In-depth architectural comparison of the Projectmem and Central Intelligence MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Projectmem
Knowledge & Memory · Local stdio
Quality: 60/100 (Good) | Auth: No auth required
Central Intelligence
Knowledge & Memory · Local stdio
Quality: 49/100 (Fair) | Auth: API Key required
Verdict Summary: Choose Projectmem if you need specialized Knowledge & Memory tools running via a local process. Choose Central Intelligence if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Projectmem when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Local-first memory and judgment layer for AI coding agents. Captures issues, failed attempts, fixes, and decisions in readable Markdown + JSONL, re-injects them into future sessions, and warns at git commit before you repeat a mistake. 14 tools, works with Claude, Cursor, Antigravity, and Codex.
Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.
Category & Scope
Tools & Capabilities Breakdown
Projectmem Tools (6)
Local-first memory stored in .projectmem directory
Projectmem is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Central Intelligence belongs to Knowledge & Memory using local stdio subprocess. Select Projectmem when you need capabilities focused on knowledge & memory and Central Intelligence when you require tools for knowledge & memory.