by TencentCloud · Codex 技能 · ★ 29.6k
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 vector piles.
| Stars | 29,631 |
| Forks | 2,978 |
| Language | TypeScript |
| Category | Codex 技能 |
| Quality Score | 66.7743118858515/100 |
| Open Issues | 772 |
| Last Updated | 2026-10-19 |
| Created | 2026-04-07 |
| Platforms | node |
| Est. Tokens | ~19k |
These tools work well together with TencentDB-Agent-Memory for enhanced workflows:
Explore other popular codex 技能 tools:
TencentDB-Agent-Memory is TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, s. It is categorized as a Codex 技能 with 29.6k 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/TencentCloud/TencentDB-Agent-Memory. The project has 29.6k stars and 2978 forks, indicating an active community.