TencentDB-Agent-Memory
TencentDB Agent Memory provides local long-term memory through a four-layer progressive pipeline, with no dependency on external APIs.
- Region
- Domestic
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 4.9k
- Source
- GitHub
- Added
- 2026-06-04
- Last verified
- 2026-06-04
Overview
TencentDB Agent Memory is a technology that enables AI agents to maintain local long-term memory via a four-layer progressive pipeline, eliminating the need for external API dependencies. It addresses the recurring issue of users having to repeatedly explain standard operating procedures or project context, helping AI agents learn and retain task context to improve efficiency. Ideal for developers seeking to reduce repetitive work and focus more on creative tasks.
Key features
- ▪Symbolic short-term memory
- ▪Hierarchical long-term memory
- ▪Reduced token usage
- ▪Improved task success rate
Use cases
Pros
- ＋Reduces repetitive information input
- ＋Improves task execution efficiency
- ＋Enhances cross-session experience accumulation
Limitations / notes
- －Requires specific Node version
- －Needs integration with a particular framework
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
How does TencentDB Agent Memory reduce token usage?
By compressing repetitive tool logs into compact Mermaid symbols.
Does this technology support all versions of Node.js?
Node.js version must be 22.16 or higher.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.