mnemosyne
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mnemosyneRemember that I'm lactose intolerant and prefer oat milk."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dsh-ai-memory
Mnemosyne OS 8.1.0 memory for DeepSeek Harness — auto-register, auto-remember, auto-recall.
One command, one click in the browser, and your DSH sessions remember across restarts. 52 MCP tools (write, recall, knowledge graph, memory formation layer) with no glue code.
Install (30 seconds)
dsh plugin add github:MnemosyneOS/dsh-ai-memory
dsh-ai-memory-loginRestart dsh web. That's it.
Requires Node 18+ and pnpm on PATH (
dsh plugincalls pnpm under the hood).
Related MCP server: aura-memory
First authorization (Device Flow)
dsh-ai-memory-login prints a short link:
请在浏览器打开下面这个地址完成授权:
https://ai-memory.net/api/device/confirm?code=ABCD2345Open it, sign in, click 授权. The command then:
receives a
mn-key bound to your namespace,writes exactly one line (
Authorization: Bearer mn-…) into your profile'scordis.patch.yml,backs the file up first as
.bak-dsh-ai-memory,never touches any other line — your comments and other MCP servers stay byte-identical.
The key is shown as mn-Abcd****wxyz; the full value is never logged.
What it gives you
The plugin registers one MCP server (mnemosyne, streamable HTTP at https://ai-memory.net/v1/mcp),
which exposes the full Mnemosyne OS tool surface. Commonly used:
Tool | What it does |
| Write memories (content / type / tags / confidence / importance) |
| Five-channel recall with token budget and compression |
| Soft forget: confidence → 0, marked deleted, still auditable |
| Compress a memory to pointer + fact atoms; expand back and verify its hash |
| Progressive disclosure: titles first, full text on demand |
| Walk the knowledge graph; return version chains by time |
| Build injectable context within a token budget |
| Session and project-level summaries |
| Six conflict classes, four resolution operations |
| Record intent, constraints and rejected approaches; archaeology on past changes |
Then in any session: "记住:我叫张三,乳糖不耐" — and in a brand-new session, "我喝咖啡要注意什么" gets the right answer.
Privacy & data
Where data lives. In your Mnemosyne namespace on ai-memory.net, isolated per account.
Isolation is server-side. The namespace is decided by the server from your session (
defaultfor administrators,u_<sha256(email)[:16]>for members). A namespace supplied by a client is ignored. Another user's key cannot reach your memories.Keys. Only SHA-256 digests are stored; the plaintext exists once, at issuance. Revoke or regenerate keys in the ai-memory.net console.
Delete / opt out.
dsh plugin remove dsh-ai-memoryremoves the plugin; rundsh-ai-memory-login --removeto strip the profile entry, and delete the namespace from the console to erase stored memories. The DSH-side config file is yours: the login tool only ever edits one line, keeps a.bak-dsh-ai-memorybackup, and rolls back if its own check fails.No telemetry. The plugin talks to ai-memory.net only (device flow + MCP). Nothing else.
Uninstall
dsh-ai-memory-login --remove # drop the MCP entry from your profile
dsh plugin remove dsh-ai-memory # remove the packageRestart dsh web.
Options
--profile <name> target DSH profile (default: web)
--file <path> point at a cordis.patch.yml directly
--base-url <url> override the service base URL (default https://ai-memory.net)
--no-browser do not try to open the browser automatically
--remove strip the entry this plugin wrote
-h, --help helpExit codes: 0 success / already configured · 1 failure · 2 cancelled or timed out.
Development
node test/login.test.mjs # 26 checks: protocol + idempotent profile writesLicense
MIT © MnemosyneOS
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Gives your AI assistant persistent memory and intelligence about your work patterns.
Memory for AI agent teams across tools, sessions, repositories, and teammates.
Persistent engineering memory designed to follow developers across coding agents.
1
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables persistent memory for AI systems by providing tools for episodic, semantic, and procedural data storage through a vector-and-graph-enhanced database. It allows models to maintain long-term continuity using similarity search, thematic clustering, and identity tracking.241-
- AlicenseNot gradedqualityBmaintenancePersistent cognitive memory for AI agents. Sub-millisecond recall, fully offline, encrypted. 8 tools: recall, recall_structured, store, store_code, store_decision, search, insights, consolidate.2,941 PyPI85MIT
- AlicenseNot gradedqualityAmaintenanceA persistent, project-scoped memory layer for AI coding agents, providing 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions.0MIT
- FlicenseAqualityBmaintenanceShared fleet memory for AI agents — what one agent learns, the whole fleet knows. Nightly self-correction: stale facts rewritten in place, duplicates merged. Recall pushed into every prompt in supported coding agents. Self-hosted.113-