DSH-TDAI-Memory-Adapter
Run the following command in DeepSeek Harness:
dsh plugin install Vocllum/DSH-TDAI-Memory-Adapter
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness. Source: https://github.com/Vocllum/DSH-TDAI-Memory-Adapter
About this plugin
DeepSeek Harness aims to build smarter agents but often struggles with integrating long-term memory effectively. The DSH TDAI Memory Adapter serves as a lightweight solution to this challenge. Instead of replicating a heavy memory core, it acts as a seamless connector to an existing TencentDB Agent Memory Gateway and Core service.
The plugin's core capabilities focus on "Intelligent Association" and "Focused Tools." It supports auto Recall, retrieving relevant memories to inject context before Agent execution. It features a Turn Capture mechanism to prevent duplicate submissions and provides read-only search tools for active exploration. Additionally, it ensures high availability through asynchronous background processing and fail-open isolation strategies.
For developers who have already deployed the TencentDB Agent Memory service and wish to quickly gain memory capabilities within DeepSeek Harness, this is the ideal choice. It eliminates the overhead of a full UI and local directory management, focusing instead on DSH lifecycle management and identity passing, allowing agents to possess powerful memory and retrieval skills while maintaining a lightweight architecture.
Use Cases
- Intelligent chatbots requiring long-term memory
- DeepSeek projects integrating TencentDB memory services
- Customer service systems with historical retrieval capabilities
- Building Agent applications based on knowledge bases
Best For
- Developers who have deployed TencentDB Agent Memory
- Users who want to add memory functions to DeepSeek
- Technical teams looking for lightweight memory solutions
- Developers wishing to reuse existing infrastructure
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.