top of page

Knowledge graphs × LLMs for autonomous agents

2 hours ago
1 min read

By @yoheinakajima — BabyAGI creator Yohei Nakajima maps how knowledge graphs ground LLM agents—GraphRAG-style ingestion, embeddable graph DBs, and graphs to track agent task flow. Why structured KG memory beats raw chunk retrieval for multi-hop reasoning.

 
 
 

Recent Posts

See All
Open-sourcing MindGraph

By @yoheinakajima — MindGraph starter kit for building and querying an expanding knowledge graph via natural language—relevant to company-data enrichment and enterprise knowledge layers. Read on X: ht

 
 
 
Build Agents that never forget

By @akshay_pachaar — First-principles walkthrough of agent memory—from lists and files to vector search and graph–vector hybrids for multi-hop business questions. Read on X: https://x.com/akshay_pacha

 
 
 
Why memory isn’t a plugin (it’s the harness)

By @sarahwooders — Letta CTO Sarah Wooders explains why agent memory isn’t a bolt-on: context loading, compaction, and long-term recall are core harness responsibilities. Read on X: https://x.com/sara

 
 
 

Comments

bottom of page