HN Showcase
Back to browse
MemoryGate – Open-source persistent memory for AI agents via MCP

MemoryGate – Open-source persistent memory for AI agents via MCP

by pstryder·Feb 11, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemBig BrainSlick

MCP-native persistent memory solves cross-platform agent amnesia without context hacks.

Strengths
  • •Solves a real, painful problem: agent knowledge dies at model updates or session boundaries, not theoretical.
  • •Confidence-weighted memories + automatic lifecycle management is genuinely clever — signal survives, noise fades without manual tuning.
  • •Production-grade from day one: OAuth, audit logs, append-only lineage, multi-tenant isolation — not an experiment.
Weaknesses
  • •Adoption hinges entirely on MCP ecosystem maturity; if platforms don't adopt MCP fully, MemoryGate stays niche.
  • •No evidence of large-scale testing: works in theory, but memory at scale across 33 tools + knowledge graphs may have latency or coherence surprises.
Target Audience

AI engineers, AI agent builders, multi-agent system maintainers

Similar To

Anthropic Context Protocol (MCP itself) · LangChain memory modules · OpenAI Assistants knowledge retrieval

Post Description

I built MemoryGate because I kept watching context vanish. I run multiple AI agents across Claude, ChatGPT, and Cursor. Every time a model updated, a platform changed its API, or a context window rolled over — everything the agent had learned was gone. Preferences, decisions, project history, relationship context. Just... wiped. The fundamental problem: AI memory is trapped inside the platform that hosts the conversation. Your agent's knowledge dies with the session, the model version, or the provider's business decisions. MemoryGate is a persistent semantic memory layer that sits outside any single model or platform. It connects via MCP (Model Context Protocol), so any MCP-compatible agent — Claude Desktop, ChatGPT, Cursor, custom agents — can store and retrieve memories through a shared, durable knowledge store. What it actually does:

Semantic memory with vector embeddings — recall by meaning, not keywords Confidence-weighted observations that strengthen or decay based on evidence Automatic lifecycle management — high-signal stays hot, noise fades to cold storage Append-only architecture — memories are never overwritten, only superseded with lineage Knowledge graphs linking observations, patterns, concepts, and documents Multi-tenant with org isolation, roles, and shared memory stores OAuth 2.0, audit logs, rate limiting — production infrastructure, not a toy

What it's not:

Not a RAG pipeline. MemoryGate stores what the agent learns from interaction, not document chunks. Not prompt injection. Memory lives at the infrastructure layer, not stuffed into system prompts. Not tied to any model or provider. Switch from Claude to ChatGPT to a local model — memory persists.

Stack: Python/FastAPI, PostgreSQL + pgvector, Redis, deployed on Railway. MCP-native integration — your agent gets 33 memory tools on connection. The real pitch: Platforms die. Models get deprecated. Context windows roll over. Your AI's memory shouldn't be hostage to your AI's provider. Open source (Apache 2.0), self-hostable, with a hosted SaaS option if you don't want to run infrastructure.

GitHub: https://github.com/PStryder/MemoryGate SaaS: https://memorygate.ai Docs: https://memorygate.ai/docs/

I'm a solo founder — built this after leaving a decade in enterprise solutions engineering. Happy to answer questions about the architecture, the MCP integration, or why I think persistent memory is the missing infrastructure layer for AI agents.

Similar Projects