Fully offline, encrypted-at-rest vector memory for AI agents. AEAD-encrypted vectors, no cloud.
If you already use Compartment, the compartment mcp server is the piece that lets your assistant work with it directly. Fully offline, encrypted-at-rest vector memory for AI agents. AEAD-encrypted vectors, no cloud.
Your AI agent forgets you the moment the session ends. Compartment ends that. With Compartment, your AI agent gets better with experience: it keeps every decision, preference and detail you give it, permanently, encrypted, on your own computer. Hermes, Claude, OpenClaw and other AI Agents can install in one command. One fully-transferable memory store is shared simultaneously by all agents on the computer. 100% offline: no network, no API key, no cloud account, no telemetry. The embedding model ships inside the package, and a full search returns in about 12 ms, beating the round-trip a hosted memory charges you
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
forget — -shred destroys the record's key. The content is mathematicallyTamper-evident — hash-chained audit log, sealed journal, verified kill-9paraphrases — 16/16Measured — Against the previous scorer, end to end through Vault.search, on a real 6,705-memory vault with 44 queries in four families: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.
Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Compartment's toolset — forget, Tamper-evident, paraphrases and 1 more — is a fair guide to whether it matches your workflow. It is maintained by MaxFreedomPollard; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| forget | -shred destroys the record's key. The content is mathematically |
| Tamper-evident | hash-chained audit log, sealed journal, verified kill-9 |
| paraphrases | 16/16 |
| Measured | Against the previous scorer, end to end through Vault.search, on a real 6,705-memory vault with 44 queries in four families: |
{
"mcpServers": {
"compartment": {
"command": "uvx",
"args": ["compartment"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
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.