It sounds like you've created a useful package called claude-runner that simplifies working with the Claude Code platform by Anthropic. This package aims to make it easier for developers to integrate and utilize Claude's capabilities in their projects, particularly around code generation, testing, and more.
Here are some key points about your project:
- Simplified API: The package abstracts away complex interactions with the
@anthropic-ai/claude-agent-sdkby providing a simpler interface. - Docker & E2B Support: It includes sandboxing options to run code in isolated environments, enhancing security and flexibility.
- CLI Tool: A command-line interface is provided for easy integration into workflows.
- Session Management: Supports resuming sessions and multi-turn conversations, keeping context intact.
Key Features
-
Simplified MCP Configuration:
- Allows users to configure Model Context Protocol (MCP) services with shorthand strings or full configurations.
-
Docker & E2B Sandboxes:
- Provides options for running code in Docker containers and cloud-based VMs, ensuring that tools operate within isolated environments.
-
Multi-Turn Conversations:
- Supports resuming sessions
Read the full article at DEV Community
Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.

![[AINews] The Unreasonable Effectiveness of Closing the Loop](/_next/image?url=https%3A%2F%2Fmedia.nemati.ai%2Fmedia%2Fblog%2Fimages%2Farticles%2F600e22851bc7453b.webp&w=3840&q=75)



