A zero-dependency local memory engine with CLI, Python, HTTP, and stdio MCP interfaces.
DSH integration
Ecosystem-related
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-08
License
MIT
01What can it help you accomplish?
Store and retrieve local AI memories for an agent workflow
A local memory store available through CLI, Python, HTTP, or MCP
DSH users who want a self-hosted memory system exposed through MCP
02How to install into DeepSeek Harness
Installation steps
- 01
Install with `pip install mnemosyne-os`.
- 02
Start the stdio MCP server with the documented `python -m mnemosyne.webui.mcp_server` command.
Verify the integration
- Run the documented standard-library core import command and confirm it prints `Ready!`.
03DSH integration and capability boundaries
Connects to DeepSeek Harness through the README-documented MCP deployment path
MCP memory server
Memory retain and recall requests over stdio JSON-RPC→Thirteen documented MCP tools for storing, retrieving, auditing, and exchanging memories
The local dashboard creates a default `admin / mnemosyne` account on first run
04Who is it for? When not to use it?
Good for
- DSH users who want a self-hosted memory system exposed through MCP
Not for
- Change the dashboard default password after first login.
05Compatibility, maintenance and safety notes
- Change the dashboard default password after first login.
Author README tracked from the referenced commit
06Frequently asked questions
How can DSH use Mnemosyne?
Start the documented stdio MCP server and connect the DSH-side MCP configuration to that command.
Does its core need a vector database?
The README describes a standard-library core with no vector database or LLM runtime required for memory storage and recall.
What should I secure first?
The local dashboard creates `admin / mnemosyne` on first run; change that password after login.
07Related DSH workflows
memos
by memtensor
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
dsh-anchored-standard
by xiaobright
Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)
mem9
by mem9-ai
Unlimited memory for OpenClaw
mindmemos
by mindscale-noah
Gives dsh agents persistent cross-session memory: auto-recalls relevant user/task context before each turn and writes back lessons after each turn, evolving memory via schema learning and skill distillation
08Data and sources
docs/DEPLOY_DEEPSEEK_HARNESS.md` — Deploy with DeepSeek Harness (via MCP)
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-08. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.