agentkart is an MIT-licensed Python package for creating skill-driven AI agents across domains such as data engineering, RAG, SQL, and infrastructure automation. It provides a reusable agent core with integrations and skills for tools including dbt, PySpark, PyTorch, Terraform, and MCP.
agentkart sits in PulseGate's Frameworks & runtimes category. It focuses on building domain-specific AI agents without implementing a separate agent core for each use case. It is built as an open-source project for AI and data engineers. agentkart is open source under the MIT license. It ships for the command line and API, and it can be self-hosted.
Sumit Gupta builds and maintains agentkart, and it first shipped in 2026. Development happens publicly on GitHub with 8 commits in the last 90 days. Among its 10 catalogued features are skill-based agents, domain skills, and RAG workflows. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do