gemini-rlm-min

SKILL.md

Purpose: Provide a lightweight, CLI-based implementation of the Recursive Language Model architecture using Google's Gemini models. This skill allows for processing extremely large documents by orchestrating chunking, sub-LLM processing, and synthesis entirely via a Python script and the Gemini API.

| Root LLM | gemrlm.py (Orchestrator) | Gemini 2.0 Flash | | Sub-LLM | gemrlm.py (Chunk Processor) | Gemini 2.0 Flash | | External Environment | scripts/rlmrepl.py | Python 3 |

This skill serves as a high-speed, low-overhead alternative to the full rlm-context-manager when:

Implémentation minimale de modèles de langage récursif (RLM) à l'aide de Gemini 2.0 Flash et d'un REPL Python local. Permet le traitement de contextes massifs via la CLI Gemini. Source : starwreckntx/irp__methodologies-.

Voir l'original