DEDUPED Hot AI repos, turned into use cases Get the Monday 5
179 stars · JavaScript

How to use Mneme: what you can do with it

What is Mneme? dsh-mneme is a cross-session memory plugin for DeepSeek Harness that stores memories locally in SQLite with Markdown mirrors and can also serve them to MCP clients and a standalone daemon.

How do I use it? Install the plugin and open the web interface: dsh plugin --profile web add @modusensus/dsh-mneme then dsh web; then in DSH, open 设置 → 外部访问 API and generate a token; install the MCP package globally: npm i -g mneme-memory. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Give Claude Code or Cursor a shared memory via MCP

    Mount the six memory tools from the Mneme MCP server so coding agents read and write the same memory store.

    View prompt
    In the dsh-mneme repo, use the mneme-memory MCP server to call memory_save with the text '<fact about the target project>', then call memory_search for '<keyword>'. Expected output: the new memory id and its text returned by search. Verify that memory_get on that id returns the same text.

  • Read and write memory from scripts with DSH closed

    Run the standalone daemon so third-party scripts and your own panel reach the same memory library.

    View prompt
    In the dsh-mneme repo, start the daemon with dsh-mneme-serve and send one authenticated request to 127.0.0.1:8790 using the token in <token-file>. Expected output: a successful response listing memories. Verify that the daemon refuses to start if port 8790 is already in use.

  • Run memory search fully offline with local embeddings

    Switch the embedding provider to local so semantic recall needs no API key.

    View prompt
    In the dsh-mneme repo, set embedProvider to local in the memory library settings, save one test memory, then run a semantic search for a paraphrase of it. Expected output: the test memory returned in the results. Verify that no API key field is required for the search to succeed.

  • Keep memories separate across agents and workspaces

    Turn on scope isolation so memories from one project do not leak into another project's sessions.

    View prompt
    In the dsh-mneme repo, enable scopeEnabled, save a memory tagged to workspace A and another to workspace B, then search from workspace B. Expected output: workspace B memory ranked first and any workspace A memory down-weighted or hidden if strictScope is on. Verify the search result list for the scope tags.

Quick start with Mneme

  1. Check you have what it needs: DeepSeek Harness (DSH) installed, with the dsh command available; Node.js and npm for the MCP server and the standalone daemon; Access to the DSH settings panel to generate an external access token.
  2. Open slow-stack/mneme on GitHub and read the README and license.
  3. Install the plugin and open the web interface: dsh plugin --profile web add @modusensus/dsh-mneme then dsh web
  4. In DSH, open 设置 → 外部访问 API and generate a token
  5. Install the MCP package globally: npm i -g mneme-memory (inferred, check the README)
  6. In your project root, create .mcp.json with {"mcpServers": {"mneme-memory": {"command": "mneme-mcp", "env": {"MNEME_TOKEN": "<your-token>"}}}}

These steps come from our top use case, Give Claude Code or Cursor a shared memory via MCP, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for slow-stack/mneme

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Mneme alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and power users of DeepSeek Harness who want AI assistants to keep project context across sessions and tools.
  • Why it is hot179 stars, launched 74 days ago
  • LanguageJavaScript
  • Sourcegithub.com/slow-stack/mneme · Back to Hot repos

Requirements

  • DeepSeek Harness (DSH) installed, with the dsh command available
  • Node.js and npm for the MCP server and the standalone daemon
  • Access to the DSH settings panel to generate an external access token

Add this badge to your README

Maintain Mneme? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/slow-stack/mneme.svg)](https://dedupedai.com/use-cases/slow-stack-mneme/?utm_source=github&utm_medium=badge&utm_campaign=slow-stack-mneme)

HTML 

<a href="https://dedupedai.com/use-cases/slow-stack-mneme/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=slow-stack-mneme"><img src="https://dedupedai.com/badge/slow-stack/mneme.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Mneme

What is Mneme?

dsh-mneme is a cross-session memory plugin for DeepSeek Harness that stores memories locally in SQLite with Markdown mirrors and can also serve them to MCP clients and a standalone daemon. It is an open-source project on GitHub: https://github.com/slow-stack/mneme.

How do I use Mneme?

Install the plugin and open the web interface: dsh plugin --profile web add @modusensus/dsh-mneme then dsh web; then in DSH, open 设置 → 外部访问 API and generate a token; install the MCP package globally: npm i -g mneme-memory. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Mneme for?

Developers and power users of DeepSeek Harness who want AI assistants to keep project context across sessions and tools.

What can I do with Mneme?

4 use cases so far, for example: Give Claude Code or Cursor a shared memory via MCP; Read and write memory from scripts with DSH closed; Run memory search fully offline with local embeddings. Each has steps and a copy-paste agent prompt.

What do I need to run Mneme?

DeepSeek Harness (DSH) installed, with the dsh command available; Node.js and npm for the MCP server and the standalone daemon; Access to the DSH settings panel to generate an external access token.

What are alternatives to Mneme?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Mneme safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.