LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with ...
Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggabl...
支持Cursor、Codex、Claude Code等AI编程工具，自动抓取会话内容整理后同步至Obsidian知识库，无需手动归档即可沉淀编程思路方案，次日可直接检索。
Structured memory engine for DeepSeek Harness. Offline semantic search, entity-attribute-timeline, autoDream self-consol...
支持AI Agent跨会话持久存储记忆，可随交互持续学习更新，基于智能论v3.2实现可审计的信任验证机制，保障记忆可靠性，让智能体交互更连贯稳定。
提供热启动、中文BM25冷召回、租约锁事务写入与只读管控能力，本地优先架构保障数据自主可控，无需云端依赖即可实现高效记忆存储与检索。
Persistent engineering memory for coding agents over MCP.
生物仿生记忆系统插件：Biomimetic memory for DeepSeek Harness — transparent Markdown memory, approval-gated writes, frozen snapshot ...
提供全权限持久化运行的智能代理能力，依托成熟Harness运行时框架构建，支持跨会话保持运行状态、无限制调用系统资源，部署简单运行稳定，可无缝对接各类自动化任务流程。
Local-first cross-session memory for DeepSeek Harness (DSH): automatic capture, Event/Element cards, evidence-gated reca...
MindForge技术栈实现四层加密的终身记忆能力，可无缝接入DeepSeek Harness框架，自动完成记忆数据的加密存储与分层调用，无需额外配置即可为AI应用提供长期稳定的上下文记忆支撑，兼顾数据安全与调用效率。
PLUR memory for DeepSeek Harness — engrams injected into the system prompt, no tool call required. Local-first, Apache-2...