LLM Digest

Story

langchain_blog · Oct 28, 2026 · news

Source brief

How to build evidence-grounded agent memory with OpenWiki and Graphs

the LangChain blogOct 28, 2026
original source linked

In brief

LangChain used OpenWiki, its open-source wiki compiler, and an evidence graph to build a persistent memory layer that preserves knowledge for agents to reuse across tasks. Learn how.

Feed lens

agent

Read the original at langchain.com →Open in live feed

How to build evidence-grounded agent memory with OpenWiki and Graphs

Earlier in this thread 4 items

Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation

MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning

MACE: Memory-Agent Co-Evolution with Adaptive Memory Graphs for Multi-Agent Systems

How Credit Genie keeps codebase docs fresh with OpenWiki