Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Semantic Memory MCP Store that I prefer concise code reviews."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Semantic memory for AI agents. Store patterns, search by meaning, remember forever.
š For LLMs: See ARCHITECTURE.md for detailed implementation & TESTING.md for tool reference
Give your AI agents a brain that learns and remembers:
š§ Semantic Search: Find patterns by meaning, not keywords
š¾ Three Memory Types: Semantic (forever), Episodic (90 days), Procedural (forever)
š Intelligence Compounds: Learn from every task, recall before you act
š Auto-Consolidation: Promotes validated patterns automatically
Related MCP server: Memsolus MCP Server
claude mcp add memory -- npx -y github:Sceat/semantic-memory-mcpThen configure environment variables in ~/.claude.json:
{
"mcpServers": {
"memory": {
"env": {
"REDIS_URL": "redis://localhost:6379/0",
"OPENAI_API_KEY": "your-openai-key-here"
}
}
}
}Six tools available immediately:
store_pattern - Save what you learned
search_patterns - Find similar patterns
set_reminder - Never forget important details
check_reminders - Get context before tasks
consolidate_memories - Promote validated patterns
health_check - Verify system status
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā ā
ā Before Task: Query memory for similar patterns ā
ā Check reminders for this task type ā
ā ā
ā During Task: Execute with learned context ā
ā ā
ā After Task: Store what you learned ā
ā Set reminders for next time ā
ā ā
ā Result: Intelligence compounds over time ā
ā ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāIf you want to develop or modify the server:
git clone https://github.com/Sceat/semantic-memory-mcp.git
cd semantic-memory-mcp
npm installThen add to your Claude Code config:
{
"mcpServers": {
"memory": {
"command": "node",
"args": ["/path/to/semantic-memory-mcp/src/index.js"],
"env": {
"REDIS_URL": "redis://localhost:6379/0",
"OPENAI_API_KEY": "your-openai-key-here"
}
}
}
}Node.js ā„ 18
Redis 7.2+ with RediSearch module
OpenAI API key
Claude Code
MIT
This server cannot be deployed
Memory system for AI agents with semantic search. Store and recall memories with ease.
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
