A-Mem
Self-evolving memory system with dynamic knowledge graph for AI agents.
A-Mem provides self-evolving memory capabilities for AI agents through a dynamic knowledge graph. When new knowledge is added, the system identifies semantically similar existing memories and strengthens or updates connections between them. Features dual-mode search combining semantic vector similarity with graph traversal, and token-efficient retrieval using lightweight metadata summaries. Supports multiple LLM backends including OpenAI, Ollama, SGLang, and OpenRouter.
Source
Repository: https://github.com/diaaaj/a-mem-mcp
Maintain A-Mem?
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/diaaaj-a-mem-mcp?ref=badge) Related mcp
Sketchfab Integrates with Sketchfab to enable searching, viewing details, and downloading 3D models in various formats using an API key for
Ollama Integrates with Ollama for local large language model inference, enabling text generation and model management without relying on
Giphy Allows AI models to search, retrieve, and utilize GIFs from Giphy.
SearXNG Meta Search Integrates SearXNG's meta-search capabilities to provide privacy-focused, customizable search results from multiple engines for di
Better Notion Integrates with Notion through composite tools that combine multiple operations into unified workflows for page management, databa
X Twitter Provides a bridge between Twitter's API and conversational interfaces, enabling comprehensive platform interaction including profi