MARM Systems
Persistent memory system with semantic search for AI agents
MARM (Memory Accurate Response Mode) provides a unified, persistent memory layer for AI agents that survives across sessions. Features include semantic search using AI embeddings, auto-classification of content, smart recall with vector similarity, notebook management for reusable instructions, and session logging. Supports HTTP, STDIO, and WebSocket transports.
Source
Repository: https://github.com/lyellr88/marm-memory
Maintain MARM Systems?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/lyellr88-marm-memory?ref=badge) Related mcp
Obsidian Bridges Claude with Obsidian note-taking application, enabling direct interaction with markdown notes through tools for listing, r
Tree-sitter Provides code analysis capabilities through tree-sitter parsing, enabling structured understanding and manipulation of source code
Home Assistant Integrates with Home Assistant to enable natural language control of smart home devices, querying device states, troubleshooting a
Nim Language Server Official Nim language server with MCP support for symbol navigation, diagnostics, and type resolution in Nim projects.
Open Deep Research Performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate co
Ori Mnemos Persistent memory infrastructure for AI agents with identity, knowledge graph, and semantic search.