MCP server providing persistent AI memory with four-tier retrieval (SQLite FTS5, graph, vector, LLM agent) to give AI assistants structured, long-term memory without RAG.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.SANDBOX_PARAMSOPENROUTER_API_KEY— export =your_key_hereVLLM_HOSTVLLM_PORTUVMCP_TRANSPORTMCP_HOSTMCP_PATHMCP_PORTLMSTUDIO_BASE_URLSUPERMEM_LLM_PROVIDER— export =openrouterSUPERMEM_LLM_MODEL— provider default Model string (e.g. openai/gpt-4o-mini, llama3)OLLAMA_HOSTOLLAMA_DEFAULT_MODELVLLM_DEFAULT_MODELANTHROPIC_API_KEY— _(required for claude)_ Anthropic API keyANTHROPIC_DEFAULT_MODELLMSTUDIO_HOSTLMSTUDIO_DEFAULT_MODELSUPERMEM_DB_PATH— ~/.supermem/supermem.db SQLite database pathSUPERMEM_VAULT_PATH— export =~/notesSUPERMEM_KUZU_PATHSUPERMEM_CHROMA_PATHSUPERMEM_VECTOR— ├─ Tier 3: ChromaDB vector similarity ~50ms optional (=true)SUPERMEM_MAX_TOOL_TURNSSUPERMEM_SANDBOX_TIMEOUTSUPERMEM_COMPRESS_EVERY— 50 Observations written before LLM compressionSUPERMEM_OBS_TTL_DAYSSUPERMEM_API_KEY— _(none)_ Bearer token for HTTP API auth (disabled if unset)SUPERMEM_RATE_LIMIT— 60 Requests/minute limitSUPERMEM_WORKER_PORT— 37777 HTTP dashboard portSUPERMEM_WORKER_HOSTSUPERMEM_MIN_RESULTSSUPERMEM_DEFAULT_TIER_LIMITSUPERMEM_LOG_LEVELSUPERMEM_LOG_FORMAT[](https://m8ven.ai/mcp/lamenting-hawthorn-supermem-10cd4z)