TencentCloud/TencentDB-Agent-Memory
#113 of 803 by Stars among GitHub repos
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, shared, and equipped across agents and frameworks.
About
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.
When integrated with OpenClaw, it cuts token usage by up to 61.38%, improves pass rate by 51.52% (relative), and raises PersonaMem accuracy from 48% to 76%.
These results are measured over continuous long-horizon sessions, not isolated turns. For example, SWE-bench runs 50 consecutive tasks per session to simulate the…
Excerpted from github.com/TencentCloud/TencentDB-Agent-Memory
Latest metrics
| Stars | 26.8k | 2026-09-15 |
|---|---|---|
| Forks | 2.5k | 2026-09-15 |
| Commits | 36 | 2026-09-15 |
| Releases | 16 | 2026-09-15 |
| Watchers | 92 | 2026-09-15 |
| Open issues | 226 | 2026-09-15 |
| Open PRs | 544 | 2026-09-15 |