mcp-server

dsh-memory

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。
360 stars+54★ this week30 forksPythonUpdated 10/9/2026100% free · open source
What it does

Provides a white‑box AGI framework that combines self‑cognition loops, continual learning, and a world‑model graph for fully auditable AI pipelines.

When to use it
  • •You need an open‑source, self‑improving AI core that you can inspect and modify.
  • •Your product requires a traceable knowledge‑flywheel that continuously incorporates new data.
  • •You want to experiment with meta‑cognitive loops (self‑awareness) without relying on proprietary LLM APIs.
Ready-to-paste prompt
curl -X POST http://localhost:8000/api/v1/think \ 
  -H 'Content-Type: application/json' \ 
  -d '{"question": "What are the emerging trends in sustainable fintech for 2025?", "context": "latest market reports, internal research"}'
Heads up: The core engine expects a compatible PyTorch 2.x build; using an older PyTorch version will cause import errors when loading the world‑model tensors.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/5775defd-afc4-4502-a3dc-f19178f02fec && curl -fsSL https://workflowstacks.com/api/skills/5775defd-afc4-4502-a3dc-f19178f02fec/claude-skill -o ~/.claude/skills/5775defd-afc4-4502-a3dc-f19178f02fec/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How dsh-memory works
Codeflow
Free to inspect

Dsh-memory is a very large Python project (~387k lines across 737 code files, plus 115 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~387k lines · 737 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 695 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Node.js
Python 93%Rust 4%TypeScript 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    src/cli.ts
    Where the program starts running
  3. 3
    skills/README.md
    Inside skills/ — an example of what the AI is told to do
What's in each folder
skills/Prompts, skills & agent definitions704 files
src/Core code — the actual logic16 files
docs/Documentation231 files
md_cg/Folder935 files
hive/Folder149 files
scripts/Helper scripts109 files
compiler/Folder39 files
swarm/Folder36 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
FuRongJun-1999
Language
Python
Category
mcp-server
Published
8/14/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/5775defd-afc4-4502-a3dc-f19178f02fec.svg)](https://workflowstacks.com/skills/5775defd-afc4-4502-a3dc-f19178f02fec?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.