Enables AI coding assistants to store and retrieve project-aware context as plain Markdown files locally, with no cloud or vector database required.
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.MEMORY_FABRIC_LLM_DEBUG— Via Environment Variables: Set the variable in your environment:MEMORY_FABRIC_LLM_PROVIDER— 1. Direct LLM Provider: Uses direct API calls if is set in the environment along with the corresponding API keys.GEMINI_API_KEY— Zero-Config: No need to configure or expose , OPENAI_API_KEY, or ANTHROPIC_API_KEY to the background MCP server process.OPENAI_API_KEY— Zero-Config: No need to configure or expose GEMINI_API_KEY, , or ANTHROPIC_API_KEY to the background MCP server process.OPENAI_API_BASE— OpenAI MEMORY_FABRIC_LLM_PROVIDER=openai<br>OPENAI_API_KEY=your_key<br>OPENAI_MODEL=gpt-4o-mini (opt)<br>=... (opt) Can connect to custom local/remote OpenAI-compatible endpointsOPENAI_BASE_URLOPENAI_MODEL— OpenAI MEMORY_FABRIC_LLM_PROVIDER=openai<br>OPENAI_API_KEY=your_key<br>=gpt-4o-mini (opt)<br>OPENAI_API_BASE=... (opt) Can connect to custom local/remote OpenAI-compatible endpointsANTHROPIC_API_KEY— Zero-Config: No need to configure or expose GEMINI_API_KEY, OPENAI_API_KEY, or to the background MCP server process.OLLAMA_HOST— Ollama MEMORY_FABRIC_LLM_PROVIDER=ollama<br>=... (opt)<br>OLLAMA_MODEL=gemma2 (opt) Offline, local reasoningOLLAMA_MODEL— Ollama MEMORY_FABRIC_LLM_PROVIDER=ollama<br>OLLAMA_HOST=... (opt)<br>=gemma2 (opt) Offline, local reasoningMEMORY_FABRIC_DEDUP_THRESHOLDMEMORY_FABRIC_TOKEN_BUDGETMEMORY_FABRIC_FAILURE_MERGE_THRESHOLDMEMORY_FABRIC_DIRECTIVE_BUDGETMEMORY_FABRIC_MAP_TOKEN_CAP[](https://m8ven.ai/mcp/elvirafa-agentic-memory-c6rpen)