腾讯开源的四层本地记忆管线解决了智能体长期记忆的痛点，做本地 AI 应用或智能体开发的团队可以直接集成，建议试试这个 MIT 许可的方案。
腾讯开源了 TencentDB Agent Memory，一个完全本地的 AI 智能体记忆系统，采用 MIT 许可证。该系统结合了符号短期记忆（将冗长的工具日志压缩为紧凑的 Mermaid 任务画布）和四层长期记忆金字塔（L0 对话 → L1 原子 → L2 场景 → L3 人格）。它作为 OpenClaw 插件和 Hermes Docker 镜像提供，默认在本地 SQLite + sqlite-vec 上运行，并使用混合 BM25 + 向量检索与 RRF 融合。腾讯自己的基准测试显示，在 WideSearch 上使用 OpenClaw 时，令牌减少 61.38%，相对通过率提升 51.52%，PersonaMem 准确率从 48% 提升到 76%。
Tencent Open-Sources TencentDB Agent Memory: A 4-Tier Local Memory Pipeline for AI Agents
Tencent has open-sourced TencentDB Agent Memory, a fully local memory system for AI agents released under the MIT license. The project pairs symbolic short-term memory, which offloads verbose tool logs into a compact Mermaid task canvas, with a 4-tier long-term memory pyramid (L0 Conversation → L1 Atom → L2 Scenario → L3 Persona). It ships as an OpenClaw plugin and a Hermes Docker image, runs on local SQLite + sqlite-vec by default, and uses hybrid BM25 + vector retrieval with RRF fusion. Tencent's own benchmarks report a 61.38% token reduction and 51.52% relative pass-rate gain on WideSearch with OpenClaw, alongside PersonaMem accuracy moving from 48% to 76%. The post Tencent Open-Sources TencentDB Agent Memory: A 4-Tier Local Memory Pipeline for AI Agents appeared first on MarkTechPost .