MCP Catalogs
Home

codex-agent-mem vs filesystem

Side-by-side comparison to help you pick between these two MCP servers.

codex-agent-mem
by MarceloCaporale
filesystem
by modelcontextprotocol
Stars★ 21★ 85,748
30d uses
Score4377
Official
Categories
AI / LLM ToolsDeveloper ToolsProductivity
File SystemDeveloper ToolsProductivity
LanguagePythonTypeScript
Last committhis monththis month

codex-agent-mem · Summary

Local-first MCP memory layer that compresses context packs with SQLite + FTS5 for multiple AI coding workflows.

filesystem · Summary

A feature-rich MCP server for filesystem operations with dynamic directory access control.

codex-agent-mem · Use cases

  • Improving context continuity in long-running AI coding workflows by maintaining persistent memory locally
  • Reducing token usage in AI agents by compressing repeated operational context into smaller packs
  • Creating auditable memory systems for sensitive development projects without external data transmission

filesystem · Use cases

  • Enable AI models to read and write project files during development
  • Allow Claude or other MCP clients to browse and analyze codebases
  • Provide secure sandboxed access to specific directories for content generation

codex-agent-mem · Install

Install codex-agent-mem via pip:

pip install codex-agent-mem

For Claude Desktop, add to your config.json:

{
  "mcpServers": {
    "codex-agent-mem": {
      "command": "codex-agent-mem",
      "args": ["--read-only", "--profile", "minimal"]
    }
  }
}

The server also supports stdio mode for other MCP-compatible clients with various runtime profiles (minimal, standard, full) and configuration options.

filesystem · Install

Installation

Using NPX

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Using Docker

{
  "mcpServers": {
    "filesystem": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
        "mcp/filesystem",
        "/projects"
      ]
    }
  }
}

VS Code Extension

Click the installation buttons in the README to install directly in VS Code.

Comparison generated from public README + GitHub signals. Last updated automatically.