| FMRS | 57 / 100 · C | 75 / 100 · B |
|---|
| Reliability | 5 / 20 | 12 / 20 |
|---|
| Security and permissions | 10 / 20 | 16 / 20 |
|---|
| Maintenance | 14 / 20 | 14 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Individual users needing shared persistent memory across multiple AI tools.
- Developers who want to self-host a memory layer on Cloudflare's free tier.
- Users prioritizing data privacy and control, as data stays in their own cloud account.
- Users wanting a quick setup with complete ecosystem support (desktop app, CLI, extensions, etc.).
| - 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 | - Teams needing collaborative memory (currently single-user design).
- Users wanting zero technical setup without touching Cloudflare (except desktop app).
- Users requiring offline or local-only memory (depends on cloud services).
- Strict compliance environments that require non-cloud infrastructure.
| - 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 | - Requires a Cloudflare account to deploy the Worker and infrastructure.
- Requires an AUTH_TOKEN (or password) to authorize all clients.
- Supports OAuth 2.0 dynamic client registration; clients do not need to embed the token in configs.
- For calendar, email, and Notion integrations, requires iCal links, app passwords, or Notion connection secrets.
| - 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 | - Self-hosting means you are responsible for maintenance and updates.
- Data is stored on Cloudflare, subject to Cloudflare's privacy policy (though within your own account).
- Free tier may have usage limits (e.g., vector index size).
- If you forget your password, you must log into Cloudflare to reset; you might temporarily lose access to memories.
- Deploying with incorrect parameters (e.g., Vectorize dimensions) can degrade search functionality.
| - 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, ChatGPT, Cursor, Codex | 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 | 8 | 14 |
|---|