Hey Product Hunt 👋 I'm Emmanuel, the solo maker behind Remembr. I built this because I kept hitting the same wall building AI agents — they forget everything between sessions. Vector databases help with retrieval but they don't solve the actual problem: agents need a proper memory architecture, not just a search index. Remembr gives agents: → Short-term memory (Redis session cache) → Long-term episodic memory (PostgreSQL + pgvector) → Multi-tenant isolation (Org → Team → User → Agent) → Hybrid semantic search across all past sessions → GDPR-compliant deletion 8 framework adapters all tested end-to-end: LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, Pydantic AI, OpenAI Agents, Haystack. MIT licensed. Self-host with Docker in 5 minutes. Happy to answer any questions about the architecture or how to integrate it into your agent stack

Remembr

Persistent memory infrastructure for AI agents

Persistent memory infrastructure for AI agents