| FMRS | 41 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 4 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 16 / 20 |
|---|
| Maintenance | 17 / 20 | 14 / 20 |
|---|
| Documentation | 7 / 20 | 18 / 20 |
|---|
| Setup experience | 5 / 20 | 15 / 20 |
|---|
| Best for | - Teams already using PostHog for product analytics, feature flags, or experiments who want to control it from an AI agent
- Developers who want product signals (errors, rage clicks, etc.) surfaced directly inside Claude Code, Cursor, or similar agent environments
| - 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 who only need a narrow, single-purpose MCP tool (e.g., pure database or file-system access) — PostHog's surface area is broad
- Users requiring a strictly FOSS codebase — the `ee` directory in this repo is under a separate, non-MIT license
- Self-hosted deployments needing vendor support — the README explicitly states no customer support or guarantees are provided for open-source deployments
| - 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 | - Access to data within a PostHog project/account, including events, session recordings, feature flags, experiments, error tracking, surveys, and data warehouse records
- Write access to modify project configuration if using the agent to create or change feature flags/experiments
| - 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 | - PostHog aggregates substantial user behavioral and product data; agent access to it carries exposure risk for sensitive information (user identifiers, session content)
- Repository licensing is mixed (MIT for the main repo, separate proprietary license for the `ee` directory) — confirm which features are covered before relying on them in production
- Self-hosted open-source deployments are explicitly unsupported by the vendor and are recommended only up to roughly 100k events/month before needing to migrate to Cloud
| - 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 |
|---|