Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by biojazzard • NLP & LLM
A local MCP-compatible long-term memory server that stores, searches, retrieves and deletes persistent agent memories using embeddings and local LLMs.
Persist chat or user information across sessions so subsequent interactions can use prior context.
Semantically search past memories to find relevant facts or events using embeddings.
A self-hosted memory backend integrating with local LLMs (Ollama) and standard MCP clients.
This project provides a Dockerized MCP server to manage long-term memory for AI agents, based on mem0.ai. It exposes four memory tools (memory_save, memory_get_all, memory_search, memory_delete) and supports OpenAI, OpenRouter, and local Ollama models and embeddings. Designed to run locally with Ollama and PostgreSQL, it enables semantic search over stored memories and integration with any MCP client.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.