Build intelligent AI agent workflows with visual simplicity and enterprise power.
Kasal transforms complex AI orchestration into an intuitive visual experience. Design, deploy, and monitor autonomous AI agents that collaborate seamlessly to solve real-world business challenges.
• Visual Workflow Designer - Drag-and-drop interface for creating sophisticated agent interactions
• Enterprise-Ready - Built for Databricks with OAuth, security, and scalability
• Extensible Toolkit - Rich library of tools including Genie, custom APIs, and data connectors
• Real-time Monitoring - Live execution tracking with detailed logs and performance insights
• Production-Grade - Robust error handling, retry logic, and enterprise deployment patterns
- Data Analysis Pipelines - Agents that query, analyze, and visualize your data
- Content Generation Systems - Collaborative agents for research, writing, and content creation
- Business Process Automation - Intelligent workflows that adapt and make decisions
- Customer Support Bots - Multi-agent systems with specialized knowledge domains
- Research & Development - Agents that gather, synthesize, and present insights
Install directly from the Databricks Apps Marketplace with one click. Perfect for production use with automatic updates and enterprise support.
Use the deployment script in this codebase for custom installations and development. Ideal for customization and advanced configurations.
Quick setup for testing and development - requires Python 3.9+ and Node.js.
Visual workflow designer for creating AI agent collaborations
Create your first agent workflow in under 2 minutes:
- Design - Drag agents onto the canvas and define their roles
- Connect - Link agents to create collaboration flows
- Execute - Hit run and watch your agents work together
- Monitor - View real-time logs and execution traces
| Topic | Description |
|---|---|
| Why Kasal | What problems it solves and who it's for |
| Solution Architecture | Layers, lifecycles, and platform integration |
| Code Structure | Where things live and how to navigate the repo |
| Developer Guide | Local setup, config, and extension patterns |
| API Reference | REST endpoints, payloads, and errors |
- Docs Hub - Documentation index
- End‑User Tutorial Catalog - Screenshot-ready walkthroughs
- Testing Guide - Testing strategy and coverage
Kasal uses a modern, layered architecture designed for scalability and maintainability:
Frontend (React) → API (FastAPI) → Services → Repositories → Database
The CrewAI Engine integrates at the service layer for intelligent agent orchestration.
Entity extraction in memory backends has compatibility issues with:
- Databricks Claude (
databricks-claude-*) - JSON schema validation errors - Databricks GPT-OSS (
databricks-gpt-oss-*) - Empty response errors
Automatic Fallback: The system automatically uses databricks-llama-4-maverick for entity extraction when these models are detected, while keeping the original model for all other agent tasks.
Licensed under the Databricks License
Unlocking Databricks Marketplace: A Hands-On Guide for Data Consumers
