Sovereign encrypted persistent memory for AI agents. 8 MCP tools. GDPR erasure. Apache-2.0.
Connect Saihm to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Sovereign encrypted persistent memory for AI agents. 8 MCP tools. GDPR erasure. Apache-2.0. The saihm mcp server is what makes that connection.
A Model Context Protocol server that exposes eight tools any MCP-capable AI agent (Claude Code, Claude Desktop, custom agents) can call to gain a persistent, encrypted memory layer the user owns:
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
saihm_remember — store an encrypted memory cellsaihm_recall — retrieve and decrypt your memoriessaihm_forget — true cryptographic erasure (GDPR Art. 17)saihm_status — your protocol-runtime stats and storage tier dashboardLocal — first, then deep-archive.** A typical operator routes writes to aPer — call abort window.** Each request runs under an AbortController that aborts after 30s, preventing a hung endpoint from starving the MCP serverResponse — size cap.** Responses whose Content-Length exceeds 16 MB are rejected before deserialisationIETF — draft-saihm-memory-protocol-01 (2026-05-27) was submitted to theSite — https://saihm.coti.globalSecurity — see SECURITY.md for private vulnerabilityContributing — see CONTRIBUTING.md andGovernance — see GOVERNANCE.mdConfiguration is passed through the environment: SAIHM_ENDPOINT_URL, SAIHM_AUTH_HEADER. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Saihm's toolset — saihm_remember, saihm_recall, saihm_forget and 11 more — is a fair guide to whether it matches your workflow. It is maintained by SAIHM-Admin; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| saihm_remember | store an encrypted memory cell |
| saihm_recall | retrieve and decrypt your memories |
| saihm_forget | true cryptographic erasure (GDPR Art. 17) |
| saihm_status | your protocol-runtime stats and storage tier dashboard |
| Local | first, then deep-archive.** A typical operator routes writes to a |
| Per | call abort window.** Each request runs under an AbortController that aborts after 30s, preventing a hung endpoint from starving the MCP server. |
| Response | size cap.** Responses whose Content-Length exceeds 16 MB are rejected before deserialisation. |
| IETF | draft-saihm-memory-protocol-01 (2026-05-27) was submitted to the |
| Site | <https://saihm.coti.global> |
| Security | see [SECURITY.md](./SECURITY.md) for private vulnerability |
| Contributing | see [CONTRIBUTING.md](./CONTRIBUTING.md) and |
| Governance | see [GOVERNANCE.md](./GOVERNANCE.md) |
| Changelog | see [CHANGELOG.md](./CHANGELOG.md) |
| saihm_share | Share |
{
"mcpServers": {
"saihm": {
"command": "npx",
"args": ["@saihm/mcp-server"],
"env": {
"SAIHM_ENDPOINT_URL": "https://operator.example.com/mcp",
"SAIHM_AUTH_HEADER": "Bearer <token>"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| SAIHM_ENDPOINT_URL | Endpoint or connection string the server talks to. | Yes |
| SAIHM_AUTH_HEADER | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.