MemoryGate – Open-source persistent memory for AI agents via MCP
MCP-native persistent memory solves cross-platform agent amnesia without context hacks.
Three-layer memory architecture for AI coding agents. Persistent facts, cross-session task tracking, and ephemeral execution — so agents stop forgetting.
Structured memory layers for agents—but vector search already solves this problem.
AI agent builders, OpenCode users, autonomous coding systems
LangChain · Mem0
MCP-native persistent memory solves cross-platform agent amnesia without context hacks.
VSA memory uses 32× less RAM than float vectors while beating RAG on recall.
Clever multi-layer memory architecture (seed/narrative/delta), but "AI memory" is well-explored territory.
Swapping global vector scans for O(k) prefix/deterministic retrieval is a clever pivot that could cut latency and cost for local agent memory. The repo ships a usable Windows binary plus an MIT Python SDK and LangChain-friendly badges — enough to test the claim quickly — but the core engine is proprietary and lacks reproducible benchmarks, so you’ll want evidence before trusting it at scale.
SQLite-backed agent memory with graph viz when Mem0 and Zep already dominate.
MCP-native memory with synthetic data generation for AI agent retrieval workflows.