腾讯开源 TencentDB Agent Memory：本地运行的智能体长期记忆
腾讯开源的智能体记忆方案，跑在本地 SQLite 上，不用向量库和云 API，准确率在 PersonaMem 上从 48% 拉到 76%，可以自己搭一套试试。
腾讯开源了 TencentDB Agent Memory，让 AI 智能体在本地获得长期记忆，全部基于 SQLite 运行，不依赖 Pinecone 等外部向量数据库和云端 API。它不做有损压缩，而是构建 L0 对话、L1 原子、L2 场景、L3 人格的四层语义结构，各层均为可读的 Markdown。短期状态以 Mermaid 图编码进上下文，冗长的工具日志转移到磁盘，需要时通过 node_id 回溯到原始日志。官方数据显示 token 消耗减少 61%，PersonaMem 基准准确率从 48% 提升到 76%。项目已获 5.1k stars，代码完全开源。
least clickbait slop post Divyanshi @Divyyanshishrma 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. 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 2 👀 365 📊 1 ⚡
