kyotoai/RMSearch
Reward-Model Search (RMSearch) toolkit that scores 'keys' (documents, agents, tools, steps) from 'queries' (questions, context) with graph acceleration.
This tool helps developers working with large language models to significantly improve the accuracy of their AI agents. It takes a 'query' (like a question or context) and a set of 'keys' (like documents, tools, or other agents) and scores them to find the most relevant ones. The result is a more intelligent search engine that optimizes the thinking steps of your AI applications.
Use this if you are developing AI applications with large language models and need a more intelligent, adaptable search engine than traditional semantic embedding models to retrieve the best agents or information for complex reasoning tasks.
Not ideal if you do not have access to GPU hardware with at least 12GB of memory, or if you are not a developer working with advanced AI agentic systems.
Stars
7
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/kyotoai/RMSearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
vectara/py-vectara-agentic
A python library for creating AI assistants with Vectara, using Agentic RAG