LEVH provides persistent, searchable memory for AI coding agents, enabling stateful interactions across sessions and tools with adaptive memory decay and reinforcement. It integrates with MCP-compatible clients and offers features like spaced repetition, backups, and a knowledge graph.
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.NEXT_PUBLIC_API_URLSQLITE_DB_PATH— ./stackmemory.db SQLite database pathEMBEDDER_MODE— Defaults work out of the box; set =local for semantic searchGITHUB_TOKENNOTION_API_KEYANSWER_MODELOPENAI_API_KEY— or Whisper output. Each meeting → one summarized memory (LLM if isDOGFOOD_JOURNAL_PATH— (override with ). With the flag unset (the default)OLLAMA_URLOLLAMA_MODEL— nomic-embed-text Ollama embedding modelLOCAL_MODEL— all-MiniLM-L6-v2 Local embedding modelSUMMARY_MODEL— gpt-4o-mini OpenAI chat model used for session summaries[](https://m8ven.ai/mcp/ali-ulu-levh-17ugrn)