Compartment turns agent memory into a single fully local, encrypted vault and deliberately leaves the question of what to remember to the host model, handling capture, encryption and recall itself. Its pitch is clear: no account, no API key, no network at runtime, encrypted embedding vectors, expiring memories, a relation graph and tags, plus a cross-platform GUI and a read-only dashboard. The README also provides a comparison table against other memory servers (described as each project's own documentation dated 2 September 2026) and documents its ranking formula, weights and measured latencies. The realistic constraints are worth noting: moving between machines means copying the vault file by hand, a lost passphrase or 2FA keyfile cannot be recovered, memory_unlock is deliberately off by default, and the Docker image is headless stdio only. It suits privacy-conscious individuals and small teams, and is not aimed at users who want cloud sync or server-side fact extraction.
Strongest · Documentation 18/20 Weakest · Reliability 12/20
Static review · not runListed 2026-09-10
Read the FMRS scoring method →Runtime：Python 3.11+
COMPARTMENT_PASSPHRASE
Vault passphrase for scripts and CI; a secret normally entered interactively.
COMPARTMENT_VAULT
Path to the vault file; defaults to ~/.compartment/memory.vault.
COMPARTMENT_SESSION_DIR
Directory where the unlock credential lives.
COMPARTMENT_UI_SCALE
UI scale for the menu bar / tray panel.
COMPARTMENT_ASSERT_OFFLINE
Aborts on any network socket attempt to enforce offline operation.
COMPARTMENT_EMBED_DAEMON
Set to 0 to load the embedding model in-process instead of the shared daemon.
COMPARTMENT_EMBED_SOCKET
Overrides the shared embedding process's socket path.
COMPARTMENT_EMBED_IDLE
Seconds the shared embedding process survives after its last client (default 300).
1) Install with pip: pip install compartment && compartment init (needs Python 3.11 or newer; pipx install compartment or uv tool install compartment also work). 2) compartment init asks you to choose a passphrase, creates the vault, loads the reference facts and connects Claude Code, Hermes Agent or OpenClaw if they are installed. 3) Wire a specific client: compartment integrate claude, compartment integrate hermes, compartment integrate openclaw, or compartment integrate --all for every installed client it knows. 4) For any other MCP client, use the stdio block: {"mcpServers":{"compartment":{"command":"compartment","args":["serve"]}}} (VS Code uses the key servers with "type": "stdio"; Zed uses context_servers; Codex uses TOML under [mcp_servers.compartment]). 5) On a Mac you can instead download Compartment.pkg from the latest release and open it, which needs no command line. 6) Restart your agent and it has a memory.
{"mcpServers":{"compartment":{"command":"compartment","args":["serve"]}}}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"compartment": {
"command": "compartment",
"args": [
"serve"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add compartment -- compartment serve
Run it in a terminal; replace any <…> placeholders with your own values first.
After `pip install compartment && compartment init` and registering the MCP config block, restart your client and confirm memory_search and memory_store appear in the tool list; store a fact and recall it in a new session to prove the connection.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
Compartment is an MCP server that gives AI agents durable memory. It keeps one encrypted vault on the user's own computer, read and written by Claude Code, Claude Desktop, Hermes Agent, OpenClaw, Cursor, Codex and any other MCP client. There is no API key, no account, no network at runtime and no telemetry. Each memory is a single claim recorded with a required source and the date it was learned, and memories can expire: set expires to a date or a duration such as 14d, 2w, 3m or 1y and the memory is removed after that date. Recall is a hybrid vector and keyword search over an in-memory index; the documented median for a full hybrid search is about 11.6 ms. The embedding model is bundled (384-dimension int8 ONNX) and everything on disk, embedding vectors included, is encrypted under the user's passphrase. A new vault ships with about 6,700 reference facts about hardware, operating systems, ports, encodings and shell tools, removable from search with one switch. Security primitives include XChaCha20-Poly1305 encryption at rest, Argon2id key slots, a key per record, a hash-chained audit log, and a runtime guard that aborts on any network socket attempt (--assert-offline). The project ships a macOS menu bar app, a Windows notification-area app, a Linux window, a read-only browser dashboard bound to 127.0.0.1, memory packs, and a serve command that speaks MCP over stdio. Installation routes include PyPI (pip, pipx, uv), a Claude Code plugin, Docker, and a Compartment.pkg for macOS. Licensed Apache-2.0.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Exa's official MCP server for web search and crawling built for AI applications
Source revision be47c40ce1e7 Data synced 2026-10-19 Read the FMRS scoring method