RLM
Handles massive contexts exceeding token limits by chunking content strategically, enabling recursive sub-queries with tool access
Implements the Recursive Language Model (RLM) pattern for handling massive contexts that exceed token limits by treating content as external variables rather than loading directly into prompts. Supports multiple LLM providers (Claude SDK, Ollama), automatic content type detection with optimized chunking strategies, parallel batch processing with concurrency controls, and context persistence to disk. Designed for analyzing large codebases, documents, or datasets by decomposing them into manageable pieces while maintaining hierarchical processing capabilities through controlled recursion depth.
Source
Repository: https://github.com/richardwhiteii/rlm
Maintain RLM?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[RLM on getagentictools](https://getagentictools.com/mcp/richardwhiteii-rlm?ref=badge) Related mcp
Zig Integrates with Zig tooling to provide code optimization, analysis, and generation capabilities for efficient Zig development.
Home Assistant (Vibecode) IDE-integrated development environment for creating and managing Home Assistant automations, dashboards, themes, and configuration
WeMo Smart Home Control WeMo smart home devices — discover, toggle, adjust brightness, and manage HomeKit codes.
ZenML Integrates with ZenML to enable querying pipeline metadata, triggering new runs, and analyzing ML workflow history through Python-
Weather Provides real-time weather information for any city through the Open-Meteo API without requiring API keys or complex setup.
VChart Generates interactive charts and visualizations using the VChart library, supporting over 15 chart types from basic line and bar c