| FMRS | 44 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 4 / 20 | 12 / 20 |
|---|
| Security and permissions | 6 / 20 | 16 / 20 |
|---|
| Maintenance | 15 / 20 | 14 / 20 |
|---|
| Documentation | 11 / 20 | 18 / 20 |
|---|
| Setup experience | 8 / 20 | 15 / 20 |
|---|
| Best for | - Users who already run multiple CLI coding agents (Claude Code, Codex, Gemini CLI, etc.) and want one unified interface
- Individuals or teams wanting local-only storage (SQLite) and control over which LLM API key/provider they use
- Users who need scheduled automation or multi-channel remote access to an AI agent
| - 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 | - Use cases needing a lightweight, single-purpose MCP tool server
- Users wanting a fully managed cloud service with no local install
- Scenarios requiring an officially Anthropic- or protocol-maintained MCP server
| - 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 | - Local file system read/write access for agent file operations
- Ability to execute locally installed CLI agents
- Network access to call configured LLM provider APIs
- Optional bot tokens and network access for chat-platform integrations (Telegram, Lark, DingTalk, WeChat)
- Local SQLite database storage
| - 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 | - Agents get broad local file read/write and command-execution access, which requires trust before enabling
- "YOLO Mode" and "Full-Auto Mode" auto-approve agent actions without confirmation, raising the risk of unintended file changes if misconfigured
- Chat-platform integrations require storing bot tokens/credentials, which carries credential-exposure risk if mishandled
- The project is maintained by a single company (iOfficeAI); evaluate its security practices and update cadence before granting broad automation permissions
| - 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 |
|---|