Run This Ai
EN DE

SAG

SAG — A new SOTA for RAG. An original retrieval architecture and open-source knowledge base for humans and agents.

★ 2,259 GitHub MIT ragknowledge-baseknowledge-graphagentvector-searchllmgraphrag RAG & Knowledge

Overview

An original retrieval architecture that replaces both traditional RAG and GraphRAG. Through event-entity indexing and query-time dynamic hyperedges, SAG delivers semantic retrieval and relational reasoning in one system. It achieves state-of-the-art results on 8 of 9 Recall metrics across multi-hop QA datasets including HotpotQA, 2WikiMultiHopQA, and MuSiQue. The project is a complete knowledge base application for individuals and Agents: upload documents, SAG parses them, extracts events and entities, and keeps every retrieval result connected to the original text with full source tracing. Features include multi-turn agent chat with citations, knowledge graph inspection, REST/OpenAPI and MCP integration, and a desktop app that requires no installation of Python, Node.js, or databases.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  sag:
    image: 82surf/sag:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/sag:/data

Best VPS for SAG →

Related tools

LangChain

Build context-aware reasoning applications powered by LLMs

Supabase

Open-source Postgres platform for AI apps with vector search, realtime subscriptions & built-in dashboard

RedisStack

Redis with integrated modules for vector search, JSON, and search capabilities

Meilisearch

Lightning-fast search engine with AI-powered hybrid and vector search

PrivateGPT

Chat with your documents privately using LLMs — 100% local, no data leaks

Milvus

High-performance cloud-native vector database for scalable ANN search

Guides & articles

Getting Started with SAG: Deploy Your Own SOTA RAG Knowledge Base

Step-by-step guide to deploying SAG — the new state-of-the-art RAG knowledge base. Learn both desktop and Docker deployment methods, explore key features, and see performance benchmarks.

Jul 30, 2026

SAG: The New State-of-the-Art for RAG Knowledge Bases

Discover SAG — the original retrieval architecture that replaces both traditional RAG and GraphRAG. Learn about its event-entity indexing, query-time dynamic hyperedges, and state-of-the-art performance across multi-hop QA benchmarks.

Jul 30, 2026