The Ralph Wiggum plugin implements a development methodology designed for iterative, self-referential AI development loops within Claude Code. Based on the concept of continuous AI agent loops, the plugin uses a Stop hook to intercept exit attempts, effectively feeding the same prompt back to the agent until a specific completion promise is met. This allows the AI to autonomously improve its work by observing its own previous outputs, file modifications, and git history. It is particularly well-suited for well-defined tasks with clear success criteria, such as building APIs or passing test suites, emphasizing the philosophy that persistent iteration is more effective than seeking immediate perfection.
LLM-powered Rust development assistant with meta-cognition framework.
Simon Willison introduces llm-smollm2, a plugin for LLM that includes a quantized version of the SmolLM2-135M-Instruct model. The article details how to install and use the model, discusses the process of finding, building, packaging, and publishing the plugin, and evaluates the model's capabilities.
A new plugin for LLM, llm-jq, generates and executes jq programs based on human-language descriptions, allowing users to manipulate JSON data without needing to write jq syntax.
An optional component to enable AI features in iTerm2, providing network request functionality, ensuring secure data transmission.
