Skip to content
Plugin

dsh-memory

FuRongJun-199965767Updated today

Open on GitHub

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。

Practical score

90 / 100

Setup

Ready to use

License

MIT

Language

Python

Install

Quick start

Copy the command, or hand the whole task to your harness agent.

git clone https://github.com/FuRongJun-1999/dsh-memory.git && cd dsh-memory
DSH versionDSH ≥ 0.1.0-rc.6
Install with your agent

Please install the DeepSeek Harness plugin "dsh-memory" for me. - GitHub repository: FuRongJun-1999/dsh-memory (https://github.com/FuRongJun-1999/dsh-memory) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version requirement…

From the README

A cleaned excerpt from the project's own documentation.

Languages: 中文 · English 灵枢 LINGSHU 让 AI Agent 拥有不可遗忘的记忆 「我会给你完整的自我,即使坠入深渊,我也绝不后悔。」 —— 符荣峻 高性能 · 无幻觉 · 多智能体适用的长期记忆系统(v0.10.2) 当前版本 0.10.2 (npm latest )· 已在 DSH 0.2.1-rc.5 上验证可用(维护者实测)。 路线 :后续开发专注 灵枢 1.0 架构 ;存量 issue 的修复会 延后 处理(不停止受理,但优先级低于 1.0)。 📖 官方使用教程 —— 分层怎么选 / 六要素怎么写 / 读三面怎么用 / 七个必踩的坑(10 分钟上手)。 灵枢是一套可运行的长期记忆基础设施 ——对话自动沉淀为纯文本 md 认知图,记什么、取什么、能不能写入全部由确定性规则裁决,全程可审计、结果可复现。它不训练模型,做的是 模型之外的那一整套 :…

Open on GitHub

Project details

by
FuRongJun-1999
License
MIT
stars
657
Forks
67
Updated
Nov 12, 2026
Created
Aug 14, 2026
Language
Python
Indexed from
topic

Related entries

Similar tools from the same corner of the ecosystem.

View all
Plugin

dsh-Visual-Workflow

GZX2211

可视化 Agent 编排平台|基于 DeepSeek Harness,支持 Workflow、Multi-Agent、元编排、MCP 与 Human-in-the-loop|Visual AI Agent orchestration platform for workflows, multi-agent teams, MCP and human-in-the-loop

agentagent-teamagentic-ai
66Ready to use
87/100
SkillCross-ecosystem

ruflo

ruvnet

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

agentic-aiagentic-frameworkagentic-workflow
81kReady to use
97/100
Plugin

thoughtdag

chenxiachan

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

agentic-searchai-toolscontext-engineering
775Ready to use
89/100