Show HN: One Code, almost all of Claude Code's features on pi, with any model (github.com)

One Code has been introduced as an open-source project that enables users to replicate the Claude Code workflow while allowing for flexibility in the choice of AI models. By integrating features like subagents, context management, and plan execution, One Code simplifies the process of switching between different AI models—like those from Anthropic and OpenAI—without the need for complicated import steps or relearning. This tool is particularly significant for the AI and machine learning community as it empowers developers to optimize tasks using various models, potentially enhancing productivity and resource management. With the ability to assign different models to main and subagents, One Code encourages efficient task delegation, enabling users to mix providers within a single session. Notably, it maintains compatibility with existing Claude Code configurations, ensuring seamless transitions for current users. Key technical features include multi-provider support, auto mode enhancements, and a comprehensive permission system that maintains control over task execution. By fostering an adaptable and customizable workflow, One Code represents a significant step forward in developing user-centered AI coding environments.