memorizer-v1
Verified Safeby petabridge
Overview
A .NET-based service for AI agents to store, retrieve, and search through long-term memories using vector embeddings, PostgreSQL (pgvector), and a Model Context Protocol (MCP) API, featuring versioning, relationships, and asynchronous chunking.
Installation
docker-compose up -dEnvironment Variables
- MEMORIZER_ConnectionStrings__Storage
- MEMORIZER_Embeddings__ApiUrl
- MEMORIZER_Embeddings__Model
- MEMORIZER_LLM__ApiUrl
- MEMORIZER_LLM__Model
- MEMORIZER_Server__CanonicalUrl
- ASPNETCORE_ENVIRONMENT
Security Notes
The default `docker-compose` configurations for development include hardcoded `postgres` passwords and `pgAdmin` credentials, as well as highly permissive CORS (`*` for origins, methods, headers). These are suitable for local development but are critical security vulnerabilities if deployed to production without being locked down. The `docs/security.md` addresses these, providing strong recommendations for production-ready configuration.
Similar Servers
mcp-memory-service
A comprehensive, AI-enhanced memory service for AI agents, enabling semantic search, intelligent consolidation, and multi-backend storage via a token-efficient API and MCP protocol.
memory-graph
A graph-based MCP server that provides intelligent memory capabilities for Claude Code, enabling persistent knowledge tracking, relationship mapping, and contextual development assistance for AI agents.
mcp-duckdb-memory-server
Serves as a local knowledge graph memory backend for LLMs, storing entities, relations, and observations using DuckDB for efficient querying and data management.
vector-memory-mcp
A local-first semantic memory server for AI assistants to store and retrieve context through semantic search.