max-ramas/rms-memory-mcp
by Various
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
MCP
max-ramas/rms-memory-mcp
Added 3 Sept 2026
Overview
A persistent, local memory system for AI agents that uses markdown as the source of truth and LanceDB for semantic search. It operates across IDEs with no cloud dependency, written in Rust.
Best for
Best for
Developers building local-first AI agent workflows
Use cases
- Store and retrieve agent memories locally
- Semantic search over markdown notes
- Maintain cross-IDE context for AI assistants
How to use
Tested with
Claude Code, Cursor, VS Code
Notes
A persistent, local memory system for AI agents that uses markdown as the source of truth and LanceDB for semantic search. It operates across IDEs with no cloud dependency, written in Rust.
37 stars on GitHub. Last updated 2026-07-28. Licensed MIT.
Use cases
- Store and retrieve agent memories locally
- Semantic search over markdown notes
- Maintain cross-IDE context for AI assistants
Pros
- Zero cloud dependency ensures privacy
- Markdown-based source of truth is human-readable
- Semantic search via LanceDB
Cons
- No cloud sync or backup
- Requires local setup and management
- Small community (37 stars) may limit support
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Zero cloud dependency ensures privacy
- Markdown-based source of truth is human-readable
- Semantic search via LanceDB
Cons
- No cloud sync or backup
- Requires local setup and management
- Small community (37 stars) may limit support
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.