Nowledge Mem
The graph augmented, smart and local-first Personal Context Manager, or Personal Agent Memory, just works.
Nowledge Mem ingests your agent’s summarized memories through its MCP tools or prompts, enabling you to enhance your memory and knowledge using a GraphRAG approach. By leveraging LLMs, embedding models, BM25, graph algorithms, and a built-in knowledge graph, Nowledge Mem makes building, searching, and exploring your personal knowledge easier than ever.
Overview
What is Nowledge Mem?
Nowledge Mem is a graph-augmented, smart, and local-first personal context manager that helps users manage and augment their personal context across different tools and agents, all while ensuring data is stored locally with on-device AI models.
How to use Nowledge Mem?
Users can create memories in Nowledge Mem through three main methods:
- Import from AI Agent Conversations: Configure the Model Context Protocol (MCP) with your AI agent to extract insights from conversations.
- Distill Memories from Conversation Threads: Import long conversation threads from AI tools and distill insights into memories.
- Create Memories Manually: Navigate to the Memories view and click the '+ Create' button to add a new memory.
Key features of Nowledge Mem?
- Local-first storage with on-device AI models.
- Automatic indexing of memories for fast search using BM25 and vector search.
- Integration with various AI agents for seamless memory creation.
- Knowledge graph augmentation for enhanced memory searching and exploration.
Use cases of Nowledge Mem?
- Managing insights from multiple AI conversations.
- Storing and organizing personal knowledge for easy retrieval.
- Enhancing productivity by keeping track of important decisions and findings.
FAQ from Nowledge Mem?
- Can I use Nowledge Mem with any AI agent?
Yes! Nowledge Mem supports various AI agents like Claude, ChatGPT, and more through the Model Context Protocol.
- Is my data safe with Nowledge Mem?
Yes! All data is stored locally on your device, ensuring privacy and security.
- How do I search for my memories?
Memories are indexed for fast search, and you can also explore them using the knowledge graph.
Server Config
{
"mcpServers": {
"nowledge-mem": {
"url": "http://localhost:14242/mcp",
"type": "streamableHttp",
"headers": {
"APP": "Client via MCP.so"
}
}
}
}Project Info
Created At
8 months agoUpdated At
8 months agoAuthor Name
Nowledge Labs, LLCStar
-Language
-License
-Homepage
https://github.com/nowledge-co/Recommend Servers
View AllTavily Mcp
@tavily-ai
JavaScript
a year ago
Playwright Mcp
@microsoft
Playwright MCP server
TypeScript
10 months ago