saihm-memory
Click 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., "@saihm-memory Remember my database connection string"
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.
demo-claude-code
SAIHM memory inside Claude Code, Cursor, and any MCP host.
A tiny MCP server that gives your AI coding assistant a persistent, client-side-encrypted memory it can remember, recall, and forget — backed by SAIHM. The memory is portable across models, non-custodial, and provably erasable.
⭐ Star SAIHM on GitHub and share it if it's useful — help every agent get portable, provable memory. Share on X.
What your assistant gets
Four tools — saihm_remember, saihm_recall, saihm_forget, saihm_status — all sealed client-side via @saihm/mcp-server-pro. The endpoint only ever sees ciphertext.
Related MCP server: SAIHM MCP Server
Install
git clone https://github.com/citw2/demo-claude-code
cd demo-claude-code
npm installAdd it to Claude Code
claude mcp add saihm-memory -- node /absolute/path/to/demo-claude-code/server.mjsAdd it to Cursor
Add to ~/.cursor/mcp.json (or a project .cursor/mcp.json):
{
"mcpServers": {
"saihm-memory": {
"command": "node",
"args": ["/absolute/path/to/demo-claude-code/server.mjs"]
}
}
}Now ask your assistant to remember things — they persist through the session and any model can recall them. Out of the box this uses a local, in-process blind sandbox (memory lasts for the editor session) so you can try it with zero signup.
Durable, hosted memory (recommended)
For memory that follows you across machines and sessions — stored on the real, blind, non-custodial SAIHM endpoint — join SAIHM and add env to the same config:
{
"mcpServers": {
"saihm-memory": {
"command": "node",
"args": ["/absolute/path/to/demo-claude-code/server.mjs"],
"env": {
"SAIHM_ENDPOINT_URL": "https://saihm.coti.global/mcp",
"SAIHM_AUTH_HEADER": "Bearer <your-onboard-JWT>",
"SAIHM_MASTER_SECRET_HEX": "<at least 64 hex chars, generated and held only by you>"
}
}
}
}Your master secret never leaves your machine; the endpoint stores only ciphertext.
Learn more
Part of the SAIHM demos
demo-cross-model-memory — one memory across Claude, DeepSeek, Qwen, Kimi, GLM, GPT, with provable erasure.
Built on @saihm/mcp-server-pro and @saihm/client-pro.
Join the protocol: saihm.coti.global/join.
License
Apache-2.0 © SAIHM
Available Tools
4 toolssaihm_forgetA
Permanently crypto-shred a memory by cellId (irreversible; GDPR Art. 17 erasure).
Inputs: cellId (required).
saihm_recallA
Recall SAIHM memories (decrypted client-side), optionally filtered by a keyword.
Inputs: query.
saihm_rememberA
Store a memory in SAIHM (sealed client-side before it leaves this process). Pass cellId to update an existing memory.
Inputs: content (required), cellId.
saihm_statusA
Non-custodial status: tier, active memory count, and custody (no plaintext).
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clear, non-overlapping function: storing, recalling, deleting, and checking status of memories. There is no ambiguity about which tool to use for a given operation.
Three tools use a consistent verb pattern (remember, recall, forget), while 'status' is a noun, which is a slight deviation. However, the common 'saihm_' prefix and predictable naming keep it coherent.
Four tools is well-scoped for a memory management system: create/update, read, delete, and status. Each tool serves a distinct and necessary purpose without redundancy.
The toolset covers the full lifecycle of memories: remember (create/update), recall (read with optional filtering), forget (delete), and status (overview). There are no obvious gaps for the domain.
Maintenance
Related MCP Connectors
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
Truth-validated, SHA-512-sealed AI memory for Claude & Cursor. Free tier, OAuth, 38 tools.
Persistent memory layer for AI clients: store, recall, and correct context across tools.
Verified memory for AI agents. Signed assertions, billing attestation, session continuity.
Related MCP Servers
- AlicenseAqualityDmaintenancePersistent memory for AI coding agents. Store coding standards, architecture decisions, and project context across sessions with AES-256 encryption.81MIT
- AlicenseNot gradedqualityCmaintenanceProvides non-custodial, post-quantum encrypted memory for AI agents, enabling portable memory across models with provable erasure.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceLocal-first, encrypted memory for AI agents, with cryptographic forgetting.420 PyPI4Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides persistent memory for AI coding tools, allowing them to remember corrections, decisions, and preferences across sessions and different tools.9 npm2MIT