@renzynx/memory-mcp

A persistent memory MCP server with FTS5 fuzzy search. Compatible with Bun and Node.js.

Features

- Persistent Storage: Data stored in ~/.mcp-memory/memory.db survives npx/bunx cache clears
- Fuzzy Search: FTS5 with trigram tokenization for substring matching (pyth → python)
- Token Efficient: Results in TOON format for minimal token usage
- Auto Maintenance: Prunes entries older than 30 days, creates backups on startup
- Cross Runtime: Works with both Bun and Node.js

Installation

``bash
npx @renzynx/memory-mcp


or


bunx @renzynx/memory-mcp
`

Configuration

$3

Add to ~/.config/opencode/opencode.jsonc:

`jsonc
{
"mcp": {
"memory": {
"type": "local",
"command": ["bunx", "@renzynx/memory-mcp"]
}
}
}
`

$3

Add to claude_desktop_config.json:

`json
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["@renzynx/memory-mcp"]
}
}
}
`

Tools

$3

Store information with a category.

`
save_memory(content: string, category: string)
`

Categories: preferences, facts, context, projects, conventions

$3

Fuzzy search stored memories. Returns TOON format or Ø if empty.

`
search_memories(query: string)
`

$3

List all unique categories. Returns TOON format or Ø if empty.

`
list_categories()
`

Agent Instructions

Add to your agent system prompt:

`


Memory System

You have access to a persistent memory system via MCP tools. Use it proactively to remember important information across sessions.

$3


- save_memory(content, category) - Store information with a category
- search_memories(query) - Fuzzy search (supports partial matches like "pyth" → "python")
- list_categories() - View all memory categories

$3

- User preferences (coding style, tools, frameworks, communication preferences)
- Project context (architecture decisions, file structures, conventions)
- Facts about the user (name, role, team, timezone)
- Recurring tasks or workflows
- Corrections or clarifications the user provides
- Important decisions and their rationale

$3

- preferences - User preferences and settings
- facts - Information about the user or their environment
- projects - Project-specific context and decisions
- conventions - Coding standards and patterns
- context - Session or task context worth preserving

$3

- At the start of conversations to recall user context
- Before making assumptions about preferences
- When the user references something previously discussed
- Before suggesting tools, patterns, or approaches

$3

Results return in TOON format for token efficiency. "Ø" means no results found.

$3

- Save incrementally, not everything at once
- Use specific, searchable content
- Search before asking the user to repeat themselves
- Update memories when information changes (save new version)
``

License

MIT