Tencent open-sources TencentDB Agent Memory for local AI agent memory
Overview
Tencent has open-sourced TencentDB Agent Memory, a memory system for AI agents that runs locally on SQLite without external vector databases or cloud APIs, according to a post shared by Jerry Liu (@jerryjliu0) on X. The post says the system cuts token use by 61% and raises accuracy on the PersonaMem benchmark from 48% to 76%.
The system stores conversations, atoms, scenarios and personas as readable markdown files. It encodes short-term state as Mermaid graphs and offloads tool logs to disk. These figures come from the post and have not been independently verified.
Written by AI from the articles below · updated Oct 12, 8:14 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
Jerry Liu@jerryjliu0XTencent open-sources TencentDB Agent Memory for local long-term AI agent memoryAIJerry Liu shares a post saying Tencent has open-sourced TencentDB Agent Memory, a memory system for AI agents that runs locally on SQLite without external vector databases or cloud APIs. The post cites a 61% reduction in tokens and a PersonaMem accuracy rise from 48% to 76%. It describes a layered design that stores conversation, atoms, scenarios, and personas as readable markdown, with short-term state encoded as Mermaid graphs and tool logs offloaded to disk.
Heat trend
Not enough continuous observations to show a trend yet.