Agentkits Memory vs Iai Personal Memory E… | AllMCPs
Side-by-Side Model Context Protocol Comparison
Agentkits Memory vs Iai Personal Memory Engine
In-depth architectural comparison of the Agentkits Memory and Iai Personal Memory Engine 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
Iai Personal Memory Engine
Knowledge & Memory · Local stdio
Quality: 67/100 (Great) | Auth: No auth required
Verdict Summary: Choose Agentkits Memory if you need specialized Knowledge & Memory tools running via a local process. Choose Iai Personal Memory Engine 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.
Local memory daemon for any MCP-over-stdio client with three-tier storage (episodic/semantic/procedural). Own SQLite + hnswlib store (Hippo) with bge-small-en-v1.5, MIT-licensed community-detection reranking (MOSAIC), and sleep-cycle consolidation. AES-256-GCM encrypted at rest, no telemetry. Verbatim recall >=99% and post-contradiction Rescue@10 1.000 at honest scale. Ambient capture via shell hooks. Windows support in beta.
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
Iai Personal Memory Engine Tools (9)
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, Iai Personal Memory Engine belongs to Knowledge & Memory using local stdio subprocess. Select Agentkits Memory when you need capabilities focused on knowledge & memory and Iai Personal Memory Engine when you require tools for knowledge & memory.
Cue-based recall — returns hits **and anti-hits**: memories that *contradict* the cue surface next to the ones that match, so a stale fact can't masquerade as current.
memory_temporal_recall
Time-anchored recall — *"what did I say about pricing in May?"*
memory_recall_structural
Retrieve by the *shape* of a memory (the HD substrate), not just its embedding.
memory_search
Plain text search over the store.
memory_capture
Write a memory explicitly (ambient capture normally does this for you).
memory_contradict
Record that a fact changed. The old version is archived, not erased — both stay retrievable. That's the Rescue@10 and historical-verbatim story in the [benchmarks](#benchmarks).
memory_reinforce
Strengthen a memory's recall pathways.
memory_consolidate
Run a consolidation pass now instead of waiting for idle.
profile_get_set
The eleven sealed procedural knobs the engine learns about you.