necigit/@dsh-external/dsh-client-coral
“脑珊瑚 Coral Memory — 面向 LLM Agent 的热度感知记忆层（DeepSeek Harness 插件）：MCP 记忆工具（memory_search/insert/thread_* 等 16 个）+ 设置面板（统计/容…”
脑珊瑚 Coral Memory — 面向 LLM Agent 的热度感知记忆层（DeepSeek Harness 插件）：MCP 记忆工具（memory_search/insert/thread_* 等 16 个）+ 设置面板（统计/容量/检索/配额）。作者：Mr. Code Muggle (@Ne)。
volcengine/OpenViking
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
vectorize-io/hindsight
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
mnemon-dev/mnemon
Install the full dsh-mnemon integration from the Mnemon repository.
Ikalus1988/MisakaNet
Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.