| FMRS | 25 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 2 / 20 | 12 / 20 |
|---|
| Security and permissions | 7 / 20 | 16 / 20 |
|---|
| Maintenance | 10 / 20 | 14 / 20 |
|---|
| Documentation | 4 / 20 | 18 / 20 |
|---|
| Setup experience | 2 / 20 | 15 / 20 |
|---|
| Best for | - Privacy-conscious users who want data to remain on-device
- Users needing local AI capabilities on mobile or Mac
- Users working with GGUF models or local-network model servers
| - Individuals or teams who prioritise privacy and offline operation and do not want data leaving the machine
- Users who share memory across multiple MCP clients such as Claude Code, Claude Desktop, Hermes Agent, OpenClaw, Cursor, Codex and Gemini CLI
- Scenarios that need encrypted storage, a hash-chained audit log and verifiable vault migration
- Users who want low-latency recall, a bundled embedding model and no extra LLM calls inside the memory layer
|
|---|
| Not for | - Users seeking a server with explicitly documented MCP tools and transport configuration
- Users requiring cloud hosting, remote APIs, or verified MCP client compatibility
- Devices without sufficient hardware resources for the selected models
| - Users who need cloud multi-device sync or a hosted team memory service; moving between machines means locking the vault and copying the file
- Users who expect the server itself to run an LLM that extracts facts and decides what to remember; Compartment explicitly keeps no LLM inside and leaves that to the host model
- Users who cannot keep a passphrase safe or who need a recovery path if it is lost, since Compartment never generates a password, seed or recovery phrase
- Deployments that require network transports such as SSE or streamable-http; this server is stdio only and opens no ports
|
|---|
| Required permissions | - Use device CPU, GPU, or NPU for local model inference
- Access the microphone for on-device Whisper transcription
- Access the camera for vision analysis
- Access local files or documents for attachments and knowledge-base processing
- Access the local network to connect to OpenAI-compatible remote LLM servers
| - Read and write the vault file under the user's home directory, by default ~/.compartment/memory.vault, and its sibling settings file
- Access the session directory holding the unlock credential (configurable with COMPARTMENT_SESSION_DIR), which also carries the shared embedding process's Unix socket
- Optionally use the macOS keychain (compartment unlock --keychain is an explicit opt-in, and it survives reboots)
- Write or merge an mcpServers entry into each MCP client's own configuration file, taking a byte-exact backup first
- Install a PostToolUse hook for Claude Code that captures memory files the agent writes
- Serve a read-only dashboard on 127.0.0.1 behind a one-time random URL token
|
|---|
| Risks and side effects | - Model inference and image generation can consume substantial device resources and memory
- Hexagon NPU support is marked experimental; some quantizations or model architectures may fall back to CPU or produce garbled output
- When connected to a remote LLM server on the local network, data is sent to that service; the README does not specify its privacy policy
- Tool calling may perform searches or query device information and the local knowledge base; no separate MCP permission boundary is documented
| - A leaked passphrase means the encrypted content can be decrypted; Compartment generates no recovery phrase and cannot recover a lost passphrase
- Enabling the memory_unlock tool places the passphrase in the model's context, which is why it is off by default
- If a 2FA keyfile is lost, for example a USB stick, the vault cannot be opened even with the passphrase
- `export --plaintext` writes the vault as unencrypted JSONL, so that file must be handled carefully
- Memory content can come from untrusted sources; recall wraps memories with a notice that they are stored data and content can be marked quarantined, but the host agent must still treat memory as data to limit prompt-injection risk
- The capture hook and client integration write into the user's own settings files, although the implementation backs up and merges rather than replacing
|
|---|
| Supported clients | | Claude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro |
|---|
| Tools | 0 | 14 |
|---|