In-depth architectural comparison of the Agentkits Memory and Mcp Agent Memory 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
Agentkits Memory
Knowledge & Memory · Local stdio
Quality: 56/100 (Good) | Auth: No auth required
Mcp Agent Memory
Knowledge & Memory · Local stdio
Quality: 56/100 (Good) | Auth: No auth required
Verdict Summary: Choose Agentkits Memory if you need specialized Knowledge & Memory tools running via a local process. Choose Mcp Agent Memory 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 Agentkits Memory 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).
Primary tools included: 100% local SQLite database storage with no cloud or API keys, Hybrid search: full-text (FTS5) plus vector embeddings for semantic similarity, Automatic session tracking and context injection via hooks.
Persistent memory for AI coding assistants with hybrid search (FTS5 + vector embeddings), session tracking, automatic context hooks, and web viewer. SQLite-based with no daemon process — works with Claude Code, Cursor, Windsurf, and any MCP client.
Persistent agent memory via filesystem-native consolidation daemon. Agents read/write/search memory through MCP; a background daemon handles consolidation and extraction. Works with Kiro, Claude Desktop, Cursor, and any MCP client. npx mcp-agent-memory --setup
Category & Scope
Tools & Capabilities Breakdown
Agentkits Memory Tools (6)
100% local SQLite database storage with no cloud or API keys
Hybrid search: full-text (FTS5) plus vector embeddings for semantic similarity
Automatic session tracking and context injection via hooks
Background workers for AI enrichment and data compression
Web viewer UI for browsing, searching, and editing memories
Cross-platform compatibility with multiple AI coding MCP clients
Mcp Agent Memory Tools (4)
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Agentkits Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Mcp Agent Memory belongs to Knowledge & Memory using local stdio subprocess. Select Agentkits Memory when you need capabilities focused on knowledge & memory and Mcp Agent Memory when you require tools for knowledge & memory.
Read the agent memory index (MEMORY.md) and optionally specific topic files. Call with no arguments to load only the lightweight index (cheap). Pass `topics` only when you need the full content of a specific topic file.
memory_append_session
Append a session summary to the sessions directory. The daemon will later extract durable memories from it. Call this at the end of meaningful exchanges. Keep summaries focused on durable findings and decisions (target 300-800 tokens), not play-by-play — longer summaries cost more during consolidation.
memory_search
Search memory files for a substring. Use this to recall specific facts without loading everything.
memory_daemon_status
Check whether the memory consolidation daemon is running. Reports if the daemon is not installed or not available on this platform.