Persistent graph memory for AI agents — one-time payment, self-hosted AI agents are stateless by default. Every session starts from zero. VEKTOR fixes that. It's a self-hosted graph memory layer built on Neo4j that gives your AI agents persistent, relational memory across every session. Entities, relationships, and context are stored as a true graph — not flat vectors — so your agent can actually reason about history, not just retrieve chunks of it.
No reviews yetBe the first to leave a review for Vektor memory
Maker
📌
VEKTOR gives your AI agents persistent, relational memory across every session.
Built on Neo4j — stores entities and relationships as a true knowledge graph,
not flat vectors.
https://vektormemory.com
Why VEKTOR?
- **Graph, not vector** — reason about relationships, not just retrieve similar chunks
- **Persistent** — memory survives across every session automatically
- **Self-hosted** — your data stays on your server, always
- **Any LLM** — Claude, GPT, Ollama via MCP or API
- **One-time payment** — no monthly fees for memory infrastructure