apenab/pyrlm-runtime
Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT CSAIL paper "Recursive Language Models".
This project helps developers overcome the challenge of processing extremely large text documents or datasets with Large Language Models (LLMs) without hitting token limits. It takes your documents and a question, then uses an LLM to generate Python code to navigate and analyze the context. The output is a concise answer to your query, allowing you to work with massive information volumes efficiently. It is designed for developers who build applications relying on LLMs for complex information extraction or summarization.
Use this if you are building an application where LLMs need to analyze vast amounts of text data (e.g., hundreds of documents, millions of tokens) that would typically exceed LLM context window limits.
Not ideal if your use case involves short, single-turn LLM queries on small to medium-sized texts, or if you prefer a simpler, less code-centric approach to LLM prompting.
Stars
14
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/apenab/pyrlm-runtime"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aalok-sathe/surprisal
A unified interface for computing surprisal (log probabilities) from language models! Supports...
EvolvingLMMs-Lab/lmms-engine
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
FunnySaltyFish/Better-Ruozhiba
【逐条处理完成】人为审核+修改每一条的弱智吧精选问题QA数据集
reasoning-machines/pal
PaL: Program-Aided Language Models (ICML 2023)
microsoft/monitors4codegen
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static...