| FMRS | 37 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 8 / 20 | 12 / 20 |
|---|
| Security and permissions | 3 / 20 | 16 / 20 |
|---|
| Maintenance | 4 / 20 | 14 / 20 |
|---|
| Documentation | 13 / 20 | 18 / 20 |
|---|
| Setup experience | 9 / 20 | 15 / 20 |
|---|
| Best for | - Developers comfortable with Go and the Alpaca API who want to experiment with AI-driven options strategies in a paper trading sandbox
- Engineers interested in an example architecture for wiring Claude Code to a custom trading backend via MCP
| - 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 | - Anyone wanting to trade real money in production — the author explicitly warns to use paper trading only
- Users who need active maintenance or updates, since this repo is deprecated and development has moved to OpenProphet
- Users without an Alpaca trading account and API keys, or unfamiliar with compiling and running a Go backend
| - 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 | - Alpaca API keys (permission to place/cancel orders and read positions and account balance)
- Optional Gemini API key for AI-based news cleaning and summarization
- Local filesystem write access for the SQLite database and activity_logs/decisive_actions logs
- Outbound network access to Alpaca, Google News, MarketWatch, and Gemini services
| - 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 | - Misconfiguring a live (non-paper) Alpaca endpoint can result in real financial losses; the author provides no warranty
- The project is marked deprecated by its author and no longer receives updates or fixes — review the code yourself before relying on it
- AI-generated trading decisions may be flawed and should be reviewed before execution
- Alpaca and Gemini API keys are stored in plaintext in the .env file and must be protected from exposure
| - 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 Code | 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 | 32 | 14 |
|---|