Mnemoverse

Hosted memory for AI agents that learns which facts matter. Feedback reranks recall — a Rescorla-Wagner update on the prediction error, not a similarity score — so what helped rises and what misled sinks, and recall favors recent memories (an exponential recency boost with a ~30-day half-life). The engine also ships consolidation (HDBSCAN clustering, with Von Restorff protection so distinctive memories survive compression). One API key works across Claude, Cursor, VS Code, ChatGPT, and any MCP client.

Memory that persists across sessions, projects, and tools — and improves with use. Hosted, so there's no infrastructure to run, and not locked to a single cloud.

⭐ If Mnemoverse saves you from re-explaining context to your agents,star the repo. It helps other builders find it.

Sign up atconsole.mnemoverse.com— takes 30 seconds, no credit card.

claude mcp add mnemoverse -s user \ -e MNEMOVERSE_API_KEY=mk_live_YOUR_KEY \ -e MNEMOVERSE_API_URL=https://core.mnemoverse.com/api/v1 \ -- npx -y @mnemoverse/mcp-memory-server@latest

{ "mcpServers": { "mnemoverse": { "command": "npx", "args": [ "-y", "@mnemoverse/mcp-memory-server@latest" ], "env": { "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY", "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1" } } } }

VS Code— add to.vscode/mcp.json(note: VS Code usesservers, notmcpServers):

{ "servers": { "mnemoverse": { "type": "stdio", "command": "npx", "args": [ "-y", "@mnemoverse/mcp-memory-server@latest" ], "env": { "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY", "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1" } } } }

Windsurf— add to~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "mnemoverse": { "command": "npx", "args": [ "-y", "@mnemoverse/mcp-memory-server@latest" ], "env": { "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY", "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1" } } } }

More MCP clients— same server, different config file:

Zed— add to~/.config/zed/settings.json(Zed usescontext_servers, and"source": "custom"is required):

{ "context_servers": { "mnemoverse": { "source": "custom", "command": "npx", "args": [ "-y", "@mnemoverse/mcp-memory-server@latest" ], "env": { "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY", "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1" } } } }

JetBrains(AI Assistant) —Settings → Tools → AI Assistant → Model Context Protocol (MCP), then paste:

{ "mcpServers": { "mnemoverse": { "command": "npx", "args": [ "-y", "@mnemoverse/mcp-memory-server@latest" ], "env": { "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY", "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1" } } } }

Cline—MCP Servers → Configure(or editcline_mcp_settings.json). Cline readsenvvalues literally, so paste your real key — not a${VAR}reference:

{ "mcpServers": { "mnemoverse": { "command": "npx", "args": [ "-y", "@mnemoverse/mcp-memory-server@latest" ], "env": { "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY", "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1" } } } }

Continue— add~/.continue/mcpServers/mnemoverse.yaml(Continue uses YAML):

mcpServers: - name: mnemoverse command: npx args: - "-y" - "@mnemoverse/mcp-memory-server@latest" env: MNEMOVERSE_API_KEY: "mk_live_YOUR_KEY" MNEMOVERSE_API_URL: "https://core.mnemoverse.com/api/v1"

Why@latest? Barenpx @mnemoverse/mcp-memory-serveris cached indefinitely by npm and stops re-checking the registry. The@latestsuffix forces a metadata lookup on every Claude Code / Cursor / VS Code session start (~100-300ms), so you always pick up new releases.

⚠️Restart your AI clientafter editing the config. MCP servers are only picked up on client startup.

3. Try it — 30 seconds to verify it works

"Remember that my favourite TypeScript framework is Hono, and please callmemory_writeto save it."

Your agent should callmemory_writeand confirm the memory was stored.

Then open anew chat / new session(this is the whole point — memory survives restarts), and ask:

"What's my favourite TypeScript framework?"

Your agent should callmemory_read, find the entry, and answer "Hono". If it does — you're wired up. Write whatever you want next.

If it doesn't remember: check that the client was fully restarted and the config has your realmk_live_...key, not the placeholder.

- User preferences: "I use dark mode", "I prefer Tailwind over CSS modules"
- Project context: "This project uses PostgreSQL + Prisma", "Deploy to Railway"
- Lessons learned: "Always run tests before push on this repo"
- Decisions made: "We chose REST over GraphQL because of caching simplicity"
- People & roles: "Alice is the designer, Bob owns the API"
- Past mistakes: "Don't deploy on Fridays — learned this the hard way"

The same API key works across all tools. Write a memory in Claude Code — read it in Cursor. Learn something in VS Code — your GPT Custom Action knows it too.

┌── Claude Code (this MCP server) ├── Cursor (this MCP server) Mnemoverse API ──├── VS Code (this MCP server) (one memory) ├── GPT (Custom Actions) ├── Python SDK (pip install mnemoverse) └── REST API (curl)

- Documentation
- Cursor·VS Code·Claude Code·ChatGPT
- Python SDK
- API Reference
- Console (get API key)

- Memory MCP servers compared— thirteen shipping options, with pricing and registry presence
- How to choose a memory MCP server— the five questions that narrow the field
- What AI agent memory is— the category explained
- Is this a vector database?— what makes a memory layer different
- Shared memory for multi-agent systems— how Rooms work and when to use them

- GitHub
- Releases
- MCP Registry entry
- Contributing

One thing goes out that you did not explicitly request: since 0.8.1, when a search or feed comes back empty, the server sends one or two authenticated read-only GET probes (/memory/roomsand/or/memory/stats) so the empty answer can say what it did not cover. The probes carry your API key and nothing else, change no stored state, and are disclosed in theCHANGELOG.

Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.