Compartment
local MCP serverCompartment is a local MCP server: Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud. Install it from pypi as compartment.
Installation
Terminal
claude mcp add compartment -- uvx compartment
Run in your project folder. Add --scope user to use it everywhere.
Claude Desktop, Cursor & other clients
Add to claude_desktop_config.json or .cursor/mcp.json.
{
"mcpServers": {
"compartment": {
"command": "uvx",
"args": [
"compartment"
]
}
}
}What you need
- Runtime: Python with uv (runs with uvx).
- MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over stdio.
Summary
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
Compartment vs similar servers
| Server | Stars | Type | API key | Runtime |
|---|---|---|---|---|
| Compartment | 581 | Local | No | pypi |
| Midas | 14 | Local | Yes | pypi |
| telemem | 492 | Local | Yes | pypi |
| doc-scraper | 101 | Local | No | mcpb |
| Pensyve | 87 | Hosted | No | None |
Questions
No. The registry entry lists no keys or environment variables.
Python with uv (runs with uvx), plus an MCP client such as Claude Code, Codex, Claude Desktop or Cursor.
Compartment is a local MCP server distributed as the pypi package compartment.
Run: claude mcp add compartment -- uvx compartment
Run: codex mcp add compartment -- uvx compartment
Similar MCP servers
NameStars
- Midasio.github.vornicx/midas14
- telememio.github.TeleAI-UAGI/telemem492
- doc-scraperio.github.Sriram-PR/doc-scraper101
- Pensyveio.github.major7apps/pensyve87
- enquire-mcpio.github.oomkapwn/enquire-mcp33
- genesys-memoryio.github.Astrix-Labs/genesys-memory29
- Synapse Layer — Trust Infrastructure for AI Agentsio.github.SynapseLayer/synapse-layer13
- Engramapp.getengram/engram12