No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by FuRongJun-1999 · MCP Server · ★ 227
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dsh-memory safe to install? View the security audit →
让 AI Agent 拥有不可遗忘的自我 灵枢（AEIS）× DeepSeek Harness · AGI 的长期记忆基础设施 一句话：dsh-memory 让 DeepSeek Agent 拥有 AGI 级别的长期记忆——跨会话、自演化、可审计。 这不是又一个"记忆插件"。灵枢（AEIS）是一套遵循「智能论 v3.2」协议的时空记忆引擎，它把当前大模型范式缺失的 AGI 能力逐一给了工程实现。 ⚡ 三步快启（30 秒上手） ⚠️ 安装方式：插件必须通过 装进 profile（它会用 pnpm + 正确解析 peer 依赖）。 不要用 把插件装进 profile 的 ——那会引入错误版本的 peer 包，导致插件加载失败 / 浏览器报错。 想自己改源码？克隆 后用 （构建插件本身），再用 部署。 兼容：DSH 官方列表（Memory 分类）· npm （0.2.8）。 AGI 需要什么 · 灵枢提供了什么 自我认知
| Stars | 227 |
| Forks | 17 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 59.1050041054535/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-20 |
| Created | 2026-08-14 |
| Platforms | mcp, python |
| Est. Tokens | ~16k |
Looking for a dsh-memory alternative? If you're comparing dsh-memory with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM provi
TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM provi
Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control
ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloa
Deterministic safety solutions for probabilistic AI agents
An introduction to the world of AI Agents
Explore other popular mcp server tools:
dsh-memory is 白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。. It is categorized as a MCP Server with 227 GitHub stars.
dsh-memory is primarily written in Python. It covers topics such as agent-safety, agentic-ai, agi.
You can find installation instructions and usage details in the dsh-memory GitHub repository at github.com/FuRongJun-1999/dsh-memory. The project has 227 stars and 17 forks, indicating an active community.
dsh-memory is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to dsh-memory on Agent Skills Hub include agentos, agentos, ctxvault. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: