← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionHonchoReasoning memory for stateful agents.CompartmentEncrypted, fully offline long-term memory for AI agents
FMRS55 / 100 · C75 / 100 · B
Reliability8 / 2012 / 20
Security and permissions9 / 2016 / 20
Maintenance11 / 2014 / 20
Documentation14 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Stateful agents that need cross-session memory
  • Applications requiring personalization and long-term context
  • Developers using MCP-compatible clients
  • Teams choosing between a managed or self-hosted memory service
  • 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
  • One-off conversational applications that do not retain history
  • Integration reviews requiring a documented list of MCP tool names and parameters
  • Workloads where messages or documents must not be sent to an external memory service
  • 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 an Authorization request header to mcp.honcho.dev
  • Requires a valid OAuth access token or Honcho API key
  • May optionally require a default workspace ID
  • The service may receive and process session messages, events, documents, or tool traces
  • 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
  • Content sent to Honcho may contain sensitive personal or application data
  • Background reasoning is asynchronous, so newly added messages may not immediately appear in chat or representation results
  • The managed service depends on network access, credentials, and Honcho availability
  • The AGPL-3.0 license may affect self-hosting and redistribution plans
  • 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 clientsClaude Code, Cursor, Cline, Windsurf, OpenCode, OpenClaw, HermesClaude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro
Tools014