name: rlm title: Recursive Language Model - Long Context Processing version: 1.0.0 category: retrieval description: > Process documents exceeding context limits using RLM pattern. Chunk large files, delegate to sub-LLM, synthesize results. For massive single files (logs, transcripts, dumps). user-invocable: true author: Brainqub3 tags:
| #!/usr/bin/env python3 | |
| """Persistent mini-REPL for RLM-style workflows in Claude Code. | |
| This script provides a *stateful* Python environment across invocations by | |
| saving a pickle file to disk. It is intentionally small and dependency-free. | |
| Typical flow: | |
| 1) Initialise context: | |
| python rlm_repl.py init path/to/context.txt | |
| 2) Execute code repeatedly (state persists): |