remembrances
by josegarridodigio
Overview
Provides long-term memory, knowledge base, and code indexing capabilities to AI agents using multiple memory layers and embedding models.
Installation
go run ./cmd/remembrances-mcp/main.go --knowledge-base ./kbEnvironment Variables
- GOMEM_SSE
- GOMEM_SSE_ADDR
- GOMEM_HTTP
- GOMEM_HTTP_ADDR
- GOMEM_REST_API_SERVE
- GOMEM_KNOWLEDGE_BASE
- GOMEM_DB_PATH
- GOMEM_SURREALDB_URL
- GOMEM_SURREALDB_USER
- GOMEM_SURREALDB_PASS
- GOMEM_SURREALDB_NAMESPACE
- GOMEM_SURREALDB_DATABASE
- GOMEM_GGUF_MODEL_PATH
- GOMEM_GGUF_THREADS
- GOMEM_GGUF_GPU_LAYERS
- GOMEM_OLLAMA_URL
- GOMEM_OLLAMA_MODEL
- GOMEM_OPENAI_KEY
- GOMEM_OPENAI_URL
- GOMEM_OPENAI_MODEL
- GOMEM_CODE_GGUF_MODEL_PATH
- GOMEM_CODE_OLLAMA_MODEL
- GOMEM_CODE_OPENAI_MODEL
- GOMEM_SURREALDB_START_CMD
Security Notes
The `surrealdb-start-cmd` configuration option allows execution of arbitrary shell commands (`/bin/sh -c "<cmd>"`) if the server fails to connect to SurrealDB. This presents a critical security risk if the configuration can be manipulated by an untrusted entity, as it effectively provides an 'eval'-like capability. Additionally, default SurrealDB credentials of 'root:root' are provided in the sample configuration, which are insecure if not changed. Network-exposed HTTP and SSE APIs lack explicit mention of authentication/authorization mechanisms.
Similar Servers
post-cortex
Provides long-term, persistent memory and knowledge management for AI assistants, enabling them to store, semantically search, and retrieve conversation context, decisions, and code-related insights.
mcp-server
Provides AI tools with persistent context, semantic code search, and team knowledge sharing across sessions.
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.
amp
Provides a persistent, structured memory (Short-Term, Long-Term, and Graph) for AI agents, mimicking a hippocampus for continuous learning and recall.