Skip to content

Latest commit

 

History

History

README.md

Self-Correcting Agent Kernel (SCAK) — Community Edition

Part of Agent OS - Kernel-level governance for AI agents

PyPI version Python License: MIT

Basic self-correction with retry for AI agents.

SCAK provides a lightweight self-correction loop that detects agent failures and retries with corrective feedback. When an agent produces an incorrect or incomplete result, SCAK catches the failure, applies a correction strategy, and retries the action.

Installation

pip install scak

Quick Start

from scak import SelfCorrectingKernel

kernel = SelfCorrectingKernel()
result = await kernel.run(task="Summarize this document", max_retries=3)

Features

  • Failure detection and classification
  • Configurable retry strategies
  • Memory of past corrections to avoid repeated mistakes
  • Integration with Agent OS policy engine

Documentation

See docs/ for guides and CONTRIBUTING.md for development setup.

License

MIT License - see LICENSE for details.