Kasal
Build intelligent AI agent workflows with visual simplicity and enterprise power.
Kasal turns complex AI orchestration into an intuitive visual experience. Design, deploy, and monitor autonomous AI agents that collaborate to solve real-world business problems — without writing orchestration code.
Why Kasal?
- Visual Workflow Designer — Drag-and-drop canvas for composing sophisticated agent interactions
- Enterprise-Ready — Built for Databricks with OAuth, teamspace isolation, and scale in mind
- Extensible Toolkit — A rich library of tools, including Genie, MCP servers, custom APIs, and data connectors
- Real-Time Monitoring — Live execution tracking with detailed logs, traces, and performance insights
- Production-Grade — Robust error handling, retry logic, and enterprise deployment patterns
What You Can Build
- 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 Assistants — Multi-agent systems with specialized knowledge domains
- Research & Development — Agents that gather, synthesize, and present insights
Get Started in Minutes
Databricks Marketplace (Recommended)
Install directly from the Databricks Apps Marketplace with one click — the best path for production, with automatic updates and enterprise support.
Deploy from Source
Use the deployment script in this repository for custom installations. Ideal for tailored configurations and advanced setups.
Local Development
A quick setup for testing and development — requires Python 3.11 (pinned >=3.11,<3.12), uv and Node.js 22.
cd src/backend && ./run.sh # API on http://127.0.0.1:8000, SQLite by default
cd src/frontend && npm ci && npm start # UI on http://localhost:3000
run.sh syncs dependencies with uv, binds to loopback, and enables a local development identity (LOCAL_DEV_AUTH). See the Quick Start for details.
See It in Action
Create your first agent workflow in under two minutes:
- Design — Drag agents onto the canvas and define their roles
- Connect — Link agents together to form collaboration flows
- Execute — Hit run and watch your agents work as a team
- Monitor — Follow real-time logs and execution traces
Documentation
| 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 |
| Configuration | Environment variables, defaults, and where they are read |
More Documentation
- Docs Hub - Documentation index
- End‑User Tutorial Catalog - Screenshot-ready walkthroughs
- Testing Guide - Testing strategy and coverage
- Continuous Integration - CI workflows and how to run the checks locally
- Contributing - How to set up, test, and submit a change
Architecture
Kasal follows a clean, layered architecture designed for scalability and maintainability:
Frontend (React) → API (FastAPI) → Services → Repositories → Database
Agents run on Kasal's own runtime (src/backend/src/services/execution/runtime/), with CrewAI available as an alternative harness. See Harnesses.
License
Licensed under the Databricks License
Additional Resources
Unlocking Databricks Marketplace: A Hands-On Guide for Data Consumers
1 maintainer
Metadata
1 maintainer
Release files for kasal 2.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| kasal-2.0.0.tar.gz | 11.1 MB | Without provenance | Details for kasal-2.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| kasal-2.0.0-py3-none-any.whl | Python 3 | none | any | Details for kasal-2.0.0-py3-none-any.whl |
Total release size: 23.1 MB
Release files / kasal-2.0.0.tar.gz
| Download URL | kasal-2.0.0.tar.gz |
|---|---|
| Size | 11.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
024de8d5ab43d115124d2ce340790f740d7b50294c3d4482ae43684a67040056
|
|
BLAKE2b-256 checksum How to use checksums |
bfe7411d523c07eded3e0a9a9ac97a6eb0e884aaa3f5d449f18756a1c2dbcf0a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.33 {"installer":{"name":"uv","version":"0.11.33","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / kasal-2.0.0-py3-none-any.whl
| Download URL | kasal-2.0.0-py3-none-any.whl |
|---|---|
| Size | 12.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c488d95ee18518d21a2d2d429e685b1d3311a92aec9a069905a3185c7f0179cb
|
|
BLAKE2b-256 checksum How to use checksums |
6dbc8c60e9b928cec82410a64b497a8c649b5181c86b460cfbdba966475af289
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.33 {"installer":{"name":"uv","version":"0.11.33","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for kasal 2.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
