least clickbait slop post
Tencent open-sources TencentDB Agent Memory for local long-term AI agent memory
AISummary
Jerry 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.
Post on XView on X
Jerry LiuVerified on X
@jerryjliu0
China has killed the entire vector database industry. They open-sourced TencentDB Agent Memory. It gives any AI agent long-term memory that runs 100% locally. No Pinecone. No cloud APIs. No repeating yourself every session. - 61% fewer tokens - PersonaMem accuracy: 48% → 76% - Zero external API dependencies - Runs on plain SQLite Most memory systems compress your history into an opaque vector pile. when recall goes wrong, you're guessing. this one doesn't compress, it builds a semantic pyramid. L0 Conversation → L1 Atom → L2 Scenario → L3 Persona. Short-term state gets encoded as a Mermaid graph in your agent's context. verbose tool logs get offloaded to disk. when the agent needs proof, it drills back via node_id to the exact raw log. no lossy compression. every layer is readable markdown you can just open and inspect. 5.1k stars. 100% Open Source.
Source: Jerry Liu · x.comPublished · added here