DeepSeek Harness Hierarchical Long-Term Memory Plugin
`dsh-layered-memory` is a static plugin for DeepSeek Harness (DSH), designed to address the issue of agents forgetting context during multi-turn conversations. The plugin organizes memory into transient, episodic, and semantic layers, uses AI to automatically refine and deduplicate information, and supports maintaining continuity across sessions. After installation, it requires zero configuration, and models can invoke four tool functions in natural language to perform memory retrieval, writing, and committing. Plugin data is stored in local JSON files, while the management interface is provided through an HTTP API, including operations for statistics, retrieval, and create, update, and delete, ensuring data privacy and security.
Read Moredsh-layered-memory: DSH Cross-Session Long-Term Memory Plugin
dsh-layered-memory is a cross-session long-term memory plugin for DeepSeek Harness (DSH), licensed under the MIT License, designed to address the issue of context loss following a session. The plugin persistently stores verified facts, task experiences, and environmental information on disk, supporting cross-session retrieval. Core features include L1-L3 layered memory, namespace isolation, BM25 full-text search, content deduplication, and cross-namespace experience enhancement. The plugin provides 14 memory tools, such as `memory_write` (mandatory evidence verification), `memory_search`, and `memory_index`, and supports progressive tool exposure. Consistency maintenance relies on deduplication, manual updates, and candidate merging; the system does not automatically detect contradictions, and it is strictly prohibited to physically discard verified facts, allowing only compression.
Read More