INXM // local` OSS for using LLM as compiler and not as runtime
Source
github.com
Author
oesimania
Date
Context
INXM Local separates describing a workflow from running its steps. A LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → converts a request into a versioned plan with declared inputs. An executor then follows the plan's dependencies and saves progress after each step. Plans can pause for human answers, and proposed repairs become new versions only when accepted.
This makes the workflow and its revisions inspectable. Model calls can still occur inside designated PROMPT_CALL steps, so the deterministic component is the orchestration, not every answer or external action.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
