11.0 🚀

Special thanks to @anthonydevs17 for this amazing collaboration in bringing these powerful RAG-based tools to life! 🙏

import { SimpleRAG, WebsiteSearch, PDFSearch, TextFileSearch } from '@kaibanjs/tools';

New Tools

🧠 Simple RAG Tool

• Foundational RAG implementation with langchain components
• Flexible configuration for embeddings and vector stores
• Built-in support for OpenAI's latest models
• Perfect for quick RAG prototyping and simple implementations

Check the docs

🌐 Website Search Tool

• Semantic search capabilities for web content
• Built-in HTML parsing with cheerio
• Support for single and multi-page websites
• Ideal for documentation and web content analysis

Check the docs

📄 PDF Search Tool

• Comprehensive PDF document analysis
• Dual runtime support (Node.js and browser)
• Efficient document chunking and processing
• Perfect for document analysis and knowledge extraction

Check the docs

📝 Text File Search Tool

• Optimized for plain text document analysis
• Smart text chunking and processing
• Seamless integration with existing workflows
• Excellent for logs and documentation search

Check the docs

🔧 Common Features

All tools include:

• Advanced RAG technology integration
• OpenAI embeddings support
• Customizable vector store options (including Pinecone)
• Flexible chunking configurations
• Server-side execution support

🎯 Use Cases

These RAG-powered tools enable powerful combinations for:

• Documentation search and analysis
• Knowledge base creation and querying
• Content extraction and processing
• Intelligent document management

🔄 Vector Store Integration

All tools support custom vector stores, with built-in support for:

• Memory Vector Store (default)
• Pinecone
• Other langchain-compatible stores

We're excited to see what you'll build with these new RAG capabilities! Share your creations and feedback with us on GitHub.

v0.10.0

KaibanJS v0.10.0 🚀

import { Serper, WolframAlphaTool, ExaSearch, GithubIssues } from '@kaibanjs/tools';

New Tools

🔍 Serper Search Results

• Direct access to Google search capabilities through Serper API
• Multiple search types (web, news, images)
• Well-formatted JSON responses for LLM processing
• Perfect for news gathering and content research

Check the docs

🧮 Wolfram Alpha Tool

• Powerful computational knowledge engine integration
• Complex mathematical problem-solving
• Scientific data analysis and visualization
• Formula processing and calculations

Check the docs

🔬 Exa Search

• Advanced neural search capabilities
• Content processing with summaries and highlights
• Auto-prompt enhancement for better queries
• Ideal for academic and research tasks

Check the docs

📊 GitHub Issues Tool

• Seamless GitHub issues integration
• Automatic pagination for large repositories
• Structured issue data retrieval
• Flexible authentication with rate limit management

Check the docs

🎯 Use Cases

These new tools enable powerful combinations for:

• Research and academic analysis
• Scientific computing and data processing
• News monitoring and content creation
• Repository management and issue analysis

We're excited to see what you'll build with these new capabilities! Share your creations and feedback with us on GitHub.

v0.9.1

🎉 KaibanJS Release Notes - v0.9.1

We're excited to announce the release of KaibanJS v0.9.1!

Special thanks to @alienkarma for this one 🤗.

🔧 Enhancements

Development Experience Improvements

• Added ESLint and Prettier configuration to maintain consistent code style (#69)
  • Implemented pre-commit hooks for automated linting and formatting
  • Added new npm scripts for code quality checks:
    • npm run lint:check - Check for lint errors
    • npm run lint:fix - Attempt to fix lint errors
    • npm run format:check - Check for formatting errors
    • npm run format:fix - Fix formatting errors

🐛 Bug Fixes

Type Definitions

• Fixed ITeamParams interface to properly support arrays and other primitive types in the inputs field (#99)
  • Previously only supported string values
  • Now correctly handles arrays and other primitive types as input parameters

📝 Developer Notes

• For optimal development experience, it's recommended to install the following IDE plugins:
  • ESLint (VS Code Extension)
  • Prettier (VS Code Extension)

v0.9.0

KaibanJS Tools v0.9.0

🚀 New Features

The Tool package

Until now, KaibanJS relied on third-party implementations and APIs for the tools that agents use. While these solutions are great, we found that having different implementation patterns added some complexity to tutorials and examples.

To help simplify this, we've started an experimental tools package. It's a humble beginning with just two tools, but we'd love for the community to join us in building this together! Whether you have ideas for new tools, improvements to existing ones, or just want to share your experience - we'd be thrilled to have your input.

https://docs.kaibanjs.com/category/kaibanjs-tools

New Tools

• Firecrawl: Web scraping tool for converting websites into LLM-ready content

  • Supports both markdown and HTML output formats
  • Handles dynamic content and JavaScript rendering
  • Built-in rate limiting and anti-bot protection

  Check the docs here

• Tavily Search Results: AI-optimized search engine for accurate and trusted results

  • Real-time information retrieval
  • Configurable maximum results
  • Well-structured JSON output

  Check the docs here

v0.8.5

KaibanJS v0.8.5 - Release Notes

🚀 New Feature

• CLI Enhancement: The KaibanJS CLI now includes the installation of @kaibanjs/tools package alongside KaibanJS. This addition simplifies the setup process by providing essential tools out-of-the-box, streamlining the user experience.

v0.8.4

KaibanJS Release Notes - Version 0.8.4

Bug Fixes

Tools Array Initialization: We've fixed an issue where the BaseAgent constructor did not initialize the tools array if not provided, which could lead to runtime errors. Now, the constructor defaults the tools array to empty, ensuring all instances of BaseAgent start with a properly initialized tools property. This change prevents potential bugs and improves the stability of agent operations.

Thanks to @zhaopengme for reporting it :)

v0.8.2

KaibanJS Release Notes - Version 0.8.2

We're excited to introduce anonymous telemetry in KaibanJS 0.8.2 to help improve the library's performance and user experience.

Key Features

1. Privacy-First Telemetry

   • Collects only anonymous, non-personal information
   • Lightweight and GDPR compliant

2. Targeted Data Collection

   • Installation, Board Run, Board Init (CLI)
   • Workflow Start (Runtime)

3. User Control

   • Easy opt-out: export KAIBAN_TELEMETRY_OPT_OUT=true

4. Transparent Documentation

   • New section explaining telemetry and its benefits

Why It's Important

• Helps us understand real-world usage
• Allows for targeted improvements
• Respects user privacy

For more details, check our new Telemetry Documentation.

Thank you for using KaibanJS and for your support in making it better!

The KaibanJS Team