dsh-mnemon
用于 DeepSeek Harness (DSH) 的跨代理、本地优先持久内存插件，由 Mnemon 驱动。它在启用 Mnemon 的代理之间共享长期记忆，并添加运行时记忆、可搜索项目文档、语义召回、知识图谱和侧边栏 UI。
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
怎么安装
dsh plugin add dsh-mnemon 推荐参考
信息
- 协议
- MIT
- 语言
- JavaScript
- GitHub 星标
- 25
- 月下载
- –
- 最近更新
- 2026-08-14
- 创建于
- 2026-08-10
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:0xsline/awesome-deepseek-harness
- 主题标签
- agent-memory, cross-agent-memory, deepseek-harness, document-search, dsh, dsh-plugin, knowledge-graph, llm-agent, local-first, long-term-memory, memory-plugin, memory-system, mnemon, multi-agent-memory, persistent-memory, project-documents, runtime-memory, semantic-recall, shared-agent-memory, workspace-memory
同类推荐
ruflo
ruvnet/claude-flow
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
sandbase-harness
sandbaseai/sandbase-harness
开源、兼容 CMA 的智能体运行时，适用于任何模型，具有 MCP 工具、沙箱会话、审计、重放和本地控制台。包含基于 stdio MCP 的原生 DeepSeek Harness 包。
modlens
liustack/modlens
为纯文本模型架起视觉桥梁：粘贴图片，输出结构化 JSON 证据（OCR、版面、语义）。
pydantic-ai
pydantic/pydantic-ai
How Python does AI: agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.