remembrances
by josegarridodigio
Overview
Provides AI agents with long-term memory capabilities, including key-value, vector (RAG), and graph memory layers, knowledge base management, and multi-language code indexing with semantic embeddings.
Installation
./run-remembrances.sh --gguf-model-path ./nomic-embed-text-v1.5.Q4_K_M.gguf --gguf-threads 8 --gguf-gpu-layers 32Environment Variables
- GOMEM_OPENAI_KEY
- GOMEM_GGUF_MODEL_PATH
- GOMEM_OLLAMA_MODEL
- GOMEM_SURREALDB_URL
- GOMEM_SURREALDB_START_CMD
Security Notes
CRITICAL: The `GOMEM_SURREALDB_START_CMD` environment variable or `--surrealdb-start-cmd` CLI flag executes the provided command using `/bin/sh -c "<cmd>"`. This is a severe command injection vulnerability if the input is not carefully controlled, potentially allowing remote code execution. Additionally, the default SurrealDB credentials (`root:root`) are insecure and should be changed for production deployments.
Similar Servers
memorizer-v1
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.
claude-conversation-memory-mcp
Provides long-term memory for AI coding assistants by indexing conversation history with semantic search, decision tracking, and cross-project search.
Simple-Memory-Extension-MCP-Server
A persistent key-value memory store for AI agents, designed to extend context windows and enable semantic search over stored memories.
post-cortex
Post-Cortex transforms ephemeral AI conversations into persistent, searchable knowledge, enabling AI assistants to maintain memory across sessions with semantic search and automatic knowledge graph construction.