# LangChain pairs OpenWiki with an evidence graph for traceable agent memory

> Original title: Great look at making agent memory traceable to evidence ⤵️

- Source: LangChain
- Published: 2026-10-28T18:25:26.000Z
- Bad Influence: https://badinfluence.news/items/i66m8lnjsoa2a2byn52eqcgrk
- Original: https://x.com/LangChain/status/2115510265911418951

## Summary

LangChain says pairing its OpenWiki knowledge base with a lightweight evidence graph lets agents follow relationships and trace answers to supporting evidence. On complex, cross-source questions, the company reports 5x higher accuracy than grep alone, 27% more accuracy with the graph, and 2x citation consistency. It also reports 58% lower cost per correct answer with the graph.

## Post

Great look at making agent memory traceable to evidence ⤵️

## Quoted post @colifran_

> we've been exploring how to make the knowledge openwiki produces more useful to agents.
> 
> our latest experiment pairs the wiki with a lightweight evidence graph, letting agents follow relationships and trace information back to supporting evidence.
> 
> on complex, domain-specific questions requiring cross-source reasoning we saw:
> 👉 5x higher accuracy with openwiki vs. grep alone
> 👉 27% more accurate with the evidence graph
> 👉 2x citation consistency
> 👉 58% lower cost per correct answer with the graph
> 
> check out the blog ⤵️
> https://www.langchain.com/blog/building-agent-memory-openwiki-graphs

https://x.com/colifran_/status/2115509137790656623