by Tencent · Codex 技能 · ★ 4.5k
Agents remember,Humans innovate. Highlights · Overview · Core Technology · Features · Quick Start English · 简体中文 ✨ Highlights TencentDB Agent Memory = symbolic short-term memory + layered long-term memory. - Symbolic short-term memory offloads heavy tool logs and condenses them into compact Mermaid symbols, cutting token usage and improving task success. - Layered long-term memory distills fragmented conversations into structured personas and scenes, instead of flat vect
| Stars | 4,540 |
| Forks | 379 |
| Language | TypeScript |
| Category | Codex 技能 |
| Quality Score | 68.9686248318477/100 |
| Open Issues | 56 |
| Last Updated | 2026-06-02 |
| Created | 2026-04-07 |
| Platforms | node |
| Est. Tokens | ~216k |
Explore other popular codex 技能 tools:
TencentDB-Agent-Memory is TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.. It is categorized as a Codex 技能 with 4.5k GitHub stars.
TencentDB-Agent-Memory is primarily written in TypeScript. It covers topics such as agent, ai-agent, embedding.
You can find installation instructions and usage details in the TencentDB-Agent-Memory GitHub repository at github.com/Tencent/TencentDB-Agent-Memory. The project has 4.5k stars and 379 forks, indicating an active community.